Switchyard
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.
Runs with mockssource: GitHubRustApache-2.0commit 6f4e7749083a
Rust, Apache-2.0 licensed.
Switchyard runs, with stand-ins for the services it depends on. An Argusic agent installed it in 8 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
switchyard-server builds from source, starts on port 4124, routes requests through the stage_router (auto) algorithm to a mock upstream, and returns correct completions; all Rust unit/integration tests and Python pytest test suite pass
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 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
- Missing libpython3.12-dev system package prevents prefill-router tests from linking (rust-lld: unable to find library -lpython3.12) and prevents cargo test for switchyard-py and switchyard-node
- Install time
- 8 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- curl -s http://localhost:4124/v1/chat/completions with mock upstream returned HTTP 200 and correct routed response body
- Model tokens used
- 203,155
- Exact commit tested
- 6f4e7749083a
- 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.
Selected model IDs: ['auto']
Algorithm: noop
Outcome ID: 01a14de6-ad94-7333-bc74-61c9bf3bccf1
Response: {'id': 'switchyard-noop', 'model': 'auto', 'outputs': [{'role': 'assistant', 'content': […
Python bindings OK
Here's the final verified state of the repository:
All tests pass, the server launches and routes end-to-end. I will now stop the remaining background…
exec
/bin/sh -lc 'pkill -f mock_upstream.py 2>/dev/null; pkill switchyard-server 2>/dev/null; echo "clea…
exited 143 in 0ms:
tokens used
203,155Replay 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
- Installed in 8 minutes, faster than the median of the 11 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 12 Rust projects Argusic has installed and timed, Switchyard was the 4th fastest to reach a running state, and 10 of 12 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.03 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/switchyard)Questions
- Does Switchyard run?
- Switchyard runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 8 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test Switchyard?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6f4e7749083a. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Switchyard?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Switchyard take to install?
- 8 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 Switchyard need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Switchyard?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Switchyard compare with the alternatives?
- Of the 12 Rust projects Argusic has installed and timed, Switchyard was the 4th fastest to reach a running state, and 10 of 12 reached one at all.
- Where is the evidence for Switchyard?
- 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.