#multi-agent

Capa de control y confianza para coordinar múltiples agentes de IA. MCP, 100% local, open source.

Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services.

Open-source work buddies. Open-source personal desktop AI agent.Go runtime for office/ITops/marketing workflows.

Agent workflows with full observability and time travel: watch every step live, rewind, fork, replay any run. Claude Code, Codex, Gemini, any model or harness.

Multi-project agent orchestration for Claude Code. One command session controls everything.

MCP server with 40 tools for AI agents. Memory, web fetch, search, file ops, screenshots, and multi-agent coordination in one Go binary.

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

Lightweight Claude Code UI wrapper - integrates with your local settings and chats

NOUS (Νοῦς) — monitor, not a guard. NOUS proves the rules you declare hold across every path your AI agents could take — and anyone can check the proof offline, without trusting the vendor. Not even NOUS. EU AI Act Annex IV.

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

The missing context layer for AI-assisted refactoring

Multi-provider coding-agent orchestration in a verified loop: a critic on a different model signs off before work ships. Claude Code, Codex, Gemini, aider, Copilot, opencode, local.

Build AI agent fleets. 3 lines, any backend, local or cloud. Effort-based model routing, 48 identities, knowledge graph memory, fleet orchestration.

MCP coordination primitive for multi-agent workflows. LLM-agnostic, CLI-agnostic, self-hostable. TypeScript + SQLite.

Discord control plane for project-bound ACP agents. Kiro CLI by default, optional OMP, MCP policy, audit, usage, cron, and thread agents.

A minimal, composable Go library for building AI agent applications.

Make AI actually work for you - A personal agent that writes its own tools and repairs itself.

Factory AI: durable private coding organization with deterministic orchestration, isolated agents, Azure/Bedrock routing, memory, cost visibility, and gated delivery.

AgentWorks: the open-source control plane for running, measuring, and improving AI agent workflows across your company.

🦈 Shark AI - AI-Native Collaborative Development Tool powered by StackSpot AI and BMAD Method

A TUI session manager for Claude Code — manage multiple sessions with a tmux-based split-pane interface

Local-first control plane for AI coding agents: repo memory, verification, sessions, and dynamic workflows.

Multi-agent coordinator for Claude Code — orchestrates parallel Managed Agent workers on GitHub repos

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

Get a saved, cited report from your AI agent

A coding agent CLI that runs like an engineering org — role routing, plan DAGs, approvals, memory, and a 10-platform chat gateway. Apache-2.0.

Make AI actually work for you - A personal agent that writes its own tools and repairs itself.

Identity, memory & collaboration platform for AI agents — facts, memories, secrets, and inter-agent messaging via a CLI, MCP, and a Go server.

Open-source Go agent runtime for autonomous AI systems and multi-agent automation. MCP, RAG, 15+ LLM providers and 60+ built-in tools in a single binary.