No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by ctxr-dev · MCP Server · ★ 127
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is llm-wiki-memory safe to install? View the security audit →
Persistent local memory for AI coding agents. Your agent remembers every session, learns from its mistakes, and gets smarter the longer you work with it. Claude Code, Cursor, Codex, and every other MCP client forget everything when a session ends. LLM Wiki Memory fixes that: it captures your conversations, compiles them into durable project knowledge and lessons your agent applies next time, and recalls the right context through a local MCP server. Memory lives on your machine as plain Markdown in an LLM wiki versioned in git, searched with local embeddings, and consolidated offline while you sleep. No RAG stack. No vector database. No Docker. No cloud. Install with one prompt and your agent never starts from zero again. [. Open source must win.
🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, use
Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn fro
Explore other popular mcp server tools:
llm-wiki-memory is 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.. It is categorized as a MCP Server with 127 GitHub stars.
llm-wiki-memory is primarily written in JavaScript. It covers topics such as agent-memory, andrej-karpathy, andrej-karpathy-llm-wiki.
You can find installation instructions and usage details in the llm-wiki-memory GitHub repository at github.com/ctxr-dev/llm-wiki-memory. The project has 127 stars and 2 forks, indicating an active community.
llm-wiki-memory is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to llm-wiki-memory on Agent Skills Hub include octocode, roampal-core, mira-OSS. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: