Yes. txtai runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 19 errors on the way, and recorded the session.

How did Argusic test txtai?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 483dbd3b3bd8. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test txtai?

The run that produced this verdict cost $0.31: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does txtai take to install?

2 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 txtai need a GPU?

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

What goes wrong when installing txtai?

19 things broke in the recorded run, and 14 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for txtai?

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.

txtai

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Runssource: GitHub homepagePythonApache-2.0commit 483dbd3b3bd8

Python, Apache-2.0 licensed. The project labels itself: agents, ai, ai agents, embeddings, information retrieval, language model, large language models and llm.

txtai runs. An Argusic agent installed it in 2 minutes and hit 19 errors on a clean machine with no GPU, and the whole session was recorded.

txtai 9.14.0 installed in venv, all core embeddings/graph/workflow/agent/cloud/vector/scoring tests pass, API responds to search/index/count endpoints with real model inference, ~470 automated tests pass across 30 test suites
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 94.7 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 94.7 / 100
cost of the verifying run: $0.31 (measured)
recorded runs: 1
last tested: 2026-09-26
stars: 12,982
forks: 901
open issues: 17
watchers: 114
size: 55 MB
created: 2020-08-09
last push: 2026-09-25

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-26. 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 txtai, 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.

docling/liteparse missing (testDocling, testLiteParse errors)3 minutes
sentence-transformers not installed (testShortcuts ImportError)2 minutes
Externally-managed Python environment blocked system pip install1 minute
torchvision missing (transformers import error)1 minute
scikit-learn/scipy missing (testwords ImportError)1 minute
grand-cypher/grand-graph missing (testShortcuts graph error)1 minute

Install time: 2 minutes
Cold machine to finish: 83 minutes
Errors hit and fixed: 19 hit, 14 fixed with no human help
How the result was proved: FastAPI testclient GET /search returned 200 with real semantic search results using sentence-transformers/nli-mpnet-base-v2 model; 470+ tests passing across 30+ suites
Model tokens used: 1,548,363
Exact commit tested: 483dbd3b3bd8
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.

5. LiteLLM auth failure (needs real API key)
6. PEFT not installed (optional, for LoRA training)
exec
/bin/sh -lc "echo \"{\\\"install_succeeded\\\": true, \\\"launch_succeeded\\\": true, \\\"install_m…
 succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 2, "errors": [{"msg": "Ext…
Now I have all the data. Let me compute the elapsed time precisely and output the final result.
The session started at about 19:16 UTC and ends at about 20:38 UTC. I started around 19:16 and ende…
tokens used
1,548,363
Now I have all the data. Let me compute the elapsed time precisely and output the final result.
The session started at about 19:16 UTC and ends at about 20:38 UTC. I started around 19:16 and ende…

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 2 minutes, faster than the median of the 13 comparable projects Argusic has measured.
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

Hit 19 errors during setup, 5 of which were not solved.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 14 agents projects Argusic has installed and timed, txtai was the 4th fastest to reach a running state, and 8 of 14 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.
A quick evaluation: it was running 2 minutes after the clone.

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	94.74	0.31	2026-09-26 20:39 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/txtai.svg)](https://argusic.com/subject/txtai)

Questions

Does txtai run?: Yes. txtai runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 19 errors on the way, and recorded the session.
How did Argusic test txtai?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 483dbd3b3bd8. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test txtai?: The run that produced this verdict cost $0.31: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does txtai take to install?: 2 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 txtai need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing txtai?: 19 things broke in the recorded run, and 14 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does txtai compare with the alternatives?: Of the 14 agents projects Argusic has installed and timed, txtai was the 4th fastest to reach a running state, and 8 of 14 reached one at all.
Where is the evidence for txtai?: 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.