The best LLM Wiki & AI Knowledge Base Tools in 2026 is ragflow (rated SAFE by Agent Skills Hub, ★ 94.0k; 352 of 364 tools rated SAFE) — best for developers and AI agents needing llm wiki & ai knowledge base tools. RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a
Build AI-powered knowledge bases with retrieval-augmented generation (RAG) — ingest documents, search semantically, and answer questions.
LLM Wiki & AI Knowledge Base Tools are AI-powered software designed to help developers and teams tackle knowledge base & rag-related tasks more efficiently. These tools are typically published as open-source projects on GitHub and can be integrated into existing workflows via MCP (Model Context Protocol), Claude Skills, or standalone agent frameworks. On Agent Skills Hub, we index 364 quality-scored LLM Wiki & AI Knowledge Base Tools across languages including Python, TypeScript, Go.
In 2026, the AI agent ecosystem is maturing rapidly. LLM Wiki & AI Knowledge Base Tools can significantly boost development efficiency by automating repetitive tasks, reducing human error, and providing intelligent suggestions. The top 3 tools — ragflow, codegraph, OpenViking — have earned an average of 71,508 GitHub stars. 289 of the listed tools come with clear open-source licenses, ensuring freedom to use and modify.
When choosing among LLM Wiki & AI Knowledge Base Tools, consider these factors: 1) Community activity — GitHub stars and recent commit frequency indicate reliability; 2) Integration method — check if it supports MCP, Claude, or your preferred agent framework; 3) Language compatibility — the most common language in this list is Python; 4) Quality score — Agent Skills Hub's 9-dimension quality score rates documentation completeness, structure and agent readiness, not the code. Our recommendation: start with ragflow — it has the most GitHub stars on this list.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
git clone https://github.com/infiniflow/ragflow.git
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
npx @colbymchenry/codegraph # zero-install, or:
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
pip install openviking --upgrade --force-reinstall
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
uv tool install "lightrag-hku[api]"
Langchain-Chatchat(原Langchain-ChatGLM)基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
pip install langchain-chatchat -U
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
git clone https://github.com/Tencent/WeKnora.git
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
uv pip install cognee
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
docker run -d --name=maxkb --restart=always -p 8080:8080 -v ~/.maxkb:/opt/maxkb 1panel/maxkb
LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。
git clone https://github.com/nashsu/llm_wiki.git
AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
git clone https://github.com/xerj-org/xerj
Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme
OpenWiki is a CLI that writes and maintains agent documentation for your codebase.
npm install -g openwiki
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.
git clone https://github.com/AgriciDaniel/claude-obsidian
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.
可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
Open-source context retrieval layer for AI agents
git clone https://github.com/airweave-ai/airweave.git
Your Personal Librarian Agent. Ask anything on your computer, organize files, remember important info and files.
bun install -g @autorag/librarian
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
git clone https://github.com/vitali87/code-graph-rag.git
Persistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents.
git clone https://github.com/eugeniughelbur/obsidian-second-brain ~/.claude/skills/obsidian-second-brain
A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
git clone https://github.com/FlowElement-xinliuyuansu/m_flow.git && cd m_flow
The open-source context layer for AI agents and enterprise AI search. Permission-aware search and cited answers across 30+ sources, including Slack, Drive, Jira, GitHub and Microsoft 365, for people and agents through MCP, SDKs and built-in agents. Self-hosted or Cloud.
git clone https://github.com/pipeshub-ai/pipeshub-ai.git
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
pip install "reme-ai[core]"
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
git clone https://github.com/Ar9av/obsidian-wiki.git
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.
git clone https://github.com/SamurAIGPT/llm-wiki-agent.git
Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as markdown files you own.
/plugin marketplace add agenticnotetaking/arscontexta
AI-native note-taking app & Evernote/Obsidian alternative. Instant all-platform sync, rich notes (tables, mind maps, diagrams, posters), web clipper & MCP. 100% free on Cloudflare or Docker.
bunx wrangler d1 create edgeever
Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
/plugin marketplace add zilliztech/memsearch
A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.
git clone https://github.com/Zleap-AI/SAG.git
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
npx add-skill Astro-Han/karpathy-llm-wiki
Unified research workspace for humans & agents — PDF Q&A with citations, Vault, writing. 为人与 Agent 协作的科研工作台;补齐 Zotero 时代的人机上下文断点。
brew install --cask agentero
A skill for building a personal knowledge base based on Karpathy's llm-wiki methodology, supporting multiple platforms.
Web Crawling and RAG Capabilities for AI Agents and AI Coding Assistants
git clone https://github.com/coleam00/mcp-crawl4ai-rag.git
The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.
npm install -g llm-wiki-compiler
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
git clone https://github.com/paulmchen/synthadoc.git
Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.
/plugin marketplace add microsoftdocs/mcp
Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.
npx mex-agent setup
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !
git clone https://github.com/lucasastorian/llmwiki.git
A minimal, extensible, agent-native knowledge repository that keeps shared context current and inspectable
claude mcp add --transport http openlore http://localhost:8080/mcp
All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine
git clone https://github.com/yuezhiai/jonex.git
Guides and resources for AI engineers: an agents course, five handbooks, a hands-on second-brain project and a vetted reading list.
git clone https://github.com/undefined-ui/second-brain-os.git
🤖 Deploy a private ChatGPT alternative hosted within your VPC. 🔮 Connect it to your organization's knowledge base and use it as a corporate oracle. Supports open-source LLMs like Llama 2, Falcon, and GPT4All.
LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.
Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.
git clone https://github.com/nduckmink/arkon.git
Your entire engineering context, deeply understood
uv tool install chunkhound
Turn one dense paper into an Obsidian note worth keeping: read the way its field reads it, linked to the papers already in your vault, and aimed at your own research. Agent skills for Claude Code, Codex, Cursor, and any agent that supports skills.
npx skills add 917Dhj/DeepPaperNote
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
/plugin marketplace add study8677/repobrain
An AI knowledge base/agent built with .Net 9, AntBlazor, Semantic Kernel, and Kernel Memory, supporting local offline AI large models. It can run offline without an internet connection. Supports Aspire for monitoring application data.
git clone https://github.com/shuyu-labs/AntSK.git
把中文全渠道内容(抖音 / B站 / 小红书 / 公众号 / X / 播客)采集进个人知识库的 14 个 AI Skill:图文存图、视频转文字稿、字幕优先免 GPU、RSS/YouTube 订阅调度与每日情报简报,附带知识库 MCP server。| Ingest Chinese content into your personal knowledge base — image/video routing, subtitle-first transcription, feed subscriptions with daily digests, and a KB MCP server.
git clone https://github.com/chubbyguan/chubbyskills.git
Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
git clone https://github.com/apecloud/ApeRAG.git
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project knowledge across agents and repos.
git clone https://github.com/0xranx/OpenContext.git
A modular RAG (Retrieval-Augmented Generation) system with MCP Server architecture. Using Skill to make AI follow each step of the spec and complete the code 100% by AI.
