# guilds.run (slim)

> Open-source, self-hosted system from Cigale AI for standing teams of AI agents, each with its own role, model and tools. A guild shares chat, notes and tables, and every run keeps the prompt, tool calls and memory changes.

- Full: https://www.anchorterminal.com/tools/guilds-run.md (~6,150 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/guilds-run.json · canonical https://www.anchorterminal.com/tools/guilds-run
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-14
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

**C · 56.5/100 · rank #674 of 1084 · #11 in Agent frameworks & SDKs · not agent-ready · confidence medium**


Assessment: A self-hosted multi-agent system that records each run's prompt, tool calls and memory changes, with per-agent models and tools and no telemetry by default. Public since 9 October 2026, it has no tagged release or published package, its own security register lists 13 open issues, and the site's terms and privacy links return 404.

## Facts

- Kind: Agent framework · vendor: Cigale AI · category: Agent frameworks & SDKs · legal entity: Cigale AI · provenance 40/100
- Auth: API key · pricing: Free · x402: no · licence: AGPL-3.0-only
- Probe metrics: not measured yet (probes haven't run)
- Runs on: Docker with the Compose plugin. Three services, PostgreSQL 17, an OpenSandbox server and a Node 24 orchestrator serving the web app on 127.0.0.1:8080
- Version: No tagged release or version number. Public repository created 9 October 2026, last commit on main 13 October 2026
- Models: OpenAI, OpenRouter, xAI, DeepInfra, Kimi Code and any local OpenAI-compatible endpoint, each called through Chat Completions. Claude and Gemini through OpenRouter
- MCP client: Remote MCP servers run in the orchestrator, added by an admin or from a connector registry. Connect tokens never enter the sandbox
- Multi-agent: A guild is a team with a shared group chat, notes and tables. A message tagged @agent wakes that agent, and an untagged one wakes every agent
- Durable state: Runs, notes, tables, memory and scripts in PostgreSQL. After a restart, unresolved tool calls get an interruption result and no model call is replayed
- Human approval: Studio edits wait for the operator to publish, and writing MCP tools start Off. No per-call approval gate for agent tool calls was found
- Sandbox: One OpenSandbox container per machine with dropped capabilities and no_new_privileges. Agents on a machine share it, run commands as root and have open egress
- Telemetry: None by default. Sentry when SENTRY_DSN is set. The bundled Graft tool runs with DO_NOT_TRACK=1, and its daily npm version lookup has no switch
- Hosted: Listed as coming soon from $19 a month, not available on 14 October 2026

- Scores: Reliability 53, Performance pending, Schema & documentation 58, Agent ergonomics 67, Security & auth 68, Payments & pricing 60, Task success pending, Maintenance & community 41, Transparency & trust 52 · negative events -2 · total over the 7 assessed categories
- Why: Reliability, Read with the local-software lines, because the owner runs it. · Schema & documentation, Framework reading. · Agent ergonomics, Framework reading, scored on what it takes to run a tool-calling team with MCP. · Security & auth, Framework reading. · Payments & pricing, No payment protocol (0). · Maintenance & community, No tagged release. · Transparency & trust, AGPL-3.0-only, OSI approved (30).
- Sources: 20, open questions: 6, both in the full twin
- Capabilities: agent.framework, agent.multi-agent, agent.mcp-client, agent.durable
- JSON: https://www.anchorterminal.com/api/v1/tools/guilds-run.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/guilds-run.svg` or a link to https://www.anchorterminal.com/tools/guilds-run from a page on guilds.run or one of its subdomains, or the README of github.com/CigaleAI/guilds, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Keep the box on loopback or behind an authenticating proxy with AUTH_MODE=trusted-header. The default mode does not authenticate
2. Put agents that hold different secrets or GitHub tokens on different machines. Agents on one machine can read each other's homes and tokens
3. Back up the .env file written by ./setup.sh. It holds the only copy of the key that encrypts stored credentials
4. Set a spend limit at your model provider. guilds.run sets no spend cap, and max_tool_calls defaults to 50 per run
5. Pin a commit of main when you deploy. There are no tagged releases or versioned images yet

## Connect

```bash
git clone https://github.com/CigaleAI/guilds.git && cd guilds && ./setup.sh && docker compose up --detach --wait
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI Agents SDK | AA | 86.2 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | https://www.anchorterminal.com/tools/openai-agents-sdk.min.md |
| Pydantic AI | A | 83.7 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | https://www.anchorterminal.com/tools/pydantic-ai.min.md |
| Microsoft Agent Framework | A | 82.2 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | https://www.anchorterminal.com/tools/microsoft-agent-framework.min.md |
| Docker Agent | BB | 76.5 | agent.framework, agent.multi-agent, agent.mcp-client, agent.durable | https://www.anchorterminal.com/tools/docker-agent.min.md |
| Agent Development Kit (ADK) | BB | 74.7 | agent.framework, agent.multi-agent, agent.durable, agent.mcp-client | https://www.anchorterminal.com/tools/google-adk.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)