DB-GPT
open-source agentic AI data assistant for the next generation of AI + Data products.
Runs with mockssource: GitHubhomepagePythonMITcommit ca9f014cb3ea
Python, MIT licensed. The project labels itself: agents, bgi, database, deepseek, gpt, gpt 4, hacktoberfest and llm.
DB-GPT runs, with stand-ins for the services it depends on. An Argusic agent installed it in 15 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
DB-GPT 0.8.2 installs with uv, imports all packages, the FastAPI server starts and responds HTTP 200, the CLI (dbgpt --help) lists all commands; 1230+ tests pass across core/app/client/serve packages with 2 pre-existing failures (mock-based regression tests) and 1 pre-existing error (missing pytest fixture).
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.
- attachment_react_adapter tests patched agentic_data_api.StreamingResponse but endpoint now uses _AgentStreamingResponse (2 tests failed)3 minutes
- skill_upload endpoint had no path traversal validation (3 tests failed)2 minutes
- Optional litellm dependency missing for proxy model tests (ModuleNotFoundError)1 minute
- pilot_template directory not accessible from workspace_provisioning module in development mode (6 workspace tests failed)1 minute
- Install time
- 15 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- python -m pytest packages/dbgpt-core/src/dbgpt/ gave 729 passed / 1 error; packages/dbgpt-app/src/dbgpt_app/tests/ + packages/dbgpt-client/src/dbgpt_client/tests/ gave 261 passed / 1 failed; packages/dbgpt-serve/src/dbgpt_serve/*/tests/ gave ~239 passed; server at 127.0.0.1:8787 answered HTTP 200 on /; dbgpt --help printed CLI commands
- Model tokens used
- 415,685
- Exact commit tested
- ca9f014cb3ea
- 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.
=== SERVE TESTS ===
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
353 passed, 1 skipped, 3 warnings in 31.35s
succeeded in 31226ms:
/work/repo/.venv/lib/python3.11/site-packages/pydantic/_internal/_config.py:323: PydanticDeprecat…
warnings.warn(DEPRECATION_MESSAGE, DeprecationWarning)
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
325 passed, 1 skipped, 3 warnings in 30.05s
Good. Now I have all the data I need for the final report.
tokens used
415,685
Good. Now I have all the data I need for the final 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 4 errors 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.
- Took 15 minutes to install, slower than the median of the 10 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 11 agents projects Argusic has installed and timed, DB-GPT was the 10th fastest to reach a running state, and 6 of 11 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 | 0.10 |
Topics (from GitHub)
agentsbgidatabasedeepseekgptgpt-4hacktoberfestllmprivateragsecurityvicuna
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/db-gpt)Questions
- Does DB-GPT run?
- DB-GPT runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 15 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test DB-GPT?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ca9f014cb3ea. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test DB-GPT?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does DB-GPT take to install?
- 15 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 DB-GPT need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing DB-GPT?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does DB-GPT compare with the alternatives?
- Of the 11 agents projects Argusic has installed and timed, DB-GPT was the 10th fastest to reach a running state, and 6 of 11 reached one at all.
- Where is the evidence for DB-GPT?
- 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.