guilds.run

guilds.run is an open-source platform to run a team of AI agents and inspect every prompt and tool call.

guilds.run is an open-source platform designed to run and inspect multi-agent AI teams. It allows users to run teams of AI agents using any model, including Claude, GPT, Gemini, Grok, Qwen, and Llama, with the ability to mix different models within a single team. The platform records every prompt, tool call, and memory change to provide full transparency into agent operations. Studio acts as a coach to analyze live team data and draft fixes for recurring issues. Agents share tables, notes, and memory, and each agent operates with its own terminal, workspace, scripts, and optional browser. It includes connectors for Notion, Gmail, GitHub, wallets, and banks, allowing precise control over permissions.

guilds.run at a glance

Best for: Software engineer, Founder
Runs on: self-hosted, open source
Pricing: Free
Released: October 2026
Category: AI agent tool
Website: guilds.run

Key features

Inspect prompts and tool calls
Share tables agents read and write
Coach to tune the team
Use any model in one team
Connectors for external services
Dedicated computer for each agent

Use it for

Finds posts worth a reply, writes in your voice, and keeps the queue.
Researches accounts, drafts outreach, and tracks every thread.
Reads the inbox, tags and routes, and drafts first replies for review.
Triages issues, reviews pull requests, and keeps the backlog moving.

Alternatives to guilds.run

Agenta — Build and automate AI agents that run on your own infrastructure or the cloud.
Alook — Connects existing local coding agents to team communication channels.
OpenBot — Runs entirely on your own infrastructure with strict document permissions and custom.
Adyen — Share AI agent resources across coding tools and repositories easily.
BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
AgentGrid.io — It gives humans and AI agents one single source of truth to work on live artifacts together.
OpenRig — Coordinate multiple AI coding agents across long-term projects.
FastGPT — It uses hybrid retrieval and auto-cleansed data to prevent hallucinations.
OpenBot — Runs AI agents locally using existing subscriptions or local models.
AGiXT — Builds autonomous agents with integrated memory and web capabilities.
Merlin — Run Claude Code and Codex on your own machines with your team.
OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.

All guilds.run alternatives