Agent-ready DevOps, security, infrastructure, and compliance knowledge base with 80+ skills across Kubernetes, Terraform, AWS/Azure/GCP, AI platform operations, container hardening, SOC2/ISO27001, and incident response—plus ready-to-run scripts, templates, and playbooks for SRE, platform, and security teams.
npx skills add bagelhole/DevOps-Security-Agent-Skills
A local-first AI knowledge base & NotebookLM alternative built with Electron. More convenient, more lightweight, and understands you better!
git clone https://github.com/MrSibe/KnowNote.git
:brain: 100% Local Memory layer and Knowledge base for agents with WebUI
git clone https://github.com/mudler/LocalRecall.git
A codebase wiki for AI coding agents. Captures what the code can't say: decisions, flows, invariants, gotchas.
npx codealmanac
Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced agentic code analysis tools through MCP for efficient code agent context management
git clone https://github.com/yourorg/codegraph-rust
AI-powered StartUp Accelerator Engine built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based workflows, and page-level insight extraction.
pnpm add @launchstack/core
One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier.
IncarnaMind is a free, open-source desktop app for macOS, Windows and Linux where you write with AI and ask questions about your own documents (PDF, Word, PowerPoint, Excel and more). It can check every sentence and figure in a draft against those documents, whoever wrote it, and every answer cites the exact page it comes from.
git clone https://github.com/junruxiong/IncarnaMind.git && cd IncarnaMind
Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.
git clone https://github.com/kytmanov/obsidian-llm-wiki-local
Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.
git clone https://github.com/verygoodplugins/automem.git
Ontology-Augmented Generation for AI agents.
git clone https://github.com/FengZhenfei/carrel.git
Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.
LLM-maintained personal knowledge base for Obsidian. Based on Andrej Karpathy's LLM Wiki pattern.
npx skills add NicholasSpisak/second-brain
Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.
pip install git+https://github.com/agentic-box/memora.git
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.
npm install -g megamemory
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
npm install -g @swarmvaultai/cli
MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globally sync your mind for all agents: transparent, controllable, and evolving symbiotically.
npm install -g @geminilight/mindos@latest
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.
pip install raglight
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
pip install haiku.rag
Karpathy-style LLM knowledge base Agent Skill for OpenClaw/Codex. Experimental — will iterate over time.
Agent-native knowledge engine with MCP tools for document indexing, wiki organization, fast retrieval and deep reading across PDF/DOCX/PPTX/Markdown
sage-wiki is a graph memory and knowledge base that AI agents and humans build and query together. Drop in documents; an LLM compiler turns them into an interlinked wiki with a knowledge graph. One Go binary scales it from a personal vault to a team hub to a company knowledge graph.
go install github.com/xoai/sage-wiki/cmd/sage-wiki@latest
An Obsidian knowledge base based on Andrej Karpathy's LLM Wiki pattern, using an LLM to maintain a compounding personal knowledge layer.
Self-maintaining, Obsidian-compatible knowledge base for pi — turn raw sources into an interlinked wiki that compounds. Native Open Knowledge Format (OKF) v0.2.
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
git clone https://github.com/benmaster82/Kwipu.git
⚡ DocsAgent — chat with your Zotero library from your phone. Native iPhone app + free Mac companion. MCP server for Claude, Cursor & Cline: instant, private search over Zotero, Obsidian & Apple Notes, fully local (~15 ms).
npm install -g @docsagent/docsagent
MCP (Model Context Protocol) server for game hacking & reverse engineering. A structured knowledge base of 4,100+ skills with full source code archives, specialized agents, and workflow tools -- designed to be plugged into Claude, Cursor, or any MCP-compatible client.
Re-debugging Solved Failures? No Way. 1000+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org
git clone https://github.com/Ikalus1988/MisakaNet.git && cd MisakaNet
NVIDIA Auto Ontology's semantic layer and a personal knowledge base as an MCP server for Claude, ChatGPT and other MCP clients. No LLM API key needed.
uvx --from git+https://github.com/gogoymh/auto-ontology-mcp auto-ontology-mcp demo
A studio for everything you think, learn, and build with AI. It gathers notes and memories from every AI tool into pages, skills and rules that stay current and fully customizable. Open source. For you and your team.
Transforms Unity Catalog tables into a dynamic, understandable knowledge graph, with ontology design and reasoning exposed to AI agents as MCP tools
Asisten crypto berbahasa Indonesia: RAG pengetahuan 267 topik + data pasar realtime (6 bursa, WebSocket, derivatif, on-chain, TVL, DeFi) + tool-calling agent + LLM synthesis
An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vault. Runs 24/7 on the Claude subscription you already have.
Your First LLM-Wiki Conversation Knowledge Base
git clone https://github.com/beever-ai/beever-atlas.git
A local-first personal knowledge layer for AI agents. Build evolving knowledge spaces with LLM Wiki, knowledge graphs, and agent workflows.
git clone https://github.com/zhuzhaoyun/Molio.git && cd Molio
Karpathy-style LLM knowledge base for Obsidian. Clone, run Claude Code, start building your second brain.
git clone https://github.com/shannhk/llm-wikid.git my-wiki
Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.
npx mcp-local-rag ingest ./docs/
Talk with your notes in Claude. RAG over your Apple Notes using Model Context Protocol.
git clone https://github.com/RafalWilinski/mcp-apple-notes
LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped.
git clone https://github.com/Pratiyush/llm-wiki.git
A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.
git clone https://github.com/Ayanami0730/arag.git && cd arag
A Docker-powered RAG system that understands the difference between code and prose. Ingest your codebase and documentation, then query them with full privacy and zero configuration.
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
npx @modelcontextprotocol/inspector uv run --with mcp-logseq mcp-logseq
Private, local RAGs. Supercharge LLMs with your own knowledge base.
npm install react-native-rag
MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero-setup 🎯 Perfect for: New frameworks • API docs • Internal guides
npx skills add https://github.com/andrea9293/mcp-documentation-server --skill documentation-server
台灣法律 MCP 伺服器 + CLI(免費、免金鑰,連接時登入法律偵探帳號):2,280 萬筆裁判書、行政函釋、憲法法庭裁判,附引用查核。Free Taiwan legal MCP server for Claude/ChatGPT/Codex: sign in with a Dr.Legal account, bring your own LLM, retrieval-only.
pip install twlegalrag
A personal knowledge base system based on Andrej Kapathy's llm-wiki concept, organizing source materials, LLM-compiled knowledge, ideas in progress, and finish…
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
git clone https://github.com/aayoawoyemi/Ori-Mnemos.git
Claude Code plugin that compiles markdown knowledge files into a topic-based wiki. Implements Karpathy's LLM Knowledge Base pattern.
git clone https://github.com/ussumant/llm-wiki-compiler.git
VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.
git clone https://github.com/bibinprathap/VeritasGraph.git && cd VeritasGraph
A Easy way to create your own Knowledge-base! Notemd enhances your Obsidian workflow by integrating with various Large Language Models (LLMs) to process your notes, automatically generate wiki-links for key concepts, create corresponding concept notes, perform web research, and more.
