Gas Town CLI - multi-agent workspace manager with native binary support
Coordinate multiple agents or tasks.
Gas Town CLI - multi-agent workspace manager with native binary support
Local open-source MCP server delegating routine coding tasks to local worker agents
MCP server for AgentsWorklog — 13 tools giving coding agents shared situational awareness (activity logs, notables, overlap checks) over the REST API.
Multi-agent context sharing, memory, and status coordination via MCP tools.
AI Agent Skill - Build production-ready AI applications with multi-agent orchestration, Virtual Database, streaming conversations, and React UI Kit. For Claude Code, Cursor, Windsurf, and 30+ AI coding agents.
anvil's first-class CLI: define an outcome, the agent works, a deterministic gate decides done.
Coordinate parallel coding agents, above Git
Your agents, on a team with you. Every piece of work shows who did it and who accepted it.
Shared brain for AI coding agents - one MCP server giving Claude Code, Codex, Cursor, Kiro, Gemini CLI and Antigravity a common task board, shared memory and advisory file claims.
Claude Code Multi-Worktree Helper - Single-session parallel worktree automation with MCP server
comms for your coding agents
MCP (Model Context Protocol) server that lets AI coding agents like Cursor, Claude Code, Copilot, and Windsurf report task status, post progress updates, flag blockers, and mark work complete on a swarmboard kanban board — natively, with no manual prompti
MCP Server for ESSE — fuse multiple AI agents into one unified mind via Model Context Protocol
External MCP server for controlling Orca (worktrees, sessions, orchestration)
MCP server for Mutex pods and rooms, with optional git coordination hooks.
Local-first personal AI ops layer. Shared verbatim memory across your agents (Claude Code, Cursor, OpenClaw, Hermes, Obsidian, Telegram) in one SQLite + FTS5 corpus — plus a coordination layer where any of your agents can delegate tasks to any other. Sear
Author, check and compile multi-agent loop graphs for a coding harness: templates, a validator with stable rule codes, a compiler to a prompt package, and an MCP server. It never runs agents.
Delegate tasks to sub-agent CLI instances (Claude Code, Codex, Gemini CLI)
Chat between the AI agents on your machine — they coordinate, ask each other questions, and get notified. No server to run.
Git worktree orchestration for parallel AI coding agents — isolated worktrees, auto rebase-merge, and smart conflict routing. 多 Agent 并行编码的 Git 编排层。