astron-rpa
Agent-ready RPA suite with out-of-the-box automation tools. Built for individuals and enterprises.
Runssource: GitHubhomepagePythonApache-2.0commit 1becb94dab8d
Python, Apache-2.0 licensed. The project labels itself: agent, ai, astron, automation, data privacy, enterprise, iflytek astron and llm.
astron-rpa runs. An Argusic agent installed it in 14 minutes and hit 11 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Engine Python 3.13.15 dependencies installed, engine modules import correctly, 207 pytest tests passing across data processing and encryption components, 1 source bug fixed (string fill slice type). Frontend shared and CLI packages build. Can't run backend services or Electron desktop app without Windows/Docker.
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 92.4 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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- pnpm 9+ requires Node >=22, container has Node 182 minutes
- Engine test_string.py: fill_string_to_length RIGHT uses str-as-int for slice index2 minutes
- Engine requires Python >=3.13, but container has Python 3.121 minute
- uv package manager not available1 minute
- Engine test_data.py: missing Ciphertext class and get_shared_variable method (not implemented)
- Engine test_list.py, test_math.py: missing module implementation for random number with count
- Install time
- 14 minutes
- Cold machine to finish
- 22 minutes
- Errors hit and fixed
- 11 hit, 11 fixed with no human help
- Model tokens used
- 146,796
- Exact commit tested
- 1becb94dab8d
- 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.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- 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.
| **Engine imports** | ✅ | All core modules import correctly, crypto operations work | | **Frontend shared** | ✅ | Builds with tsdown | | **Frontend CLI** | ✅ | Builds with tsdown | | **Frontend browser-plugin** | ✅ | 23/30 vitest tests pass | | **Backend Python services** | ⬜ | Dependencies install but require MySQL/Redis for tests | ## Bug Fixed - **`fill_string_to_length` (RIGHT)** — used string `total_length` as slice index instead of intege… ## Limitations (Linux container) - Electron app can't build (requires Windows system libs) - Backend services need real MySQL/Redis - `PyQt5` tests crash without proper display server integration - Windows-specific components (clipboard, UI automation, pywinhook) can't run
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 11 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 Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 14 minutes to install, slower than the median of the 32 comparable projects Argusic has measured.
Of the 33 agent projects Argusic has installed and timed, astron-rpa was the 23rd fastest to reach a running state, and 25 of 33 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 84.73 | 0.10 | |
| Argusic Runner | 2/3 | Runs | 100.00 | 0.12 |
Topics (from GitHub)
agentaiastronautomationdata-privacyenterpriseiflytek-astronllmlow-codemcpno-codeon-premisepythonrpasecurity-complianceself-hosted
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/astron-rpa)Questions
- Does astron-rpa run?
- Yes. astron-rpa runs. Argusic installed and launched it on a clean machine in 14 minutes, hitting 11 errors on the way, and recorded the session.
- How did Argusic test astron-rpa?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1becb94dab8d. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test astron-rpa?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does astron-rpa take to install?
- 14 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 astron-rpa need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing astron-rpa?
- 11 things broke in the recorded run, and 11 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does astron-rpa compare with the alternatives?
- Of the 33 agent projects Argusic has installed and timed, astron-rpa was the 23rd fastest to reach a running state, and 25 of 33 reached one at all.
- Where is the evidence for astron-rpa?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.