PixelRAG
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
Runssource: GitHubhomepagePythonApache-2.0commit aba824b3172c
Python, Apache-2.0 licensed. The project labels itself: agent, ai, memory, multimodal, rag, search, searchengine and vision.
PixelRAG runs. An Argusic agent installed it in 30 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Core install, pixelshot/pixelrag CLIs, real page renders, text extraction, chunking, and the hosted search API all verified working; the full test suite passes 106/106 runnable tests.
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.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Render tests failed: zstd binary/zstandard module missing, could not extract bundled 81MB headless_shell15 minutes
- uv not installed; project requires uv sync3 minutes
- pytest missing after uv sync (extras not in default sync)1 minute
- Install time
- 30 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- uv run pytest tests/ -> 106 passed, 5 skipped in 33.29s; pixelshot https://example.com -o /tmp/pixelrag-e2e/net -> 1 tile dir with page_height=2669, complete:true, JPEG decoded clean via ffmpeg; pixelrag chunk --tiles-dir -> 1 article, 3 chunks written; curl -X POST https://api.pixelrag.ai/search -> HTTP 200 with real hit
- Model tokens used
- 273,501
- Exact commit tested
- aba824b3172c
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
1. `pytest` not present in default sync → fixed with `uv sync --extra dev` (0 min attributable). 2. Render tests failed: `RuntimeError: zstd not found. Install with: apt install zstd (or pip insta… 3. Pre-existing skipped tests (not errors): `faiss`/`serve`/`pdf` extras not installed in CI-style … **Verification (all observed here)** - Full suite: `uv run pytest tests/` → `106 passed, 5 skipped in 33.29s`. - All 9 render/chrome failures fixed and re-passing (headless_shell Chromium 150.0.7844.0 installed… - Real end-to-end: `pixelshot https://example.com -o /tmp/pixelrag-e2e/net` → 1 tile dir, `tiles.js… - `--extract-text` on example.com produced a real `text.md` with the page body; JPEG decodes clean. - `pixelrag chunk --tiles-dir` on a shard-style tree → `1 articles chunked, 1 tiles → 3 chunks, 3 f… - README's hosted search: `curl -X POST https://api.pixelrag.ai/search` → HTTP 200 with a real hit … - `pixelshot --help`, `pixelrag --help`, `pixelshot which-chrome` all return expected output. Final state: core install + CLI + render + chunk + hosted search verified; heavy ML extras (torch/f…
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.
- Recovered from all 3 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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 30 minutes to install, slower than the median of the 137 comparable projects Argusic has measured.
Of the 138 agent projects Argusic has installed and timed, PixelRAG was the 126th fastest to reach a running state, and 92 of 138 reached one at all.
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
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/pixelrag)Questions
- Does PixelRAG run?
- Yes. PixelRAG runs. Argusic installed and launched it on a clean machine in 30 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test PixelRAG?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit aba824b3172c. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test PixelRAG?
- 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 PixelRAG 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 PixelRAG need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing PixelRAG?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does PixelRAG compare with the alternatives?
- Of the 138 agent projects Argusic has installed and timed, PixelRAG was the 126th fastest to reach a running state, and 92 of 138 reached one at all.
- Where is the evidence for PixelRAG?
- 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.