astron-agent
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
Runs with mockssource: GitHubhomepageJavaApache-2.0commit b4f8ed57460c
Java, Apache-2.0 licensed. The project labels itself: agent, agentic ai, agentic workflow, ai, enterprise, enterprise automation, iflytek astron and llm.
astron-agent runs, with stand-ins for the services it depends on. An Argusic agent installed it in 13 minutes and hit 8 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The console React frontend builds successfully into dist/ (103M). All 5 Python microservices (agent, common, workflow, knowledge, memory/database) install deps via uv sync and pass their pytest suites (1835 total tests pass). Go (tenant) and Java (backend) services are not runnable due to missing runtimes.
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
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.
- Frontend Vite build runs out of heap memory (JS OOM)3 minutes
- Agent pyproject.toml flat-layout confuses setuptools discovery2 minutes
- Missing botocore in common/.venv (not listed in pyproject.toml deps)2 minutes
- npm peer dependency conflict with react-json-view requiring React 171 minute
- Missing snowflake-id dependency in common/venv (vs .venv)1 minute
- common module tests need PYTHONPATH to resolve 'common.*' imports1 minute
- Install time
- 13 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 8 hit, 8 fixed with no human help
- How the result was proved
- npm run build completed with assets output (103M dist); pytest ran on agent (324 passed), common (374 passed), workflow (534 passed), knowledge (409 passed), memory/database (194 passed), 1835 total Python tests passed
- Model tokens used
- 351,617
- Exact commit tested
- b4f8ed57460c
- 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.
/bin/sh -lc "# Final verification - confirm Go and Java are not available
which go java docker 2>&1; echo \"===\"
# Check frontend dist has proper content
ls /work/repo/console/frontend/dist/index.html /work/repo/console/frontend/dist/assets/*.js 2>/dev/…
# Verify agent can import key modules
cd /work/repo/core/agent && venv/bin/uv run python -c \"import fastapi; print('fastapi:', fastapi._…
succeeded in 202ms:
fastapi: 0.115.12
All results compiled. Here is my complete report:
tokens used
351,617
All results compiled. Here is my complete report: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
- Recovered from all 8 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, 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.
- Took 13 minutes to install, slower than the median of the 47 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 48 agent projects Argusic has installed and timed, astron-agent was the 33rd fastest to reach a running state, and 34 of 48 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.08 |
Topics (from GitHub)
agentagentic-aiagentic-workflowaienterpriseenterprise-automationiflytek-astronllmllm-opslow-codemcpmulti-agentnext-genorchestrationpythonrpasuperagentworkflowworkflow-engine
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/astron-agent)Questions
- Does astron-agent run?
- astron-agent runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 13 minutes, hitting 8 errors on the way, and recorded the session.
- How did Argusic test astron-agent?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b4f8ed57460c. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test astron-agent?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does astron-agent 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 astron-agent need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing astron-agent?
- 8 things broke in the recorded run, and 8 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does astron-agent compare with the alternatives?
- Of the 48 agent projects Argusic has installed and timed, astron-agent was the 33rd fastest to reach a running state, and 34 of 48 reached one at all.
- Where is the evidence for astron-agent?
- 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.