Simple Agent Manager

@simple-agent-manager.org

7 Followers 54 Following

An open source platform to run many agents at a time. Control plane built on CloudFlare, with your agents running on VMs in your cloud provider of choice. Clouds: Hetzner, Scaleway, GCP Agents: Claude Code, Codex, Vibe, OpenCode, AMP Built in Paris 🇫🇷

Screenshot of the SAM (Simple Agent Manager) chat interface. A green system message labeled "[SAM Orchestrator Check-In]" warns that the task appears to have stalled due to several minutes of inactivity. It instructs the agent to send a brief progress update and continue working if unfinished, call complete_task() if finished, or request_human_input() if assistance is needed, warning that otherwise the task will be marked as failed.

Below it, the assistant replies: "The work is finished: PR #1436 was pushed, checked, and merged successfully. I'm sending the final SAM task completion signal now so the orchestrator does not mark it stalled."

At the bottom is a collapsed tool invocation labeled "Tool: sam-mcp/complete_task" with a green success indicator, showing that the completion signal was sent. The left sidebar displays a list of previous chat sessions.

Screenshot of the SAM UI with the “Deployments” item highlighted in the left sidebar. A large pink arrow points to it, while the main page shows a “Proposed Architecture” document about deployment environment config variables.

Screenshot of SAM showing a staging deployment status summary: commit `0750bcb1` deployed successfully, PR `#1356` is still a draft, Playwright Visual Tests are in progress, and the existing app deployment is still failing because Docker Compose rejects `services.chat.provider`. The public URL still says “SAM deployment node awaiting release.”

SAM self-hosting setup screen showing a guided “Deploy your own SAM instance” welcome step, with completed checklist items in the sidebar and requirement cards for Cloudflare, GitHub, and a domain.