Yes. cocoindex runs. Argusic installed and launched it on a clean machine in 13 minutes, hitting 5 errors on the way, and recorded the session.

How did Argusic test cocoindex?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit f1c1ba4a83d3. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test cocoindex?

The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does cocoindex take to install?

13 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 cocoindex need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing cocoindex?

5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for cocoindex?

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.

cocoindex

Incremental engine for long horizon agents 🌟 Star if you like it!

Runssource: GitHub homepageRustApache-2.0commit f1c1ba4a83d3

Rust, Apache-2.0 licensed. The project labels itself: agentic data framework, ai, ai agents, change data capture, codebase intelligence, context engineering, data engineering and data indexing.

cocoindex runs. An Argusic agent installed it in 13 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Python package imports, Rust extension builds, all core tests pass (611 Rust + 857 Python), mypy type-checks 297 files clean, CLI runs all subcommands, and the files_transform example pipeline successfully converts markdown files to HTML with correct incremental change detection.
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

verdict: Runs
Argusic Score: 100 / 100
cost of the verifying run: $0.07 (measured)
recorded runs: 1
last tested: 2026-09-27
stars: 11,603
forks: 905
open issues: 89
watchers: 50
size: 114 MB
created: 2025-03-03
last push: 2026-09-24

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-27. 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.

Time lost to each failure while testing cocoindex, drawn from the recorded run — Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

uv not installed in container1 minute
Rust toolchain not installed1 minute
cargo test fails linking libpython3.12 (system Python 3.12 lacks shared lib, venv uses Python 3.11)1 minute
maturin develop fails with 'No such file or directory'1 minute
CLI test fails: cocoindex command not in PATH

Install time: 13 minutes
Cold machine to finish: 13 minutes
Errors hit and fixed: 5 hit, 5 fixed with no human help
How the result was proved: cargo test: 611 passed, 0 failed; pytest python/tests/: 802 passed, 4 skipped; pytest python/tests/cli/: 55 passed; python -m mypy: no issues; files_transform example: 2/2 files processed to HTML, incremental re-run showed 1 unchanged/1 reprocessed
Model tokens used: 381,182
Exact commit tested: f1c1ba4a83d3
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.

**Launch and verification** — exercised three ways:
- **Rust tests**: 611 passed, 0 failed (`cargo test` with `PYO3_PYTHON` set to the venv's Python 3.…
- **Python tests**: 802 passed, 4 skipped (`pytest python/tests/`, excluding connector tests needin…
- **CLI tests**: 55 passed, 0 failed
- **Type checks**: mypy found no issues in 297 source files
- **End-to-end example**: files_transform pipeline ingested 2 markdown files into HTML output, incr…
**Error record** — all 5 errors hit were environmental, each fixed:
1. `uv` not in container → installed via `python3 -m venv + pip install uv`
2. `rustc`/`cargo` not in container → installed via `rustup`
3. `cargo test` linking failed (`libpython3.12` not found) → set `PYO3_PYTHON=/work/repo/.venv/bin/…
4. `maturin develop` failed ("No such file or directory") → run `/work/repo/.venv/bin/maturin devel…
5. CLI test failed (`cocoindex: command not found`) → added `.venv/bin` to `PATH`

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 13 minutes.
Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
Ran without a GPU, so it does not need one to start.
Licensed Apache-2.0, as reported by its host.

What did not, or is not known

Measured once so far. A single attempt shows it can run, not that it runs reliably.

What it is a reasonable choice for

Trying it on a laptop or a small server: it reached a running state without a GPU.

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	100.00	0.07	2026-09-27 01:28 UTC

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/cocoindex.svg)](https://argusic.com/subject/cocoindex)

Questions

Does cocoindex run?: Yes. cocoindex runs. Argusic installed and launched it on a clean machine in 13 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test cocoindex?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit f1c1ba4a83d3. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test cocoindex?: The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does cocoindex take to install?: 13 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 cocoindex need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing cocoindex?: 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for cocoindex?: 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.