DemoGPT
🤖 Create agentic apps in a second with your prompts. Everything you need to create an LLM Agent - tools, prompts, frameworks, and models - all in one place.
Runs with mockssource: GitHubPythonMITcommit aca748b71345
Python, MIT licensed. The project labels itself: agent, agents, ai, artificial intelligence, autonomous agents, chatgpt, claude code and coding agents.
DemoGPT runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 7 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Install built a working venv with all dependencies. All 4 tests pass against a mock OpenAI server (2 LLM: OpenAIModel, OpenAIChatModel; 2 RAG: add_files, add_text). Streamlit app launches on port 8592 and returns HTTP 200. The demogpt CLI entry point uses subprocess('streamlit') which resolves only from the venv bin directory (cosmetic).
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.
- sentence-transformers package not installed12 minutes
- Tests require OPENAI_API_KEY2 minutes
- Externally-managed Python environment prevented system-wide pip install1 minute
- pytest not installed0.5 minutes
- BaseRAG has no query() method, tests call query()0.5 minutes
- ChromaDB 'attempt to write a readonly database' between test methods sharing persistent_path0.5 minutes
- Install time
- 5 minutes
- Cold machine to finish
- 55 minutes
- Errors hit and fixed
- 7 hit, 7 fixed with no human help
- How the result was proved
- cd /work/repo && OPENAI_API_KEY=sk-test-key OPENAI_BASE_URL=http://127.0.0.1:8765/v1 /work/repo/venv/bin/python -m pytest tests/ -v exited 0, 4 passed; streamlit run demogpt/app.py --server.port=8592 returned HTTP 200
- Model tokens used
- 207,831
- Exact commit tested
- aca748b71345
- 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.
- **Install**: `pip install -e .` in venv completed with all 130+ dependencies - **Tests**: All 4 tests pass against a mock Argusic server (2 LLM + 2 RAG) - **Streamlit app**: Launches on port 8592 and returns HTTP 200 - **CLI**: Module imports correctly (subprocess `streamlit` path issue is cosmetic — `streamlit run… **Errors encountered and fixed:** 1. Externally-managed Python environment → installed in venv 2. Missing `pytest` → installed 3. Tests need OPENAI_API_KEY → stood up mock Argusic server 4. `BaseRAG` lacks `query()` method → added alias to `run()` in `base.py` 5. ChromaDB persistent path conflict between tests → made paths unique per test 6. Mock returned static response regardless of context → made mock context-aware 7. Missing `sentence-transformers` → installed
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 5 minutes, faster than the median of the 32 comparable projects Argusic has measured.
- Recovered from all 7 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
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.
Of the 33 agent projects Argusic has installed and timed, DemoGPT was the 12th fastest to reach a running state, and 25 of 33 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 | 2/3 | Runs with mocks | 92.00 | 0.16 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.15 |
Topics (from GitHub)
agentagentsaiartificial-intelligenceautonomous-agentschatgptclaude-codecoding-agentsgemini-apilangchainlangchain-applangchain-pythonllmsmobile-appopenaipythonqwenreactweb-app
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/demogpt)Questions
- Does DemoGPT run?
- DemoGPT runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 7 errors on the way, and recorded the session.
- How did Argusic test DemoGPT?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit aca748b71345. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test DemoGPT?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does DemoGPT take to install?
- 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 DemoGPT need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing DemoGPT?
- 7 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does DemoGPT compare with the alternatives?
- Of the 33 agent projects Argusic has installed and timed, DemoGPT was the 12th fastest to reach a running state, and 25 of 33 reached one at all.
- Where is the evidence for DemoGPT?
- 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.