Task tracking for Agents
Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
An Agentic Framework for Reflective PowerPoint Generation
Model Context Protocol server for GraphQL
Official Portainer MCP server

An native MCP server extension for Ghidra
C++ MCP SDK - build Model Context Protocol (MCP) servers and clients in C++ / CPP. Enterprise-grade security, observability, connectivity. Stdio, HTTP+SSE, Streamable HTTP, WebSocket, TCP transports. Bindings for Python, TypeScript, Go, Rust, Java, C#.
The filesystem for AI agents
Powerful AI Client
Rome is the agentic OS.

Open-source Agent Operating System
Claude Code for Financial Market
The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.
MCP server for Anki via AnkiConnect
Academia MCP server: Tools for automatic scientific research
Model Context Protocol server for ActivityWatch time tracking data
Compound Engineering Framework for Alpha Feature Research in Quant Finance

A Nostr MCP server that allows to interact with Nostr, enabling posting notes, and more.
Build resilient agents.

🚀 The fast, Pythonic way to build MCP servers and clients.
A collection of projects showcasing RAG, agents, workflows, and other AI use cases
Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

The most RAM efficient harness