autoflow
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
Could not verifysource: GitHubhomepageTypeScriptApache-2.0commit c4cb19d8fa20
TypeScript, Apache-2.0 licensed. The project labels itself: chatbot, cot, graphrag, knowledge graph, mysql, rag, serverless and vector database.
Argusic could not get autoflow running. An Argusic agent installed it in 3 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.
Python dependencies installed and backend module loads 138 API routes, but the app cannot start because TiDB/MySQL server is unreachable on localhost:4000, no Docker is available to start it, and no third-party API keys are provided for LLM or embedding models.
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 25 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.
- TiDB/MySQL server required — backend engine connects to localhost:4000 on module import; no Docker and no root to install MySQL/TiDB15 minutes
- No third-party API keys available — 7 backend LLM tests fail with AuthenticationError, core model/knowledge_graph tests fail needing OpenAI, Jina AI, etc.10 minutes
- Backend lifespan startup fails — engine.connect() raises OperationalError (2003) to localhost:4000; 138 routes import but server cannot bind10 minutes
- No Redis server — required by Celery/Flower for async task queue, cannot start full backend5 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 24 minutes
- Errors hit and fixed
- 4 hit, 0 fixed with no human help
- How the result was proved
- cd backend && PYTHONPATH=$PWD .venv/bin/python -c 'from app.api_server import app; print(len(app.routes))' returned 138; .venv/bin/python -m pytest tests/test_dynamic_models.py -v returned 1 passed; import of app.core.db creates engine eagerly and connecting to localhost:4000 raises OperationalError
- Model tokens used
- 700,566
- Exact commit tested
- c4cb19d8fa20
- 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
- Whether it works at all
- this run verified nothing, so this page makes no claim either way
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/work/repo/backend/.venv/lib/python3.12/site-packages/pymysql/connections.py", line 361, in…
self.connect()
File "/work/repo/backend/.venv/lib/python3.12/site-packages/pymysql/connections.py", line 716, in…
raise exc
sqlalchemy.exc.OperationalError: (pymysql.err.OperationalError) (2003, "Can't connect to MySQL serv…
(Background on this error at: https://sqlalche.me/e/20/e3q8)
Attempting lifespan startup...
Here is the final report based on everything I verified.
tokens used
700,566
Here is the final report based on everything I verified.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 3 minutes.
- 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
- An agent with no time limit did not get it running.
- Hit 4 errors during setup, 4 of which were not solved.
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 | Did not run | 20.00 | 0.23 | |
| Argusic Runner | 1/3 | Did not run | 30.00 | 0.12 |
Topics (from GitHub)
chatbotcotgraphragknowledge-graphmysqlragserverlessvector-database
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/autoflow)Questions
- Does autoflow run?
- Argusic could not verify that autoflow runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test autoflow?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c4cb19d8fa20. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test autoflow?
- 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 autoflow take to install?
- 3 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 autoflow need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing autoflow?
- 4 things broke in the recorded run. Each one, and the time it cost, is listed on this page.
- Where is the evidence for autoflow?
- 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.