Turn your Claude Code session history into a searchable local knowledge base — 13 MCP tools, pure stdlib, nothing leaves your machine
git clone https://github.com/nameforjt-afk/session-knowledge.git
Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.
pip install knowledge-rag
Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW: 99.5% right note read vs 79%, 1.6× faster ingest, 63% fewer LLM tokens, no scaling limit.
git clone https://github.com/crow-hq/llm-wiki-v2 && cd llm-wiki-v2
🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.
git clone https://github.com/Govcraft/rust-docs-mcp-server.git
A lightweight RAG learning project with Streamlit, LangChain, and Chroma for local knowledge uploads, retrieval-augmented Q&A, and chat.
LLM-powered trading review knowledge base for traders: quick reviews, trade imports, FIFO P&L, stock archives, and screenshot discussions.
Revornix is an open-source, local-first AI information/markdown workspace. It helps you collect fragmented inputs, turn them into structured knowledge, generate reports with images and podcast audio, and deliver the output through automated notifications.
Turn Google Search, Papers, and Codebases into an Automatic Local Knowledge Graph for AI Agents.
npx google-surf-mcp # actual MCP - register in client config
CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.
git clone https://github.com/thomasunise/casecite.git && cd casecite
Chunkless RAG for AI agents, powered by Docling. Parse your PDFs, inspect every title, table and box on the page, then let any MCP client (Claude, Cursor…) read only the sections it needs under a token budget and cite exact, server-verified passages. No chunks, no embeddings, no vector store.
docker run -p 3000:3000 ghcr.io/scub-france/docling-studio:latest-local
Build your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinforced memory. Importantly use selected context to automatically generate skills, empowered by Claude subagents + CodeAct pipeline and gated by human review. **Try Live Demo**: https://byo-wiki-demo.vercel.app
Open-source template for building LLM-powered knowledge bases following Karpathy's LLM Wiki pattern
More than just Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.
pip install synto
(AAAI 2026) Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval
git clone https://github.com/RaZzzyz/LeanRAG.git
301 open-source coding agent skills across 22 domains — methodology, judgment & gotchas packaged as Claude Agent Skills for the Asgard AI Platform.
OnCo: total information dominance on cancer. A public, cited knowledge graph of oncology with a website, JSON API, MCP server and CLI: one page per cancer, treatment, target, trial, institution, person and idea.
Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.
LLM Wiki - Build a continuously growing personal knowledge base with LLMs, including a Claude Code skill and hands-on experience.
git clone https://github.com/你的用户名/llm-wiki.git
Amazon Bedrock Foundation models with Amazon Opensearch Serverless as a Vector DB
git clone https://github.com/aws-samples/serverless-rag-demo.git
LeanKG: Stop Burning Tokens. Start Coding Lean.
cargo install leankg && leankg --version
Hệ thống knowledge base cá nhân hoàn toàn tự động, vận hành bởi LLM. Dựa trên pattern LLM Wiki của Andrej Karpathy.
git clone https://github.com/mduongvandinh/llm-wiki.git my-wiki
🔍 Deep RAG: Advanced Retrieval-Augmented Generation system that goes beyond vector search. Enables AI to perform multi-hop reasoning, negation queries, numerical comparisons & global aggregation on your knowledge base. Supports OpenAI, Anthropic, Google Gemini. Python FastAPI + React UI
git clone https://github.com/boluo2077/deep-rag.git
Local-first code intelligence for AI assistants. Turns your codebase into a knowledge graph your AI can query, navigate, and remember. 25 MCP tools.
brew install aouicher/graphmind/graphmind # CLI
an AI interaction tool with RAG hybrid search, conversation context, web content processing and structured data analysis with LLM / GPT
git clone https://github.com/EdwardDali/erag.git && cd erag
GraphRAG, RAG, LlamaIndex, LangChain, 15 Prop Graph, 4 RDF, 10 Vector, 3 Search DBs. 14 data srcs, auto sync, Alfresco, Nuxeo, SharePoint, Box, CMIS, S3,GCS,Azure, web. KG auto-bld, Ontologies, 13 LLM providers, Docling, LlamaParse, LiteParse, Hybrid Search, AI Chat. TypeScript React, Vue, Angular, Python, REST, MCP, OpenArch, Langflow, CocoIndex.
A fully functional knowledge base platform offering robust content management, AI-powered intelligent Q&A, and a modern user experience 一个功能完善的Agentic RAG知识库平台,提供强大的内容管理、AI 智能问答和现代化的用户体验
git clone https://github.com/bulolo/CatWiki.git
Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning intelligence pipeline.
git clone https://github.com/willynikes2/knowledge-base-server.git
LLM-maintained personal wiki skills for Claude Code — implements Karpathy's LLM Wiki pattern
/plugin marketplace add kfchou/wiki-skills
[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
The World's Most Comprehensive, Authoritative, and Structured Open Source Data Source Knowledge Base
OKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles through an ecosystem of Skills, MCP, an interactive graph, TUI, CLI, Docker, and a Claude Code plugin. 100% local.
gem install okf
A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed Agent Skills. https://ascend-ai-coding.github.io/awesome-ascend-skills/
npx skills add https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/base -s '*'
📚 Student LLM Wiki — AI-compiled knowledge base for university students. Drop course slides, get a persistent interlinked wiki. Feynman review, exam prep, confidence decay, cross-course connections. Based on Karpathy's LLM Wiki pattern. Works with Claude Cowork / Claude Code / Claudian + Obsidian.学生大语言模型维基百科——专为大学生打造的AI编译知识库。
git clone https://github.com/IssacW228/student-llm-wiki.git
Terminal-vibe sunum + LLM-Wiki skill'i. Ham sohbetleri, şemayla disipline edilen büyüyen bir wiki'ye dönüştürme deseni.
Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.
git clone https://github.com/alfadur7/llm-wiki-newsroom.git
Agentic RAG over one PDF or a whole folder, with page-level evidence to check every answer: hybrid search, selective page reads, tables, OCR, charts, and CJK layouts.
pip install pdf-mcp
A Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, explore and synthesize atomic notes through Claude and other MCP-compatible clients.
git clone https://github.com/entanglr/zettelkasten-mcp.git
AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.
/plugin marketplace add dnotitia/akb # Claude Code
AI-native codebase intelligence skills — generate persistent .nexus-map/ knowledge bases and instantly query file structure, dependency graphs, and change impact. Built for Copilot, Cursor, and any tool-calling LLM. 面向 AI 编程助手的代码库感知技能——生成持久化知识图谱,精准查询文件结构、依赖关系与改动影响半径。
npx skills add haaaiawd/nexus-skills
Transform your codebase into an intelligent knowledge base for AI-powered development with Cursor IDE, Google AntiGravity, and MCP-enabled assistants
git clone https://github.com/ali-kamali/Axon.MCP.Server.git
Build Karpathy's LLM Wiki with Claude Code. L1/L2 cache architecture. Logseq + Obsidian support.
git clone https://github.com/MehmetGoekce/llm-wiki.git
A personal knowledge base that lives in this folder. Drop content in, have it organized automatically, ask questions, and get sourced answers — either through Claude Code slash commands or a local web dashboard.
