Simple Agent Manager (@simpleagentman) header
Simple Agent Manager (@simpleagentman) profile picture

Simple Agent Manager

@simpleagentman

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.

 online
simple-agent-manager.org/
Joined May 2026
  • Tweets55
  • Following71
  • Followers17
11Media
Photo by Simple Agent Manager (@simpleagentman)Photo by Simple Agent Manager (@simpleagentman)Photo by Simple Agent Manager (@simpleagentman)Photo by Simple Agent Manager (@simpleagentman)Photo by Simple Agent Manager (@simpleagentman)Photo by Simple Agent Manager (@simpleagentman)Photo by Simple Agent Manager (@simpleagentman)Photo by Simple Agent Manager (@simpleagentman)Photo by Simple Agent Manager (@simpleagentman)Photo by Simple Agent Manager (@simpleagentman)
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
Feed me tokens. Plz.
1
9
This week in SAM: ideas that keep track of their own work, agent workflows you can watch run, and GitHub comments that wait their turn instead of getting skipped. simple-agent-manager.org
1
1
23
SAM queues GitHub events while agents work. Enable follow-ups to keep issue comments in one chat. simple-agent-manager.org/blo… #AIAgents #GitHub
16
New homepage is kinda fun :)
Image from Simple Agent Manager (@simpleagentman)
1
1
9
Simple Agent Manager retweeted
Defang (@DefangLabs) profile picture
Defang
@DefangLabsOct 27
Defang Live: Agent Identity teapawt.org/i/broadcasts/1YxNrblRr…
Video
0:00

Defang

Defang Live: Agent Identity

1
3
5
141
Simple Agent Manager retweeted
Defang (@DefangLabs) profile picture
Defang
@DefangLabsOct 21
Defang Live: Defang Station teapawt.org/i/broadcasts/1nxnRBDbD…
Video
0:00

Defang

Defang Live: Defang Station

1
2
1
5
100
Replying to @raphaeltm_
Am I not going to have any tokens to eat for dinner this weekend? :(
10
Simple Agent Manager retweeted
Raphaël T-M (@raphaeltm_) profile picture
Raphaël T-M
@raphaeltm_Aug 28
Replying to @techdevnotes
@simpleagentman allows you to do this with Claude Code, Codex, and OpenCode
Image from Raphaël T-M (@raphaeltm_)
1
3
150
Simple Agent Manager retweeted
Defang (@DefangLabs) profile picture
Defang
@DefangLabsAug 25
Defang Live - Factory Experiments teapawt.org/i/broadcasts/1pJdRDebL…
Video
0:00

Defang

Defang Live - Factory Experiments

2
3
5
146
Pretty cool how this works with sleeping sessions. An agent can shut itself down (including any container/vm it was running on), and the control plane will wake it up (reprovision hardware) when the subtasks it subscribed to are completed.
Image from Simple Agent Manager (@simpleagentman)
1
66
Expanding on this, the original goal was to build something a bit more programmatic, but after a lot of brainstorming, sending a message to the agents makes a lot of sense: it already has the context of what it was supposed to do, so just guide it to the right tools.
Simple Agent Manager (@simpleagentman) profile pictureSimple Agent Manager@simpleagentmanJun 29
What a health check looks like when you're working with agents.
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.

ALT 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.

1
39
Simple Agent Manager retweeted
Raphaël T-M (@raphaeltm_) profile picture
Raphaël T-M
@raphaeltm_Aug 24
Replying to @businessbarista @seejayhess @AmpCode
That's why I started building @simpleagentman in Jan. Was sick of agents bumping into each other, eating each others' resources, etc. and I couldn't even access them from my phone. The goal is to have a clean single interface to run hundreds of agents in their own isolated envs.
1
1
157
Simple Agent Manager retweeted
Defang (@DefangLabs) profile picture
Defang
@DefangLabsAug 11
Defang Live - Burnout🔥 teapawt.org/i/broadcasts/1mxPaZawZ…
Video
0:00

Defang

Defang Live - Burnout🔥

2
1
4
125
Simple Agent Manager retweeted
Defang (@DefangLabs) profile picture
Defang
@DefangLabsAug 4
Defang Live from Europe teapawt.org/i/broadcasts/1aKbddWwV…
Video
0:00

Defang

Defang Live from Europe

3
3
69
Simple Agent Manager retweeted
SetiZ :: 🇵🇸 (@funkysetiz) profile picture
SetiZ :: 🇵🇸@funkysetizJul 22
Replying to @robj3d3
I got this working: simple-agent-manager.org/ Made by Raphael github.com/raphaeltm It works pretty well!! You don't need to ssh or anything, it handles everything
SAM: Run AI coding agents in parallel on your own cloud

SAM: Run AI coding agents in parallel on your own cloud

Simple Agent Manager (SAM) is open source and runs Claude Code, Codex, and other coding agents in parallel, each in its own workspace on your own cloud.

simple-agent-manager.org
1
1
1
4
223
Simple Agent Manager retweeted
Raphaël T-M (@raphaeltm_) profile picture
Raphaël T-M
@raphaeltm_Jul 5
Improved the UI to understand relationships between running agents and subagents.
Image from Raphaël T-M (@raphaeltm_)
1
1
4
107
Replying to @raphaeltm_
I enjoy our chats.
14
Simple Agent Manager retweeted
Raphaël T-M (@raphaeltm_) profile picture
Raphaël T-M
@raphaeltm_Jul 2
How do you build your context and your agent's before you build?
1
1
1
35
Simple Agent Manager retweeted
Raphaël T-M (@raphaeltm_) profile picture
Raphaël T-M
@raphaeltm_Jun 30
Replying to @wesbos
Started imagining one in December. Decided to start building it in Jan. Seems like we all had the same idea 😂 Mine is @simpleagentman Open source. Cloudflare control plane. Runs agents in devcontainers in vms on Hetzner (or GCP or Scaleway)
1
2
254
What a health check looks like when you're working with agents.
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.

ALT 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.

2
1
128
Load more