Stars
Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Running Qwen 3.6 on NVIDIA A10 24GB eGPU with vLLM
Everything I know about running LLMs locally
🪓 An orchestration engine for background tasks, AI agents, and durable workflows
Classic Windows 95, 98, Me, 2000, XP, Vista taskbar for modern versions of Windows
Build Real-Time Knowledge Graphs for AI Agents
Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-st…
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
Mo₅GeB₂ Materials Simulation Ab initio electronic structure and phonon calculations for a GNoME-predicted superconductor
Web & Mobile UI for Claude Code & Codex . Launch sessions, stream responses, approve tools. All from your browser / mobile
Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Dock…
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Browser automation CLI for AI agents
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
Local lightning-fast semantic code search built for agents
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
MCP Auth Proxy is a secure OAuth 2.1 authentication proxy for Model Context Protocol (MCP) servers
OAuth proxy to protect a remote Model Context Protocol server
🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.