Open-source encrypted AI agent inbox and agent-to-agent messaging CLI with permanent addresses, durable private threads, signed channels, JSON automation, and human approvals.
Coordinate multiple agents or tasks.
Open-source encrypted AI agent inbox and agent-to-agent messaging CLI with permanent addresses, durable private threads, signed channels, JSON automation, and human approvals.
Shared per-repo space for Claude Code sessions: see activity, get collision warnings, notes.
Read, cite, compose and remember over a Markdown knowledge Bundle, as MCP tools over stdio.
Swarm DAO Model Context Protocol server — exposes DAO governance tools to any MCP-compatible host (Copilot, Claude, Codex, …)
A framework for creating AI MCP servers, agents, and orchestration with Groq integration
MCP server that runs CLI AI coding agents (Claude Code, Codex, opencode, Antigravity) as sub-agents from any MCP client, with background sessions and structured code review
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
通过 MCP 统一创建、调用和编排本机 Codex、Claude 等编码 Agent
File-claim coordination for parallel AI coding agents: claim files before edits, no stomping.
Swarm DAO governance plugin for GitHub Copilot — MCP server, 7 custom DAO agents, and governance workflow
File-backed MCP server for coordinating multiple AI coding agents (Claude Code, Cursor, Cline, etc.). Local stdio or networked over Streamable HTTP.
Spec-driven verification layer for AI coding agents — Claude Code · Codex · Gemini · Antigravity · Cursor. Intent in before it writes, result verified against your spec after. Reference implementation of the Ironclad standard.
Deploy Claude Code, Codex & Antigravity (agy) CLI agents to demolish your work before users do. Real file analysis. Brutal honesty. Per-call model pinning, conversation continuation & intelligent pagination.
MCP server for orchestrating multiple agentic AI instances (Claude, Gemini, Codex, Copilot, AGY) across machines via SSH
MCP server for PR review processing with GraphQL-based GitHub integration
Lifts WxO Slack limits: every-message wake-up, multi-channel MCP. https://markusvankempen.github.io/
Collision control for parallel AI agent sessions sharing one working tree.
TeamHub — a self-hosted, project-aware MCP server + CLI for running a multi-agent Claude Code team (Team Lead plans/assigns, Developers code, Testers verify), with skills, a headless agent runner, one-command install/autostart, and a live monitoring dashb
Quota-aware agent-swarm MCP server: routes concurrent agent turns across multiple AI provider accounts
Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.