CodeRAG — repository deleted, archived audit

Repository no longer available — Neverdecel/CodeRAG returns 404 on GitHub. It was deleted, or its owner's account was removed. The data below is our last successful snapshot.

by Neverdecel · Agent Tool · ★ 211

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is CodeRAG safe to install? View the security audit →

About CodeRAG

🔎 CodeRAG A standalone, local-first semantic code-search engine for large and custom codebases. CodeRAG indexes a whole codebase into a hybrid (vector + keyword) search index and answers questions like "where is retry/backoff handled?" with the exact functions, classes, and files that matter — ranked by meaning, not just string match. It runs entirely on your machine with no API key (a local ONNX embedding model is the default), keeps its index up to date as you edit, and is built to stay fast on large codebases. Use it from the CLI, embed it as a Python library, self-host it as an HTTP service, or browse with the web UI. Built for the cases off-the-shelf IDE assistants don't cover well: a codebase that's too big, too private, or too custom — or a search/RAG capability you want to own and embed in your own tools. ✨ Highlights Local-first, zero-key. Default embeddings run locally via fastembed (ONNX, no PyTorch). OpenAI is optional. Symbol-aware chunking. Indexes functions, classes,

aiai-assistantai-codeai-toolscode-searchfaissopenai-gptragretrieval-augmented-generationvector

Quick Facts

Stars211
Forks34
LanguagePython
CategoryAgent Tool
Quality Score65.5205672327872/100
Open Issues3
Last Updated2026-06-16
Created2024-09-08
Platformspython
Est. Tokens~15k

Compatible Skills

These tools work well together with CodeRAG for enhanced workflows:

  • RAGLight — semantic(0.35)+complementary+rare_topics+same_lang+similar_pop+shared_platform (66%)
  • snippy — semantic(0.25)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (62%)
  • mcp-memory-service — semantic(0.16)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)

CodeRAG alternative? Top 6 similar tools

Looking for a CodeRAG alternative? If you're comparing CodeRAG with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • lucid-memory by JasonDocton · ⭐ 158

    Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG.

  • octocode-mcp by bgauryy · ⭐ 838

    MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturall

  • automem by verygoodplugins · ⭐ 803

    Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context ac

  • RAGLight by Bessouat40 · ⭐ 672

    RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in differen

  • octocode by Muvon · ⭐ 475

    Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o

  • deepcontext-mcp by Wildcard-Official · ⭐ 278

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is CodeRAG?

CodeRAG is CodeRAG is an AI-powered tool for real-time codebase querying and augmentation using OpenAI and vector search.. It is categorized as a Agent Tool with 211 GitHub stars.

What programming language is CodeRAG written in?

CodeRAG is primarily written in Python. It covers topics such as ai, ai-assistant, ai-code.

How do I install or use CodeRAG?

You can find installation instructions and usage details in the CodeRAG GitHub repository at github.com/Neverdecel/CodeRAG. The project has 211 stars and 34 forks, indicating an active community.

What are the best alternatives to CodeRAG?

The top alternatives to CodeRAG on Agent Skills Hub include lucid-memory, octocode-mcp, automem. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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:

View on GitHub → Browse Agent Tool tools