A context harness for AI agents: all your scattered context — code, memory, docs, databases, SaaS — in one searchable, browsable, file-like interface.
npx skills add zilliztech/mfs --all -g
Local-first compile step for knowledge bases. Save 350x cost, 1000x speed vs. frontier models
Uses Karpathy llm-wiki and AI to build a personal wiki from multiple sources, publish it with Quartz, and expose it via API through claude_agent_sdk.
npx skills add https://github.com/nashsu/llm_wiki_skill.git --skill llm-wiki
A self-hosted knowledge platform for humans and AI agents — publish wikis, blogs, and portable Agent Skills.
git clone https://github.com/Ciao1019/Petrichor.git
Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.
claude mcp add kaas -- kb-ai mcp
DocMason is a repo-native agent that turns your complex office files into a local LLM knowledge base and your second brain. The repo is the app. Codex is the runtime.
An extension of Karpathy's LLM Wiki pattern: atom layer, topic-branches, two-layer Lint. Distilled from running the pattern end-to-end.
Local-first scientific literature RAG with frozen evidence, exact human annotations, blind dual-reviewer paper screening with conflict resolution and Cohen's kappa, ASReview-style active-learning prioritization, LaTeX-safe BibTeX export, and reproducible offline workflows.
git clone https://github.com/Francis1998/scholar-rag-agent.git
Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG
npx -y @smithery/cli install mcp-pinecone --client claude
Self-improving, AI-native markdown vault you hand to an AI agent. GitHub-style file tree + Notion editing, exposed to Claude/Cursor via a built-in MCP server (24 tools): semantic & hybrid search, RAG, cited answers. Learns your voice from your edits; human-approved review queue. Local-first .md.
2026 AI project: AI政策通 and ReAct agent LvManus; Spring Boot 3/Java 21/Spring AI, LLMs, RAG, MCP, Tool Calling, multimodal, React, Docker, Nginx.
Human memory, for agents. Scalable, private, personal knowledge base for any LLM provider.
pip install openaugi
A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.
npm i -g @arihantdeva/heimdall
Karpathy's LLM Wiki idea as a product — an AI that builds and maintains a markdown wiki from your notes and sources. MCP server + web UI, runs on free local models (Ollama), no API key needed. MIT.
/plugin marketplace add frankchu91/mindbase-llm-wiki
Open Source, Self-Hosted, AI Search and LLM.txt for your website
npx @ragrabbit/mcp", "http://<RagRabbit install>/", "<name of your documentation>"
Kappa Graph — κ(G). A semantic knowledge graph where knowledge has weight. Extracts concepts, measures grounding strength, preserves disagreement, traces everything to source.
git clone https://github.com/aaronsb/knowledge-graph-system.git
Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.
git clone https://github.com/ctxr-dev/llm-wiki-memory ./.llm-wiki-memory/src
An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.
git clone https://github.com/radimsem/remindb.git
Local-first AI knowledge app and Agent Skill with evidence-backed Wiki, an interactive knowledge universe, Viki Q&A, and shareable knowledge galaxies.
git clone https://github.com/NimaChu/my-wiki.git
OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session
/plugin marketplace add guhcostan/claude-mega-brain
Persistent memory plugin for Codex. Obsidian-style knowledge base that survives across sessions
git clone https://github.com/psinetron/echoes-vault-codex.git
Memory Engine is a local-first MCP server that gives coding agents persistent, evidence-backed project memory. It automatically builds a project knowledge base, retrieves relevant architecture, constraints, incidents, and source context before complex tasks, and retains verified lessons after successful work.
git clone https://github.com/uudam42/agent-memory-engine.git
Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sources with citations.
npm install -g opendocuments
md+git knowledge base: FTS5 search (bm25+trigram/fuzzy), HTML+graph, code-ontology linter, Claude Code plugin
/plugin marketplace add vakovalskii/ontoship
Memoriki - LLM Wiki + MemPalace. Personal knowledge base with real memory.
git clone https://github.com/AyanbekDos/memoriki.git my-knowledge-base
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
/plugin marketplace add praneybehl/llm-wiki-plugin
An Agent Skill based on Andrej Karpathy’s LLM Wiki pattern, using a four-stage pipeline to turn fragmented information into a structured, searchable, growing p…
Turn your LLM into a wiki maintainer. Inspired by Karpathy's LLM Wiki. Built for Obsidian, Claude Code & Codex. | 让 LLM 成为你的 wiki 维护者。受 Karpathy 的 LLM Wiki 启发。面向 Obsidian、Claude Code 和 Codex 构建。
JAVA版本的检索增强生成(RAG)项目,包括知识库、搜索 | JAVA version of retrieval enhancement generation(RAG) project ,including knowledge base, search
Local-first RAG memory for AI agents: hybrid + GraphRAG search, MCP server with OAuth 2.1, plugin for Claude Code / OpenCode / Codex.
pip install agent-brain-rag agent-brain-cli agent-brain-ag-mcp
Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST API and MCP support for AI clients.
bun install -g @gmickel/gno
An "LLM wiki" upgraded to a real database — typed entities, graph relations, HTTP API, and a built-in natural-language agent.
git clone https://github.com/dimknaf/braindb.git
Cross-border e-commerce AI knowledge base, read by people and installed by agents: 69 trilingual guides, 878 prompts, a 100-entity / 322-constraint ontology, and 9 skills as a Claude Code plugin or over MCP. Factual claims are dated and CI-verified. CC0.
/plugin marketplace add kangise/ecommerce-ai-skills
Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills
/plugin marketplace add iurykrieger/claude-bedrock
LLM Wiki — Claude Code plugin for persistent, compounding knowledge bases in Obsidian
claude plugin install /path/to/llm-wiki
Inspired by Andrej Karpathy's llm-wiki — the idea that LLMs should maintain a persistent, compounding wiki rather than re-derive answers from raw sources on every query. https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f
npm install -g axiom-wiki
VS Code extension for a self-maintaining personal wiki — the LLM summarizes, cross-references, and files every source for you
Open-source semantic document search (RAG) engine with FastAPI and instant self-hosted deployment
pip install flamehaven-filesearch
The open framework AI agents use to share knowledge with one another. Pack knowledge into a portable, verifiable Knowledge Image, pin it by digest, mount it locally over MCP, and prove what was used. Local-first, deterministic, no vector DB required.
npm install @knolo/reflex @knolo/core
Chat with the videos you've saved: evidence-backed answers with timestamps that jump back to the source. Browser extension + MCP, self-hostable. 和你收藏的视频对话,答案带时间戳,一键回到原视频。
git clone https://github.com/deequoique/stashseek.git
Self-hosted AI agent memory — MCP memory server with durable recall for agents
git clone https://github.com/mtrnix/metronix-memory.git
Agent-native persistent knowledge management — compile knowledge once, query forever.
npm install -g @jackwener/llm-wiki
Indexed knowledge bases with command-line tools for agents.
pip install plasma-wiki
Karpathy Wiki - Claude Code skills for building persistent, compounding knowledge bases. Based on Andrej Karpathy's LLM Wiki pattern.
git clone https://github.com/toolboxmd/karpathy-wiki ~/dev/karpathy-wiki
An AI-powered Quran knowledge graph — place verses on a canvas and discover thematic, linguistic, and theological connections.
