47 packages found
Unreal Engine Vibe Coding tool
Run AI agents fully autonomously on a filesystem directory — MCP servers and skills enabled, with zero human approvals o
Your Data, Your AI — Health, Finance & More. Open Source, Privacy-First.
Benchmarked agent execution runtime for Python. Sub-10ms cold starts, real-time streaming, time-travel debugging, and se
MCP server enabling AI assistants to search and retrieve information from local resume and job application documents
Live context engine for AI assistants — resolve-before-context, session waypoints, and tool-selection intelligence for H
Your local-first AI ad ops crew. Works with Claude Code, Cursor, Codex & Gemini.
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://disco
🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.
Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.
Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.
Local MCP server that exposes classic Outlook desktop (mail, calendar, contacts, tasks, rules) to Claude and other MCP c
Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor
MCP server for Google Gemini — free image generation, editing & chat via browser cookies. No API keys needed.
BACH v3.12.4-earth: local-first text-based OS for LLM agents with SQLite memory, 113+ handlers, 550+ tools, MCP servers,
A macOS Model Context Protocol (MCP) server that acts as the central nervous system for your AI agent. Bridges Calendar,
Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A with file pa
📸🧹🗺️ MCP server for intelligent photo management with Immich — search, curate geographic albums, clean up libraries,
Vault-native, accountable memory for Claude Code and MCP clients. Markdown is the source of truth, no LLM on the Stop pa
The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.
An autonomous agent that conducts deep research on any data using any LLM providers
Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarit
Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, background tasks,
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. E
MCP server for client-encrypted AI agent handoffs with WorkBaton and WorkStash
Fast Python web crawler for RAG and AI ingestion. Extracts clean Markdown from any site for LLMs and vector stores.
Analyzes your codebase identifying important files based on dependency relationships. Generates diagrams and importance
Persistent memory and session intelligence for AI coding assistants. Auto-tracks mistakes, decisions, and context via ho
Claude Code in Docker. Drop-in OpenAI-compatible API, MCP server, Telegram bot, and CLI — five interfaces, one image. Pe
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and
Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Loca
Query, monitor, and manage Unraid servers via GraphQL API through MCP tools. Supports system info, Docker, VMs, array/pa
Search infrastructure for AI agents: free by default, MCP-ready, LLM-context aware, and production-grade when needed.
滴答清单 (Dida365/TickTick) MCP Server - 让 AI 助手控制你的滴答清单 | For OpenClaw, Claude Desktop & any MCP client
Always-on context for AI agents: screen capture, OCR, voice, MCP server. Local-first, AGPL-3.0.
Local-first Obsidian MCP server for Codex, Claude Desktop, and markdown vault automation.
AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP
Achieve infinite conversation turns in a single API request via turn-mcp. Self-hosted MCP server with browse
Start, observe, and interact with Claude Managed Agents from any MCP client (Claude.ai, Claude Code, …). Pluggable auth
Action Control for autonomous agents. Check posture. Gate risky actions. Prove execution. Fits your existing agent stack
Zero-trust Python FastMCP intelligence core for The Undesirables Ecosystem. Enables 100% local, offline AI agent tool-ca
Production-grade persistent memory service for AI agents — FastAPI + pgvector + local ONNX embeddings
Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.
Google Workspace MCP that actually writes. 28 tools across Docs/Slides/Sheets/Drive — markdown-to-Docs, smart chips, dat
Self-hosted MCP server and coordination layer for AI agent fleets: shared memory, tasks, messaging, and session handoffs
A Claude Code plugin that gives Claude persistent memory across sessions — stores lessons and decisions as markdown in y