intentkit

IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.

Runssource: GitHubhomepagePythonMITcommit afc8cc442552

Python, MIT licensed. The project labels itself: agent framework, agentic, ai, ai agent, ai agent framework, blockchain, intents and python.

intentkit runs. An Argusic agent installed it in 35 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The IntentKit Python package installs with uv, 1854 tests pass (34 skipped on-chain tests need RPC endpoints), and the API server starts and serves OpenAPI docs on port 8000.

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 96 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.54 (measured)
recorded runs
2
last tested
stars
6,520
forks
715
open issues
99
watchers
69
size
17 MB
created
last push

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.

Time lost to each failure while testing intentkit, 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.

  • psycopg import fails: no pq wrapper (libpq not found)8 minutes
  • testing.postgresql cannot find initdb/postgres3 minutes
  • BDD tests fail without Redis running3 minutes
  • uv not installed in container2 minutes
  • Python 3.13 not available1 minute
  • API server startup fails without .env1 minute
Install time
35 minutes
Cold machine to finish
28 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
python -m pytest tests/ --ignore=tests/bdd/test_engine_conversation --ignore=tests/manual -q: 1854 passed, 34 skipped, 0 failed in 63s; uvicorn app.api:app launched, curl returned 200 on /docs and /openapi.json
Model tokens used
174,626
Exact commit tested
afc8cc442552
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.

 succeeded in 3998ms:
=== Quick final verification ===
[AlertHandler] No alert service configured, skipping handler setup
TRANSPORT_TIMEOUT_ERRORS tuple has 8 entries
Chain supports 7 networks
Import test: PASS
Now, I have all the data. Let me compile the final result.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 35, "e…
tokens used
174,626
Now, I have all the data. Let me compile the final result.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 35, "e…

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 6 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 MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 35 minutes to install, slower than the median of the 62 comparable projects Argusic has measured.

Of the 63 agent-framework projects Argusic has installed and timed, intentkit was the 61st fastest to reach a running state, and 50 of 63 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.54
Argusic Runner1/3Runs with mocks92.000.39

Topics (from GitHub)

agent-frameworkagenticaiai-agentai-agent-frameworkblockchainintentspythonweb3

Embed the badge

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

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

Questions

Does intentkit run?
Yes. intentkit runs. Argusic installed and launched it on a clean machine in 35 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test intentkit?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit afc8cc442552. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test intentkit?
The run that produced this verdict cost $0.54: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does intentkit take to install?
35 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 intentkit need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing intentkit?
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 intentkit compare with the alternatives?
Of the 63 agent-framework projects Argusic has installed and timed, intentkit was the 61st fastest to reach a running state, and 50 of 63 reached one at all.
Where is the evidence for intentkit?
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.

Discussion