genkit
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
Runssource: GitHubhomepageGoApache-2.0commit 6b34d5fe6910
Go, Apache-2.0 licensed. The project labels itself: agents, ai, embedders, genkit, llm, multimodal, rag and vector database.
genkit runs. An Argusic agent installed it in 25 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Genkit JS SDK core + genkit package, all 23 JS plugins, genkit-tools (cli, common, telemetry-server), and Python SDK install, build, and run test suites, with the genkit CLI printing version 1.44.1 and help text
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.
- pnpm node-linker default (isolated) didn't create .bin symlinks, causing 'npm-run-all: not found'5 minutes
- @types/request transitively referenced tough-cookie CookieJar type which was renamed in tough-cookie v6, causing tsc to fail on core build3 minutes
- core test: 1 pre-existing flaky failure in bidi-action_test.ts (unhandledRejection race)
- genkit test: 1 pre-existing failure in mockModel agent handoff test
- Install time
- 25 minutes
- Cold machine to finish
- 26 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pnpm test in js/core: 239 tests, 238 pass; pnpm test in genkit-tools/cli: 14 suites, 206 pass; pnpm test in genkit-tools/common: 13 suites, 231 pass; pnpm test in genkit-tools/telemetry-server: 67 pass; uv run pytest across py packages: 1,236+ pass; node genkit-tools/cli/dist/bin/genkit.js --version returned '1.44.1'
- Model tokens used
- 187,489
- Exact commit tested
- 6b34d5fe6910
- 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.
Started roughly at:
Tue Oct 20 07:27:44 UTC 2026
exec
/bin/sh -lc 'date +%s' in /work/repo
succeeded in 0ms:
1792482047
Now let me put together the final result:
This is one line of plain text. LetARGUSIC_RESULT: {"install_succeeded": true, "launch_succeeded": …
tokens used
187,489
Now let me put together the final result:
This is one line of plain text. LetARGUSIC_RESULT: {"install_succeeded": true, "launch_succeeded": …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 4 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
- Took 25 minutes to install, slower than the median of the 30 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 31 agents projects Argusic has installed and timed, genkit was the 28th fastest to reach a running state, and 20 of 31 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/genkit)Questions
- Does genkit run?
- Yes. genkit runs. Argusic installed and launched it on a clean machine in 25 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test genkit?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6b34d5fe6910. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test genkit?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does genkit take to install?
- 25 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 genkit need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing genkit?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does genkit compare with the alternatives?
- Of the 31 agents projects Argusic has installed and timed, genkit was the 28th fastest to reach a running state, and 20 of 31 reached one at all.
- Where is the evidence for genkit?
- 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.