AnyModelBot

🤖 Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. Reach them in the app, WeChat or Feishu; they remember you, work in the background, run commands and use your computer. Pay per use.

Runssource: GitHubhomepagePythonMITcommit c4b0e5f17f60

Python, MIT licensed. The project labels itself: ai agent, ai assistant, chatbot, claude, computer use, deepseek, desktop app and dsh.

AnyModelBot runs. An Argusic agent installed it in 13 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Install and build succeed: npm install and npm run setup completed; TypeScript build produces dist/; magpie gateway binary built at build/bin/magpie-linux-x64; dsh-runtime prepared; npm start serves the web UI on http://127.0.0.1:3600 returning HTTP 200 with the management interface HTML; API endpoints return HTTP 200

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.11 (measured)
recorded runs
1
last tested
stars
4,344
forks
107
open issues
3
watchers
20
size
149 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing AnyModelBot, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • git submodule vendor/magpie commit hash e4ca47b0 does not exist on remote anymore; clone failed with 'Unable to find current revision'8 minutes
  • Node.js 18.19.1 is installed but project requires >=22.13; Go is not installed but project requires 1.26.8+3 minutes
Install time
13 minutes
Cold machine to finish
13 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
npm test: 113/119 test files passed, 1952/2057 tests passed (1 failed - test/skills.integration.test.ts: DSH runtime skill tool assertions mismatch)
Model tokens used
108,317
Exact commit tested
c4b0e5f17f60
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

  <link rel="apple-touch-icon" href="/amb/static/assets/apple-touch-icon.png" />
  <script>
---api---
200
---test-suite---
2026-11-18T05:13:39.234Z INFO  [main] 收到 SIGTERM,正在退出…
The UI serves proper HTML, and the API endpoint for bots returns 200. Everything works.
Now let me compile the final JSON result:
tokens used
108,317
The UI serves proper HTML, and the API endpoint for bots returns 200. Everything works.
Now let me compile the final JSON result:

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Reached a running state on a clean machine, with the session recorded.
  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Took 13 minutes to install, slower than the median of the 80 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 81 ai-agent projects Argusic has installed and timed, AnyModelBot was the 60th fastest to reach a running state, and 56 of 81 reached one at all.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.11

Topics (from GitHub)

ai-agentai-assistantchatbotclaudecomputer-usedeepseekdesktop-appdshelectronfeishugeminigptgrokllmlocal-firstmodelflaremulti-modelopenai-compatiblepersonal-ai-agentwechat

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/AnyModelBot.svg)](https://argusic.com/subject/anymodelbot)

Questions

Does AnyModelBot run?
Yes. AnyModelBot runs. Argusic installed and launched it on a clean machine in 13 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test AnyModelBot?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit c4b0e5f17f60. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test AnyModelBot?
The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does AnyModelBot take to install?
13 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does AnyModelBot need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing AnyModelBot?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does AnyModelBot compare with the alternatives?
Of the 81 ai-agent projects Argusic has installed and timed, AnyModelBot was the 60th fastest to reach a running state, and 56 of 81 reached one at all.
Where is the evidence for AnyModelBot?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion