MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Closed-loop Task & Motion Planning for a Franka Panda — PDDL + Fast Downward bridged to real geometry via falsifiable predicates, with ROS 2/MoveIt 2/Gazebo execution, YOLOv8 perception, and language-
PythonMIT★ 4Few starsNo key
An MCP that for any tool call that mutates state (send email, charge card, delete file), force a “citation-first” dry-run with an human-readable preview; only on explicit approval by the human (or age
PythonAGPL-3.0★ 6No key
Open-source privacy and approval gateway between AI assistants and your business systems (MCP): human approval, local PII checks and audit for Gmail, Drive, Slack, Salesforce, Jira and more.
PythonApache-2.0★ 1Few starsNo key
Review & approve AI agent task plans in a ComfyUI-style node editor, right in your terminal (MCP server + TUI)
PythonMIT★ 1Few starsNo key
Parallel and sequential task-tree runner with matrix expansion and effects plugins.
PythonMIT★ 5No key
Give a complex task to a team of AI agents instead of just one. Multi-agent workflow orchestrator.
PythonMIT★ 4Few starsNo key
Memory and governance for Claude Code sessions: a read-before-write gate, a context resolver with receipts, tiered project notes, handoffs between sessions, and docs checks that fail when the record a
PythonMITFew starsNo key
PythonMIT★ 1Few starsNo key
AI 規格大師 — MCP server bridging specs (Linear / JIRA / GitHub Issues / Notion / Markdown / Figma) to tests, with bidirectional traceability and a spec-quality coach. Sibling to mk-qa-master.
PythonMIT★ 2Few starsNo key
Task scheduling MCP server for autonomous agents — cron, intervals, priority queues, dependencies, retry policies.
PythonMITFew starsNo key
Open-source AI scheduling agent — your own Calendly with conversational AI
PythonMIT★ 3Few starsNo key
Strategic task prioritization and agent orchestration for multi-project operators
PythonMIT★ 2Few starsNo key
AI-powered desktop automation agent. Takes screenshots, sends to any LLM (OpenAI-compatible), receives a ctions, executes mouse/keyboard operations, and loops until task is complete. Supports SOM (ele
PythonMIT★ 2Few starsNo key
Python CLI that checks whether an AI coding session's handoff notes are complete enough for the next session to resume without guessing.
SkillMIT★ 2Few starsNo key
Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.
PythonMIT★ 11No key
A private, local-first AI agent for your terminal. It works with your files, notes, calendar, mail, reminders and messages, searches the web and remembers across sessions, all on Ollama with no API ke
PythonMIT★ 2Few starsNo key
Agent-operated outbound sales engine: LinkedIn + email cadence, two-stage ICP qualifier, learning loop. CRM-agnostic (Attio bundled, adapters generated + conformance-tested). Clone it and let your AI
SkillMIT★ 7No key
LLM-native instrumental BGM: agents write note-level text scores, onbgm renders them
SkillMIT★ 6No key
An enhanced MCP (Model Context Protocol) server for intelligent memory and task management, designed for AI assistants and development workflows. Features semantic search, automatic task extraction, k
PythonMIT★ 33No key
Automated prompt engineering for efficient AI interactions | Interactive command-line interface | Multi-provider LLM integration (Gemini, Claude, OpenAI, Groq, Qwen, GLM) | Intelligent task-based refi
PythonMIT★ 17No key
Experimental Python tool for inspecting language and task-framing changes across long AI conversations.
PythonMIT★ 1Few starsNo key
Use Google Antigravity (agy) as an agent backend from Claude Code / OpenAI Codex / Cursor / any MCP client. MCP server with 10 typed tools + Skill bundles, hybrid backend, capability detection, long-t
PythonMIT★ 25No key
Local AI meeting notes for Mac — on-device Korean & English transcription, summaries, search, and MCP for Claude Code. 맥 로컬 회의록·음성 텍스트 변환
PythonApache-2.0★ 4Few starsNo key
Reliability, memory, and model-routing for AI coding agents — you keep your agent loop, pass it in as execute_fn(model, task). Local-first, MIT.
PythonMIT★ 1Few starsNo key
Who stands behind it