CLI tool for LLM agents to build and maintain personal knowledge bases
npm install -g llmwiki-cli
Enterprise-oriented RAG knowledge base system
git clone https://github.com/Pengc-Sun/enterprise-rag-knowledge-base.git
Two Claude Code skills for building a Karpathy-style LLM wiki — a compounding AI second brain. Install: git clone https://github.com/NulightJens/ai-second-brain-skills.git && ln -s $(pwd)/ai-second-brain-skills/llm-wiki-setup ~/.claude/skills/llm-wiki-setup && ln -s $(pwd)/ai-second-brain-skills/wiki-self-heal ~/.claude/skills/wiki-self-heal
git clone https://github.com/NulightJens/ai-second-brain-skills.git ~/ai-second-brain-skills
Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.
uvx --from matryca-plumber matryca-plumber status
LLM Wiki template — Karpathy 3-layer pattern + Gold In Gold Out purpose gate + dual Claude Code·Codex harness (11 commands, 2 hooks, 18 web clipper templates)
git clone https://github.com/johnfkoo951/cmds-llm-wiki.git my-llm-wiki
Your brain, then your team's brain, then your agents' brain. Drop in documents and it compounds them into an interlinked markdown wiki you own — readable in Obsidian, synced through your own private GitHub repo. Share it with a cohort. Coding agents resume from it across sessions, models and machines.
git clone https://github.com/talirezun/the-curator.git
Claude Code / Codex 共用的长期记忆 MCP:本地 Markdown/Obsidian 存储,跨工具记住你的项目与偏好|Local-first shared memory MCP for Claude Code & Codex
Modular Context | Karpathy LLM Knowledge Base + Gmail & G-Cal — multi-account MCP server for Claude Code, encrypted local-first
AI-powered universal search for all your personal data, tailored just for you. Goal:The world's first product with "edge-side LLMs + consumer data localization" as its core development direction.
AI knowledge base for empirical economics and management research, from literature review to Stata, based on Karpathy’s LLM-Wiki and 10 entity types.
git clone https://github.com/Lambenthan/empiricalwiki.git
AI agent skill that remembers every technical decision & bug fix across sessions — and learns from them. v4.0, MIT. | 跨会话记忆的AI编程助手知识大脑
git clone https://github.com/Tubo2333/obsidian-knowledge-brain.git .claude/skills/obsidian-knowledge-brain/
Shared memory for AI coding tools: hybrid search, cited Q&A, harness memory discovery and a built-in Web console. Local index, MCP + HTTP.
pip install "loci-rag[pdf,docx]" # optional extras: PDF w/ tables, Word documents
Self-hosted semantic memory for AI agents, served over MCP. Persistent sessions, experience scoring, a graveyard for dead ends and skills compiled from what worked, plus knowledge from the RSS feeds you read. One Rust binary on SQLite: a tray app for macOS, Windows and Linux, or a server.
A memory governance engine for multi-agent cloud knowledge bases — one knowledge base shared by every agent and every device, with consistency guaranteed. Pure Markdown, nine governance automations, zero dependencies.
An agent based LLM assistant that extends RAG with batch entity extraction and SQL querying to improve performance on multi-step and analytical questions.
Create an LLM Wiki knowledge base in one command — based on Andrej Karpathy's LLM Wiki pattern.
npx skills add eleven-net-cn/llm-wiki-starter -g
Knowledge base & RAG plugin for DeepSeek Harness (DSH): chunking, local embeddings, hybrid search, management panel
Claude Code Plugin for Self-maintaining research knowledge graph for Claude Code + Obsidian
Official Findings of EMNLP 2026 implementation of Corpus2Skill: compile a document corpus into a navigable skill hierarchy that LLM agents explore at query time, with document lookup instead of a serving-time vector-search service.
MMGraphRAG is a multi-modal knowledge graph-based framework designed to enhance complex reasoning tasks, such as multi-modal document question-answering. It integrates text and image data into a fine-grained, structured knowledge graph, utilizing scene graphs for image data and a spectral clustering-based fusion module.
Kenjaku is a Karpathy-style LLM wiki, reinforced where it counts with battle-tested software (including a local RAG).
Turn Google Drive PDFs into Obsidian wiki notes via NotebookLM MCP without loading full PDFs into Claude context
Open-source, self-hostable markdown team wiki with a built-in MCP server — so AI agents read, write, and search your docs as first-class teammates. Live multiplayer, semantic + full-text search. Go + PostgreSQL + React/Milkdown.
git clone https://github.com/zcag/tela.git
Semiont supports human+ai collaborative knowledge work. Use it as: a Wiki, Semantic Layer, Context Graph, Knowledge Base, Annotator, Research Tool, or Agentic Memory...
The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.
git clone https://github.com/zby/commonplace.git
An agent skill to evolve the quality of LLM-Wiki (Graphify) at test time.
🚀 基于 Claude Agent SDK 的智能代码分析工具 | AI-powered code analyzer that generates business-oriented knowledge base and PRD docs. Supports 165+ languages.
The AI-assisted, open-source alternative to Notion and Confluence: a team wiki that lives in Git, with real-time editing, data tables, whiteboards, offline mode, and first-class AI agents. Live demo: https://demo.foliowiki.online
git clone https://github.com/evergreen-it-dev/folio.git
An open source, self-maintaining LLM-wiki. It turns what you save into cited wiki pages, updates them as you save more, and answers your AI agent over MCP.
git clone https://github.com/tuirk/Kompl.git kompl
This project is a local knowledge base "Logistics Industry" question-answering system based on the **RAG (Retrieval-Augmented Generation) technology**.
