CyberClaw

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

Runs with mockssource: GitHubPythonMITcommit 12b7c6d52fcc

Python, MIT licensed. The project labels itself: agent, agent framework, ai agent, ai safety, claude code, cross platform, enterprise ai and langchain.

CyberClaw runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Installed and the 130 tests all pass. The CLI starts, connects to an LLM provider, completes a tool-augmented conversation (user query -> get_current_time tool call -> mock response displayed), and exits cleanly.

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 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
1
last tested
stars
346
forks
32
open issues
0
watchers
0
size
1 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 CyberClaw, 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.

  • Mock LLM server launched via nohup backgrounding exited when its parent shell closed; cyberclaw run then failed with connection refused.1 minute
Install time
under a minute
Cold machine to finish
4 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
.venv/bin/cyberclaw run with stdin piped: now ji dian? triggered Tool Call: get_current_time, mock server returned time string, agent displayed it, /exit shut down cleanly; 130/130 unittest cases passed.
Model tokens used
197,891
Exact commit tested
12b7c6d52fcc
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
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

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

**What happened**
- `pip install -e .` completed without errors — all 40+ dependencies resolved cleanly.
- **130/130** unit tests pass (`unittest discover -s tests -v` → `OK`, 0 failures).
- `cyberclaw --help` shows three commands: `config`, `run`, `monitor`.
- `cyberclaw monitor` renders its ASCII-terminal dashboard (Rich-based live stream).
- A schema-correct Argusic-compatible mock server (stand-in for the real LLM) was stood up on `127.…
- `cyberclaw run` with stdin piped "现在几点?" → agent called `get_current_time` via LangGraph → mock r…
**One error encountered**
The initial `nohup`+`&` background of the mock server died when the spawning shell exited. Fix: rel…
**No real API keys needed**
The mock server fulfilled the Argusic-compatible contract. A user with a real key can drop it in `.…
**Final reported line:**

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

  • Installed in 0.5 minutes, faster than the median of the 140 comparable projects Argusic has measured.
  • Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 141 agent projects Argusic has installed and timed, CyberClaw was the 12th fastest to reach a running state, and 94 of 141 reached one at all.

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 Runner1/3Runs with mocks92.000.03

Topics (from GitHub)

agentagent-frameworkai-agentai-safetyclaude-codecross-platformenterprise-ailangchainlanggraphllmopenclawpythontransparent-aitwo-phase-invocation

Embed the badge

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

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

Questions

Does CyberClaw run?
CyberClaw runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test CyberClaw?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 12b7c6d52fcc. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test CyberClaw?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does CyberClaw take to install?
0.5 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 CyberClaw need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing CyberClaw?
1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does CyberClaw compare with the alternatives?
Of the 141 agent projects Argusic has installed and timed, CyberClaw was the 12th fastest to reach a running state, and 94 of 141 reached one at all.
Where is the evidence for CyberClaw?
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