ai-agents

The OS AI engineering and monitoring agent. 🦸‍♀️ Oversight and compliance copilot for trustworthy AI.

Drop-in AI memory layer with 2x faster response and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code changes. Self-host for free.

SochDB is a high-performance embedded, ACID-compliant vector database purpose-built for AI agents and memory

Improving langchain knowledge graphs using baml

Metis is a coding agent that boosts coding performance by 50%

A curated list of 300+ tools, platforms, and resources for vibe coding and building software by talking to AI

A curated collection of 81 production-ready subagents for Gemini CLI. Drop them into .gemini/agents/ and let Gemini delegate the right specialist.

A practical guide to AI: from running your first local model to building your own agents. 52 files covering LLMs, Ollama, RAG, prompt engineering, machine learning, AI agents, and local AI tools.

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, trade-offs, and numbers, not prompt tips

Your agent seeks what search can't find. A self-hosted perception MCP server that transcribes speech, reads behind logins, sees images and video frames, crosses languages, and remembers.

A2A protocol client for your terminal

Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance evidence (Strix Halo, DGX Spark, llama.cpp, vLLM): https://agmind.ai

Your private AI companion that lives on your wrist. Complete local AI assistant with emotional intelligence.

MCP server for Git with local Ollama — zero tokens for git operations

An AI agent that controls your Flipper Zero that uses PyFlipper, LightLLM, RAG, and can connect to your local Ollama instance!

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Bedrock is a CLI tool that bootstraps AI-ready project configurations by generating standardized rules, skills, and project context tailored to tools like Claude Code, Cursor, Antigravity, and Trae—so you can get consistent, instruction-driven AI behavior with a single command.

Operational doctrine for practical AI systems design.

34 FinOps specialist AI agents + 6 named-pattern playbooks. Drop into Claude Code, Copilot, Cursor, Windsurf, Aider, Gemini CLI. MIT.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.