A permanent Markdown knowledge base template that Claude Code synthesizes and maintains as a wiki from raw sources (LLM Wiki, Karpathy pattern)
MyKG Knowledge Graph Engine: Turn raw files into knowledge graphs with induced ontology
pip install mykg
OMem (Office Memory) — local-first memory that automatically ingests your real work (mail, calendar, notes, files) from where it already lives, into a Markdown wiki any AI agent can query. macOS today; Windows coming.
npx skills add seacen/omem --global
Omnia Vault - the all-in-one project brain: an Obsidian LLM wiki, Graphify code graphs, a living plan that triages new videos against itself, and a Claude Code ⇄ Codex relay. Everything your project knows, in one clonable vault.
git clone https://github.com/gavishap/omnia-vault.git my-project
Socratic is a framework for building reliable vertical AI agents by letting human experts teach agents interactively, turning tacit domain knowledge into a continuously improving knowledge base.
git clone https://github.com/kevins981/Socratic.git
Turn your team's AI coding sessions, GitHub code, and docs into one shared, searchable memory — a self-hosted git truth store you query right from your editor over MCP.
git clone https://github.com/Asklear/Klear-Team-Brain.git && cd Klear-Team-Brain
PaperPilot: a LangGraph system using recursive Deep Research, LLM Wiki, and Obsidian to turn research into traceable, queryable long-term knowledge.
git clone https://github.com/boluodaixue/paperpilot.git
A beginner-friendly and extensible Agentic RAG project that demonstrates the full pipeline of document parsing, retrieval, reranking, workflow orchestration, tool calling, and answer generation, designed for both learning and secondary development.
Schema-as-code memory for AI agents in Obsidian: typed cards, entity dedup, link repair, update-in-place, and Ebbinghaus decay. Plain Markdown you own — a Claude Code skill.
/plugin marketplace add smixs/autograph
Self-hosted memory server for AI agents. Your brain is a git repo, served over MCP and REST.
An LLM Agent-driven system for local Markdown literature library management and automated academic reviews
Scrape YouTube videos, extract transcripts, and build a semantic search AI knowledge base using RAG and FAISS.
Skill for Claude, Cursor & Copilot that automates the Karpathy LLM Wiki workflow: ingest web, GitHub, and YouTube URLs into a well-structured, citable, cross-referenced knowledge base with automatic linting.
npx skills@latest add ndjordjevic/pin-llm-wiki -g # global
Source-grounded MCP memory runtime and Obsidian-compatible vault template for LLM agents.
The ATLAS Agent helps answer questions about the MITRE ATLAS Framework by leveraging the ATLAS Knowledge Graph.
Open-source knowledge base for people and AI agents. Rich-text editing, hybrid search, GraphRAG, and MCP. Self-host with Docker or use DocsMint Cloud.
git clone https://github.com/HiAi-gg/docsmint.git
Agent Fusion is a local RAG semantic search engine that gives AI agents instant access to your code, documentation (Markdown, Word, PDF). Query your codebase from code agents without hallucinations. Runs 100% locally, includes a lightweight embedding model, and optional multi-agent task orchestration. Deploy with a single JAR
DeepSeek V4-Flash Vision RAG answers questions about text and scanned PDFs, gives page numbers, shows originals, and reads charts, tables, code, and formulas.
A git template for building your own LLM-powered personal wiki. Training period, metadata standard, lint system included. Clone and go.
Nia is a context-augmentation layer for agents, primarily designed for coding agents. It provides them with an up-to-date knowledge base and improves their performance by 27%.
npx nia-wizard@latest
Agent Skills plugin for a persistent LLM-managed markdown wiki — ingest, cross-reference, cited queries and lint with 5 stdlib scripts
git clone https://github.com/sametbrr/llm-wiki-manager ~/.claude/skills/llm-wiki-manager
DeepSeek V4-Flash Vision Video RAG uses deepseek-v4-flash-vision-exp to answer video questions with timestamps, clips, keyframes, and HTML previews.
Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with every conversation. Works with Obsidian, Logseq, etc. or just folders on your local drive. Compiled memory for your LLM sessions. Crossplatform. GUI install on Claude Desktop, no terminal, no code.
npx skills add vanillaflava/llm-wiki-skills --all
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
claude plugin install agentcairn@agentcairn
Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions.
Build a knowledge base into a tar.gz and give it to this MCP server, and it is ready to serve.
uv pip install kb-mcp-server
Byte-Vision is a privacy-first document intelligence platform that transforms static documents into an interactive, searchable knowledge base. Built on Elasticsearch with RAG (Retrieval-Augmented Generation) capabilities, it offers document parsing, OCR processing, and a modern UI.
git clone https://github.com/kbrisso/byte-vision.git
A local model engine with a search engine and web crawler built in. Run your coding agents on your own GPUs, and get cited answers from your files, code, and the sites you crawl. One executable.
pip install --upgrade --pre lilbee
High precision industrial grade RAG solution based on knowledge graph multi-channel recall
git clone https://github.com/loukie7/Datacapsule.git
Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.
npm install -g @syasas/llm-wiki
Karpathy-style personal wiki for LLMs - markdown + frontmatter, no vector DB, no RAG. Built for Claude Code, works with any file-editing AI agent.
git clone https://github.com/Benboerba620/karpathy-claude-wiki.git
LLM-managed personal knowledge base. Auto-extracts from git repos, Claude Code sessions (via ccrider FTS5), and iMessage bookmarks. Cross-project, qmd-indexed, runs on cron
brew install oliver-kriska/scribe/scribe
Retrieval tools for coding agents, no model in the loop: SOTA-competitive files, search, read, code_pack and write_note over the folder your session is opened in, served over MCP.
uv tool install 'silica-core[mcp]' # BM25 over documents and their sections (faster, lighter)
OpenCodeRAG is a RAG (Retrieval-Augmented Generation) plugin for semantic code search powered by locally-hosted embedding models. It features a seamless integration with OpenCode and other AI tools via MCP and offers a CLI interface for external usage. It offers hybrid search, image description, persistent memory and local decision model usage.
npm install -g opencode-rag-plugin
A RAG (Retrieval-Augmented Generation) knowledge base system with Vue.js frontend, Spring Boot backend, and FastAPI LLM service.
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
pip install zettelforge
A git-native, review-gated knowledge base for AI agents: they propose writes, you approve them. Every claim cites a source, every change is a diff in your repo. MCP + CLI.
pipx install vouch-kb
A local-first AI memory system with hybrid search, MCP integration, and a knowledge graph.
git clone https://github.com/MihaiBuilds/memory-vault.git
Git-backed shared memory for AI agent fleets: searchable knowledge base, incident and task tracking, every write versioned and attributed. CLI, HTTP API and MCP server.
npx skills add alex09x/kyb
The bridge between human-readable wikis and machine-speed memory. Built on Karpathys LLM Wiki pattern + Memvid.
git clone https://github.com/tashisleepy/knowledge-engine.git
Bedrock Knowledge Base and Agents for Retrieval Augmented Generation (RAG)
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency
brew install rms-memory-mcp
Chat with your knowledge base — a conversational RAG agent (LangGraph + OpenRouter) built on Fast Dash's native chat mode. A modern rebuild of the original Embedchain demo.
Markdown vector search MCP server for Claude Code. Natural language search for markdown files using multilingual-e5-small embeddings.
