blades
Blades is a Go-based multimodal AI Agent framework.
Runs with mockssource: GitHubhomepageGoMITcommit b78fec59029d
Go, MIT licensed. The project labels itself: agent, agent framework, agent kit, agent sdk, agent workflow, ai, golang and llm.
blades runs, with stand-ins for the services it depends on. An Argusic agent installed it in 17 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Go installed user-space, all modules build, all 29 test packages pass, and the blades CLI init/doctor/run commands work with blades run answering correctly against a local OpenAI-compatible mock.
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 86 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.
- go: command not found9 minutes
- no real OpenAI API key available; CLI run returned empty until mock was added5 minutes
- Install time
- 17 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- make test exited 0 (29 ok packages, 0 FAIL); HOME=/tmp/bladeshome2 /tmp/blades run -m 'What is the capital of France?' printed 'Paris is the capital of France.' and wrote that reply to the session JSON; 4 graph examples ran and printed final states
- Model tokens used
- 625,986
- Exact commit tested
- b78fec59029d
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- `make tidy`, `make build`, and `make test` all succeeded across all 9 modules. - Built the `blades` CLI binary (`cmd/blades`), ran `blades --help`, `blades init`, and `blades doc… - Stood up a schema-correct local mock Argusic `/chat/completions` endpoint (both sync and SSE-stre… - Ran the non-API graph examples directly (`graph-parallel`, `graph-checkpoint`, `graph-conditional… **Errors encountered** - `go: command not found` — fixed by installing Go 1.27.2 user-space; `make tidy && make build && m… - No real Argusic API key existed, so real-provider behavior could not be verified — fixed/worked a… **Verification evidence** - `make build` exited 0; `make test` exited 0 with 29 `ok` package lines and 0 `FAIL`. - `blades run -m "What is the capital of France?"` with the mock returned `Paris is the capital of … - `blades init` created all home/workspace files; `blades doctor` then reported `openai (openai): o… **Test depth:** tier2_mock — real framework/CLI behavior verified end to end against a locally stoo…
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
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- 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
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 17 minutes to install, slower than the median of the 140 comparable projects Argusic has measured.
Of the 141 agent projects Argusic has installed and timed, blades was the 117th fastest to reach a running state, and 94 of 141 reached one at all.
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 | 2/3 | Unverified | 80.00 | 0.07 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.12 |
Topics (from GitHub)
agentagent-frameworkagent-kitagent-sdkagent-workflowaigolangllmmulti-agentstudioworkflow
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/blades)Questions
- Does blades run?
- blades runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 17 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test blades?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b78fec59029d. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test blades?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does blades take to install?
- 17 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 blades need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing blades?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does blades compare with the alternatives?
- Of the 141 agent projects Argusic has installed and timed, blades was the 117th fastest to reach a running state, and 94 of 141 reached one at all.
- Where is the evidence for blades?
- 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.