MCP servers and skills: search, filter by where they run, and compare.
Exact, durable handoffs between AI coding agents: one turn in the right session, never sent twice, never interrupting a busy agent. CLI, live page, MCP server.
DockerApache-2.0★ 1Few starsNo key
面向 AI 上下文管理的 Agent Skill：为 Codex 上下文管理、Cursor 上下文切换和 Claude 上下文管理提供跨窗口续接，用 Git 保存可验证的功能说明与变更记录。AI coding context management and agent handoffs.
SkillMIT★ 104No key
Desktop workspace for coordinating multiple Claude Code agents with typed handoffs (accept / decline / cancel / expire), durable SQLite ledger, and a human-in-the-loop UI.
SkillMIT★ 2Few starsNo key
Local-first MCP server: give ChatGPT & friends grounded, current context on the repos your coding agents work in. Live git, docs, tasks, agent handoffs.
Node.jsApache-2.0★ 11No 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
MCP server for client-encrypted AI agent handoffs with WorkBaton and WorkStash
PythonApache-2.0★ 2Few starsNo key
🤖 Agentic AI Platform with InterSystems IRIS | 🔀 Multi-agent workflows with OpenAI Agents SDK & agent handoffs | 🧠 IRIS Vector Search & RAG | 🌐 MCP Server integration | 🔍 Agent tracing | 🛠️ AI a
SkillMIT★ 2Few starsNo key
Open-source security testing for A2A → MCP agent handoffs and cross-protocol AI agent systems.
Node.jsApache-2.0★ 1Few starsNo key
Local multi-agent workspace with Hermes orchestration, role-based AI agents, memory, scheduling, Skills, MCP, terminal, files, and HTML preview.
PythonMIT★ 5No key
Delegate tasks to DeepSeek right inside your Claude Code / Codex sessions.
SkillLink only★ 95
Seed agent-native, self-governing repos: AGENTS.md, MADR decision logs, deterministic gates & pre-commit hooks. Upgradeable — never overwrites your edits.
SkillMIT★ 10No key
Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs.
GoMIT★ 5No key
Ask your repo what breaks before an AI coding agent edits it.
Node.jsMIT★ 3Few starsNo key
Spec-driven development scaffold for Claude Code — workflow pipeline, memory system, sub-agent orchestration, and quality gates using Claude Code's native features
SkillMIT★ 2Few starsNo key
An Agent Skills compliant skill that enables AI agents to automatically organize user input and maintain a persistent, project-bound idea repository (mdbase) — so decisions, preferences, and constrain
SkillMIT★ 4Few starsNo key
MCP server that reverse engineers a locked rebuild spec (CLAUDE.md, .claude config, mutation tested tests) from an existing app
Node.jsMIT★ 3Few starsNo key
Reusable agent skills for evidence-backed research, approval-gated publishing, schema-validated records, and durable context handoffs.
SkillMITFew starsNo key
Reusable agent skills and plugins by Lex from SigmaStudioz, for Claude Code, Cursor, and Codex.
SkillMIT★ 1Few starsNo key
Hermes Agent skill for orchestrating a Kanban-based Coder → Tester → Reviewer AI coding workflow with structured QA, code review, retries, and persistent chat ownership.
SkillMIT★ 2Few starsNo key
Continuity ledger for AI coding agents: file-scoped memory with exits, cross-agent handoffs, plans cut into chunks. Measured, in your .git. Claude Code, Codex, OpenCode, MCP.
SkillMIT★ 1Few starsNo key
Local-first AI development orchestrator: one loopback daemon with a Kanban board, MCP endpoints and durable memory for Claude Code, Codex, Cursor and ZCode.
SkillMIT★ 1Few starsNo key
Local-first HTML review and annotation for AI coding agents
Node.jsMIT★ 1Few starsNo key
Local code search and token-budgeted repository context for AI coding agents. Rust CLI and read-only MCP server for PR review, debugging, and agent handoffs.
SkillMIT★ 1Few starsNo key
Who stands behind it