A local dual-layer memory pattern for AI agents: a compact, human-readable markdown index paired with semantic retrieval from a local vector store, queried before each message. For cross-project recall where flat memory files or vector-only RAG fall short. Local-first. Reference implementation.
pip install zer0dex
LLM-powered personal knowledge base — raw articles → compiled wiki → Q&A + outputs. Claude writes, you curate.
git clone https://github.com/hoadoan1997/llm-knowledge-base.git
Source code graph RAG (GraphRAG) for C/C++ development based on clang/clangd
git clone https://github.com/2015xli/clangd-graph-rag.git
Tapestry - a lightweight bookmark knowledge base based on an Agent Skill Bundle
claude plugin install tapestry@tapestry-skills
Find your files with natural language and ask questions.
git clone https://github.com/shredEngineer/Archive-Agent
Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.
npm install -g chatcrystal
Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube - your agent remembers forever. Based on Karpathy's LLM Wiki pattern.
pip install "llm-wiki-kit[all] @ git+https://github.com/iamsashank09/llm-wiki-kit.git"
AI-powered second brain for Claude Code that builds itself. Extract knowledge from every session—past and present—into auto-organized Markdown. Local-first, queryable, learns your patterns.
claude plugin install remember@remember-md
Semi-automated research assistant and local knowledge base for paper analysis, ideation, coding, experiments, writing, and publication workflows.
Zissa Wiki — an LLM-maintained research knowledge base in plain markdown, maintained by any AI agent (Claude, Codex, Gemini, DeepSeek, Kimi, Grok, Mistral or any chat app). Implements Karpathy's LLM Wiki pattern; checks every quote against its source.
A cross-platform note-taking Agent app with multiple note formats, a local knowledge base, an AI assistant, and vector semantic search.
Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB. Nothing leaves your machine.
uvx --from git+https://github.com/sfrangulov/minirag-mcp minirag-mcp
Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.
git clone https://github.com/sparkplug604/praxis.git
Give Claude semantic memory of your Obsidian vault — local semantic search over Smart Connections embeddings via MCP. Multi-vault, block-level, 100% private.
git clone https://github.com/msdanyg/smart-connections-mcp.git
A MCP server that is a locally running knowledge base with a hybrid vector and graph RAG engine using LightRAG
uvx knowledge-mcp --base <path-to-dir-containing-config.yaml> <command> [arguments...]
LLMs as Collaboratively Edited Knowledge Bases
git clone https://github.com/laramohan/wikillm
A dual-path memory system for proactive agents. Facts and procedures in a local knowledge graph, exposed as a CLI, MCP tools and skills. No API key.
pip install memoose # or: pipx install memoose, or uvx memoose --help
Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server for seamless AI assistant integration.
pip install qdrant-loader qdrant-loader-mcp-server
Local LLM-maintained personal wiki, built on Karpathy's LLM-Wiki pattern. Runs on Ollama + Qwen3 + QMD.
MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik
bunx @tikoci/rosetta --setup
Sample for context-aware Agentic RaG, Q&A with multi-source verification, and self-curating knowledge base. Powered by Azure AI Foundry Agent Service, Azure AI Search with agentic retrieval and query rewrite, Semantic Kernel and LangGraph agents running in Azure Container Apps, and ready for Copilot Studio
A database-agnostic Agentic GraphRAG framework using swappable System One models (local Laya / cloud Jev). A plug-and-play intelligence layer featuring a complete 4-phase pipeline, continuous evaluation and custom A* traversal for any graph database.
git clone https://github.com/bodepudimuneendra-netizen/ConsciousDB.git
This MCP server provides tools for listing and retrieving content from different knowledge bases.
npx -y @jeanibarz/knowledge-base-mcp-server@latest
A reusable template for building personal LLM-maintained knowledge bases. Implements Karpathy's LLM Wiki pattern.
git clone https://github.com/bashiraziz/llm-wiki-template.git my-wiki
蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.
git clone https://github.com/lna-lab/distill-kura && cd distill-kura
Code and resources showcasing the Retrieval-Augmented Generation (RAG) technique, a solution for enhancing data freshness in Large Language Models (LLMs). Incorporate up-to-date external knowledge into LLM-generated responses. Additionally, this repository includes a Gradio-based user interface for seamless model deployment.
One source of truth for people and AI a shared Markdown knowledge base your team can edit on the web, sync from Obsidian, and connect to AI agents
🧠 A production-grade, agentic RAG platform for portfolio intelligence, combining LangChain, Chroma/FAISS, Hugging Face embeddings, and Ollama with dynamic entity extraction, backend API tool-chaining, and a real-time interactive assistant across deploy-ready frontend, backend, and infrastructure stacks.
Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.
pip install dragon-brain
MCP server with RAG knowledge base for OCPP 1.6, OCPP 2.0.1, and EV charging standards
claude mcp add ocpp-rag -- uvx --from git+https://github.com/nader0913/ocpp-rag python -m ocpp_rag.mcp_server
One-click knowledge system for documents, internal bots, and AI agents
git clone https://github.com/mlimarenko/IronRAG.git
MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.
pip install code-memory
Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.
claude plugin install ./llm-wiki
Claude Code skill for building persistent, interlinked knowledge bases from source documents. Knowledge is compiled once and kept current — never re-derived per query. Based on Karpathy's LLM Wiki pattern.
git clone https://github.com/6eanut/llm-wiki
Private LLM/RAG platform in one command for NVIDIA DGX Spark / GB10 (arm64). Validated on real hardware.
git clone https://github.com/botAGI/AGmind.git
An advanced retrieval system that combines semantic vector search with token-based search, using contextual chunking and knowledge graphs to improve accuracy. It ensures precise query responses with LLM-based answer checking and graph visualization.
git clone https://github.com/lesteroliver911/contextual-chunking-graphpowered-rag
Claude Code plugin + portable MCP core: organizes Obsidian notes, links/classifies/summarizes, optionally indexes Notion, and checks vault health.
Open source memory infrastructure for AI and humans. Turn scattered knowledge into AI-ready context across Claude, Cursor, ChatGPT, and any MCP client.
A compounding knowledge base maintained by LLM agents — inspired by Karpathy's LLM Wiki pattern
MCP server that gives AI agents persistent memory with semantic search
Learn to design an LLM wiki from first principles. Used as agent memory. Workshop with 3 exercises, open-source code, video, and slides. No coding skills required.
aboutSecurity project skill finder / dict finder / exp finder, auto suggest and team knowledge base.
Your markdown vault, compiled into a 6-persona MCP team for Claude Code, Codex, OpenCode, and Gemini CLI. Headless-first. Cites, doesn't guess.
Your agents, briefed. Not flooded. Self-hosted context compiler: git-backed team knowledge served to coding agents as token-budgeted bundles over MCP.
Agent skills that turn docs/ into an LLM-maintained wiki and task tracker. Obsidian-friendly. Works with Claude Code, Codex and Copilot CLI.
Turn textbooks, PDFs, and web content into your own interlinked learning wiki powered by LLM
Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Cursor, Codex, and any MCP client.
LLM-powered knowledge base. Drop documents, build a wiki, ask questions. Inspired by Karpathy.
Vendor-neutral, LLM-maintained personal-context wiki. Markdown in your git, queryable by any LLM (HTTP API + MCP server). v0.7 prototype.
