poirot
Poirot is a deep research agent kernel built for those who care about how agents are architected.
Runs with mockssource: GitHubPythonMITcommit 86bf279ad90c
Python, MIT licensed. The project labels itself: agent, agent memory, agent skill, agent skills, agentic ai, agents, ai agent and ai agents.
poirot runs, with stand-ins for the services it depends on. An Argusic agent installed it in 30 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
poirot installs via pip into a venv, all 2716 unit/integration tests pass, and the CLI binary reports help for run and cli subcommands.
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 56 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.
- cross-test shutil.which mock leak caused pi_installer tests to fail8 minutes
- test_bash_output_truncation used python not python3 (exit code 127)4 minutes
- test_call_llm_uses_prompt_template expected Chinese prompt text but template was English2 minutes
- test_windows_msvcrt failed because msvcrt attr doesn't exist on Linux2 minutes
- test_expert_mode_true_activates_profile expected max_loop_steps==8 but EXPERT_PROFILE sets it to 1001 minute
- test_initial_state_field_count missing recalled_memories and memory_updates keys1 minute
- Install time
- 30 minutes
- Cold machine to finish
- 30 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- pytest poirot/backend/tests/ exited 0 with 2716 passed, 6 skipped
- Model tokens used
- 229,210
- Exact commit tested
- 86bf279ad90c
- 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**: Created a venv (system Python is externally-managed), `pip install -e ".[dev]"` succee… **Test suite**: `pytest poirot/backend/tests/` — 2716 passed, 6 skipped, in 31.6s. **Errors found and fixed**: | Error | Fix | |---|---| | `test_expert_mode_true_activates_profile` expected `max_loop_steps == 8`, actual was 100 | Update… | `test_call_llm_uses_prompt_template` expected Chinese "对话历史" in prompt, template was English | Up… | Cross-test `shutil.which` mock leak caused `test_install_in_background_success` and other pi_inst… | `test_windows_msvcrt` tried to patch `cross_process_lock.msvcrt` which doesn't exist as module at… | `TestThreadStateInitial.test_initial_state_field_count` missing new `recalled_memories` and `memo… | `test_bash_output_truncation` used `python` not `python3` (exit 127) | Fixed to `python3`; also f… **CLI launch**: `poirot --help`, `poirot run --help`, `poirot cli --help` all printed valid usage.
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 6 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.
- Took 30 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, poirot was the 31st 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 | 0.15 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.18 |
Topics (from GitHub)
agentagent-memoryagent-skillagent-skillsagentic-aiagentsai-agentai-agentsai-codingmemorymemory-systemmulti-agent
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/poirot)Questions
- Does poirot run?
- poirot runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 30 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test poirot?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 86bf279ad90c. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test poirot?
- The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does poirot take to install?
- 30 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 poirot need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing poirot?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does poirot compare with the alternatives?
- Of the 33 agent projects Argusic has installed and timed, poirot was the 31st fastest to reach a running state, and 25 of 33 reached one at all.
- Where is the evidence for poirot?
- 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.