Yes. busbar runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 0 errors on the way, and recorded the session.

How did Argusic test busbar?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit b1f3db499a4a. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test busbar?

The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does busbar take to install?

7.5 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 busbar need a GPU?

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

What goes wrong when installing busbar?

Nothing did, in the recorded run: zero errors between clone and running.

Where is the evidence for busbar?

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.

busbar

Mirror of https://git.getbusbar.dev/GetBusbar/busbar. Read-only; contribute on Forgejo. The execution control plane for AI agents. Govern every model request, MCP tool call, A2A delegation, and downstream action, while keeping your native protocols intact: six native LLM protocols in, six native LLM protocols out.

Runssource: GitHub homepageRustApache-2.0commit b1f3db499a4a

Rust, Apache-2.0 licensed. The project labels itself: ai gateway, anthropic, bedrock, circuit breaker, claude, failover, gemini and litellm alternative.

busbar runs. An Argusic agent installed it in 7.5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

Busbar 1.5.5 builds, passes its full test suite (3085 unit tests), validates a minimal config, and serves /healthz (200), /stats (valid JSON), /v1/models (model list), admin /auth, and admin /models endpoints on both the data (:8090) and admin (:8091) listeners.
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

verdict: Runs
Argusic Score: 100 / 100
cost of the verifying run: $0.06 (measured)
recorded runs: 1
last tested: 2026-10-30
stars: 215
forks: 22
open issues: 0
watchers: 2
size: 167 MB
created: 2026-05-29
last push: 2026-10-29

Subject data from GitHub, linked at the top of this page, refreshed 2026-10-30. 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.

Install time: 8 minutes
Cold machine to finish: 14 minutes
Errors hit and fixed: 0 hit, 0 fixed with no human help
How the result was proved: cargo test: 3085 passed, 0 failed, 4 ignored; busbar --validate returned 'ok: config valid'; busbar --version returned 'busbar 1.5.5'; curl http://127.0.0.1:8090/healthz returned 200; curl http://127.0.0.1:8090/stats returned valid JSON; curl http://127.0.0.1:8091/healthz returned 200; admin auth and models endpoints responded correctly
Model tokens used: 169,711
Exact commit tested: b1f3db499a4a
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.

echo \"Data plane /healthz: "'$(. "$HOME/.cargo/env" && cd /work/repo && export DUMMY_OPENAI_KEY=x …
echo \"Config --validate: "'$(. "$HOME/.cargo/env" && cd /work/repo && DUMMY_OPENAI_KEY=sk-fake BUS…
exec
/bin/sh -lc 'pkill -9 -f "target/debug/busbar" 2>/dev/null; echo "clean"' in /work/repo
 exited 137 in 0ms:
 exited 137 in 12507ms:
=== Final summary ===
Build: busbar 1.5.5
Everything works. Let me compile the final ARGUSIC_RESULT.
tokens used
169,711
Everything works. Let me compile the final ARGUSIC_RESULT.

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 7.5 minutes, faster than the median of the 21 comparable projects Argusic has measured.
Nothing broke on the way: zero errors between clone and running.
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

Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 22 ai-gateway projects Argusic has installed and timed, busbar was the 8th fastest to reach a running state, and 16 of 22 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 7.5 minutes after the clone.
Following its own README: the documented path worked with nothing to fix.

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	100.00	0.06	2026-10-30 06:58 UTC

Topics (from GitHub)

ai-gateway anthropic bedrock circuit-breaker claude failover gemini litellm-alternative llm llm-gateway llm-proxy llmops load-balancer openai openrouter-alternative reverse-proxy rust sigv4 streaming

Embed the badge

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

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

Questions

Does busbar run?: Yes. busbar runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test busbar?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit b1f3db499a4a. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test busbar?: The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does busbar take to install?: 7.5 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 busbar need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing busbar?: Nothing did, in the recorded run: zero errors between clone and running.
How does busbar compare with the alternatives?: Of the 22 ai-gateway projects Argusic has installed and timed, busbar was the 8th fastest to reach a running state, and 16 of 22 reached one at all.
Where is the evidence for busbar?: 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.