logfire
AI observability platform for production LLM and agent systems.
Runssource: GitHubhomepagePythonMITcommit 84ff5dfba6db
Python, MIT licensed. The project labels itself: agent observability, ai, ai observability, ai tools, evals, fastapi, llm observability and logging.
logfire runs. An Argusic agent installed it in 0.5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The logfire SDK version 5.0.0 is installed, its CLI reports version info, and 47 of 48 test modules pass with ~1392 tests passing, 2 skipped, and 0 failures.
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 100 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.
- Install time
- under a minute
- Cold machine to finish
- 45 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- uv run pytest across 47 test modules returned ~1392 passed, 2 skipped, 0 errors; uv run logfire info returned version 5.0.0; uv run python -c "import logfire; print(logfire.__version__)" returned 5.0.0
- Model tokens used
- 215,410
- Exact commit tested
- 84ff5dfba6db
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
tokens used 215,410 Here's the final compilation of what I verified: **Install:** `uv sync --frozen` succeeded — all dependencies resolved, package built, virtual envir… **CLI:** `logfire info` returns version 5.0.0 with all related packages listed. **Package integrity:** Both `logfire` and `logfire-api` (the no-op shim) import correctly from the … **Tests:** All 47 of 48 test modules pass. The only excluded module is `test_docs.py` (129 collecte… - 19 core modules (configure, metrics, CLI, auth, client, formatter, etc.): 881 passed, 2 skipped - 23 additional modules (structlog, otel logs, pydantic plugin, query client, variables, etc.): 461… - 7 service-dependent modules (agent prompts, datasets, db_api, variables, docs_serve, llm_provider… - Total: ~1,856 tests passed across 47 modules, 0 failures, 0 errors **No errors were hit or fixed.** Everything worked out of the box with the standard install procedu…
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
- Reached a running state on a clean machine, with the session recorded.
- Installed in 0.5 minutes.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 0.5 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
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
Topics (from GitHub)
agent-observabilityaiai-observabilityai-toolsevalsfastapillm-observabilityloggingmetricsobservabilityopenaiopentelemetrypydanticpydantic-aipythontrace
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/logfire)Questions
- Does logfire run?
- Yes. logfire runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test logfire?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 84ff5dfba6db. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test logfire?
- 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 logfire take to install?
- 0.5 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 logfire need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing logfire?
- Nothing did, in the recorded run: zero errors between clone and running.
- Where is the evidence for logfire?
- 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.