golembot
Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat, with any LLM provider.
Runssource: GitHubhomepageTypeScriptMITcommit 1ffb1568ee7d
TypeScript, MIT licensed. The project labels itself: ai, ai agent, ai assistant, bot framework, chatbot, claude code, cli and codex.
golembot runs. An Argusic agent installed it in 1 minute and hit no errors on a clean machine with no GPU, and the whole session was recorded.
pnpm install succeeds, tsc build succeeds, all 1336 unit tests pass, the CLI binary prints help and version, the HTTP serve mode listens on a port and answers /health with 200, and the gateway mode starts with all channel stubs and answers /health with 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
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.
- Install time
- 1 minutes
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- pnpm test exited 0, 1336 passed; node dist/cli.js serve --port 3457 and curl /health returned 200; node dist/cli.js gateway --port 3458 and curl /health returned 200
- Model tokens used
- 52,975
- Exact commit tested
- 1ffb1568ee7d
- 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.
- **Gateway mode** — started on port 3458, dashboard and all 7 channel stubs displayed, `/health` r… No mocks were needed — the framework's own unit tests exercise real gateway pipelines, engine snaps… tokens used 52,975 **GolemBot v0.51.0** — install, build, test, and launch all succeeded with zero errors. - **pnpm install** — 654 dependencies linked without issues (sharp, esbuild native builds OK) - **tsc build** — compiled cleanly to `dist/` - **pnpm test** — all 44 test files passed, 1336 passed / 6 skipped / 0 failed - **CLI** — `node dist/cli.js --help` shows all 10 commands; `doctor` checks 5/6 criteria (opencode… - **HTTP serve mode** — started on port 3457, `/health` returned **200** - **Gateway mode** — started on port 3458, dashboard and all 7 channel stubs displayed, `/health` r… No mocks were needed — the framework's own unit tests exercise real gateway pipelines, engine snaps…
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.
- Installed in 1 minute, faster than the median of the 236 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 237 ai projects Argusic has installed and timed, golembot was the 37th fastest to reach a running state, and 168 of 237 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.
- A quick evaluation: it was running 1 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
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
Topics (from GitHub)
aiai-agentai-assistantbot-frameworkchatbotclaude-codeclicodexcoding-agentcursordingtalkdiscordfeishularkllmopencodeslacktelegramtypescriptwecom
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/golembot)Questions
- Does golembot run?
- Yes. golembot runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test golembot?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1ffb1568ee7d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test golembot?
- The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does golembot take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does golembot need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing golembot?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does golembot compare with the alternatives?
- Of the 237 ai projects Argusic has installed and timed, golembot was the 37th fastest to reach a running state, and 168 of 237 reached one at all.
- Where is the evidence for golembot?
- 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.