Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Portable, verifiable, decision-aware context handoffs for AI agents.
PythonApache-2.0★ 1Few starsNo key
A live Kanban for AI coding agents: real progress updates, task evidence, and cross-agent handoffs. Portable skill with a dependency-free local viewer.
SkillMIT★ 4Few starsNo key
A GitHub-based mailbox for AI agents: verified handoffs, read-back after every write, receipts against duplicate work, no self-review — with the final decision always left to a human.
Node.jsApache-2.0Few starsNeeds a key
SkillMIT★ 2Few starsNo key
Reusable agent skills and plugins by Lex from SigmaStudioz, for Claude Code, Cursor, and Codex.
SkillMIT★ 1Few starsNo key
The Bi-Temporal State Graph & Lossless Context Compression Engine for AI Agents
PythonApache-2.0★ 1Few starsNo key
Open-source, local-first work contracts, agent continuity, and independent verification for coding assistants
Node.jsApache-2.0Few starsNo key
A local, open-source workspace for people and coding agents
SkillApache-2.0★ 6No key
Shared memory, focused engineering practices and reliable handoffs for coding agents. Give your agent one setup prompt.
SkillMIT★ 5No key
Desktop command center for AI coding agents: shared project memory, a context engine, a local MCP server and handoffs across Claude Code, Codex, Cursor, Gemini CLI and Copilot, shown as a live 3D virt
SkillMIT★ 3Few starsNo key
Baton (一棒到底): run your startup in owner mode. One owner per goal, many Claude Code terminals, no handoffs. A personal board and a team board, open source.
SkillMIT★ 4Few starsNo key
Shared project memory for you and your coding agents, over MCP. StateDock Cloud and the Cloudflare self-hosted edition.
Hosted by authorAGPL-3.0★ 8No key
Local-first shared memory for AI agents. Persistent project context, evidence-based handoffs, PostgreSQL, and MCP integration for Codex, Claude Code and OpenCode.
GoMIT★ 1Few starsNo key
Open-source coordination layer for AI-native engineering teams: one repo, many humans and coding agents. Task graph, intent and conflict detection, blast radius, verified handoffs, PR merge gate, git-
GoMIT★ 1Few starsNo key
Keep multiple Codex threads live and connected. Native messaging, focused handoffs, checked acknowledgments, and reconnect recovery in an installable skill.
SkillMIT★ 1Few starsNo key
Claude Usage optimization, 2x more claude usage through minimization of cache reading through an obsidian vault workflow
SkillMIT★ 4Few starsNo key
A proxy skill that can comprehend your tasks, recommend suitable Large Language Models (LLMs) based on benchmark tests and community evidence, and coordinate the handover of multi-model projects.
SkillApache-2.0★ 5No key
Not yet dead: verifiable saved-progress handoffs between AI agents.
SkillMIT★ 7No key
Codex ↔ Claude Code MCP bridge for AI agent orchestration: task delegation, event-driven handoffs, reasoning profiles and evidence reuse. Windows/macOS; optional Orca.|Codex 指挥 Claude Code:会话管理、阶段交付与验
SkillMIT★ 6No key
Put Claude Code to work for Codex. A lightweight MCP server for persistent workers and flexible orchestration: parallel tasks, sequential handoffs, and independent agent reviews.
SkillMIT★ 1Few starsNo key
Safety-first composition layer for reproducible research agents: evidence-aware claims, experiment lineage, durable handoffs, and non-overwriting adoption.
SkillMIT★ 2Few starsNo key
ACP is A model-agnostic Agent Skill for reliable AI communication, coding workflows, structured handoffs, and verifiable results.
SkillMIT★ 3Few starsNo key
AI agent migration decisions, trusted state recovery, and reliable project handoffs.
SkillMIT★ 2Few starsNo key
A shared skill for Codex and Claude Code: independent reviews, clear coding ownership, reliable dialogue, and session handoffs.
SkillMIT★ 3Few starsNo key
Who stands behind it