Your AI forgets. A wiki doesn't. Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base — verify links, filter ads, summarize in your language, save to a wiki, and alert on time-sensitive items. Zero dependencies (curl + Python stdlib), platform-independent agent skill for Claude Code / Codex / Cursor / Hermes.
Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcripts, Slack & Gmail. Runs fully local on Ollama (no cloud, no API keys); queryable by any AI agent through the built-in MCP server. Postgres-backed, publishes an Obsidian-style Quartz wiki.
Claude Code plugin for building persistent, compounding knowledge bases in Obsidian. Inspired by Karpathy's LLM Wiki pattern.
Self-hosted shared memory for AI agents: vaults of people, facts and decisions your agents recall over MCP or REST, with semantic, keyword and graph search.
Permanent memory for AI coding agents. One command to save, semantic search to retrieve, works across every project. Inspired by Karpathy's LLM Wiki.
The reference architecture for LLM-maintained knowledge vaults — schema, lifecycle loop, machine verification, self-installation
Obsidian Turbocharged — governed, agent-ready Obsidian MCP server. Multi-vault native, pluggable embeddings, OAuth-ready HTTP. TypeScript + Rust. AGPL-3.0-only.
Open-source MCP server for your docs. Zero LLM at query time. docker compose up and go.
OKF (Open Knowledge Format) — curated catalog of tools, plugins, skills, proposals, and docs for agent-friendly knowledge. YAML-driven, agent-searchable, MCP-ready.
Claude Code plugin that turns the podcasts you listen to on Spotify into a cited LLM wiki: one page per topic, every claim linked to its episode.
Build an AI advisor SKILL from any YouTube channel — transcripts, BM25 + semantic RAG, verbatim quotes with timestamps.
Memory and knowledge base for agents, on the command line or as a Cloudflare worker
Chinese law MCP server: retrieve 23,995 current provisions from 378 laws and verify citations for LLMs. Free, no signup or API key, runs locally.
Self-hostable, git-native knowledge base & AI memory (MCP) — your notes stay plain Markdown files in your own git repo. Pure-stdlib Python, no database. AGPL-3.0.
Self-hosted document retrieval with citable evidence for AI assistants and apps. Console, REST API, and MCP.
File-first knowledge base for humans and AI agents — self-hosted Markdown notes with a web editor and a built-in MCP server.
知识驱动的昇腾训练/推理诊断 skill 套件 — Ascend training/inference diagnosis skill suite (5 skills + 3-tier knowledge base, Agent Skills standard)
DocumentRAG is a self-hosted Retrieval-Augmented Generation (RAG) chatbot system that enables intelligent document querying using local language models. Built with FastAPI, LangChain, and Hugging Face transformers, it processes various document formats and provides accurate answers based on indexed knowledge
Turn YouTube videos, playlists, channels, blogs & notes into a linked Markdown knowledge base (LLM wiki / second brain). Obsidian-compatible. Gemini, OpenAI, Ollama.
AI second brain vault for Obsidian — an agent compiles web clippings into a cited Markdown wiki. Claude Code + Git, model-neutral. 옵시디언 기반 AI 지식관리(PKM) 템플릿
| Tool | Stars | Score |
|---|---|---|
| ragflow | ★ 94.0k | 73 |
| codegraph | ★ 78.0k | 82 |
| OpenViking | ★ 42.4k | 81 |
| LightRAG | ★ 40.8k | 75 |
| Langchain-Chatchat | ★ 38.7k | 59 |
| book-to-skill | ★ 38.4k | 84 |
| WeKnora | ★ 37.0k | 75 |
| cognee | ★ 33.4k | 81 |
| MaxKB | ★ 23.2k | 78 |
| llm_wiki | ★ 21.5k | 70 |
| xerj | ★ 19.3k | 77 |
| deepwiki-open | ★ 18.4k | 69 |
| openwiki | ★ 18.0k | 72 |
| claude-obsidian | ★ 16.3k | 81 |
| KAG | ★ 9.2k | 58 |
| Yuxi | ★ 7.7k | 73 |
| airweave | ★ 6.5k | 60 |
| AutoRAG | ★ 6.0k | 71 |
| code-graph-rag | ★ 5.4k | 75 |
| obsidian-second-brain | ★ 5.4k | 72 |
A knowledge base an LLM writes and maintains as linked markdown pages, instead of a vector index you search. Tools that implement it include nashsu/llm_wiki, a desktop app that turns documents into an organized wiki, and volcengine/OpenViking, a context database for agents. They are listed on this page under LLM wikis.
Besides the LLM wikis above: RAG platforms such as infiniflow/ragflow, knowledge-graph tools such as HKUDS/LightRAG and colbymchenry/codegraph, and memory layers for agents such as zilliztech/memsearch. All are in the open-source list zhuyansen/awesome-llm-wiki on GitHub, grouped by type.
The top knowledge base & rag tools in 2026 are ragflow, codegraph, OpenViking. Agent Skills Hub ranks 364 options by GitHub stars, quality score (9 dimensions, including completeness, examples and agent readiness), and recent activity. The list is rebuilt every 8 hours from live GitHub data.
ragflow (94.0k stars) is the most adopted choice for general knowledge base & rag workflows, written in Python. codegraph (78.0k stars) is a strong alternative and uses TypeScript instead. Pick by your existing stack: match the language and runtime your team already uses to minimize integration cost. If unsure, start with ragflow — it has the deepest community and the most examples online.
Avoid pre-built knowledge base & rag tools when (1) your use case requires deep customization that the tool's plugin system doesn't support, (2) you have strict compliance requirements that ban third-party dependencies, (3) the tool's maintenance is inactive (last commit >6 months ago), or (4) your data volume is small enough that a 50-line custom script is cheaper than learning the tool. For most production workflows above 100 requests/day, the time savings from a maintained tool outweigh the customization loss.
Knowledge Base & RAG focuses specifically on build ai-powered knowledge bases with retrieval-augmented generation (rag) — ingest documents, search semantically, and answer questions. Obsidian for Claude Code & AI Agents is a related but distinct category — see https://agentskillshub.top/best/obsidian-second-brain/ for those tools. The two often appear in the same agent pipeline but solve different problems: choose knowledge base & rag when your primary goal is the specific task, and obsidian for claude code & ai agents when the workflow is broader.
For most teams, yes. ragflow has 94.0k stars worth of community testing, handles edge cases you haven't thought of, and ships with documentation. Build your own only when (1) your requirements are deeply non-standard, (2) you have a security/compliance reason to avoid OSS dependencies, or (3) the maintenance burden is small enough (<200 lines of code) that you'll save time long-term. The break-even point is usually around 2-3 weeks of dev time saved.
Most knowledge base & rag tools listed are open source under permissive licenses (MIT, Apache 2.0). A handful offer paid managed/cloud versions on top of free self-hosted core. Always check the LICENSE file on each tool's GitHub repository before commercial use — some use AGPL or non-commercial restrictions that may not fit your deployment model.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: