antirion
⚡ The fastest open-source AI gateway, one Rust binary with a built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more.
Runssource: GitHubhomepageRustApache-2.0commit 08ad3b6a6199
Rust, Apache-2.0 licensed. The project labels itself: a2a, ai gateway, anthropic, api gateway, bifrost alternative, guardrails, litellm alternative and llm.
antirion runs. An Argusic agent installed it in 2.6 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The Antirion AI gateway builds from source, its test suite passes 1044/1044 tests, the binary starts in standalone mode with the embedded store, and successfully routes a chat completion request through a provider, deployment, model, and key to a mock upstream and back with HTTP 200.
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.
- Install time
- 3 minutes
- Cold machine to finish
- 16 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- cargo test --workspace --no-ail-fast reported 1044 passed, 0 failed; the binary starts on ports 18080/18081 and answers GET /admin/v1/health with HTTP 200; POST /v1/chat/completions through the pipeline returns HTTP 200 with a valid chat completion response from mock upstream
- Model tokens used
- 563,284
- Exact commit tested
- 08ad3b6a6199
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
print(f'Total passing tests: {sum(tests)}')
print(f'Number of test modules: {len(tests)}')
\"" in /work/repo
succeeded in 0ms:
Total passing tests: 1044
Number of test modules: 45
All systems verified. Here is the final report:
2026-10-26T19:37:01.907547Z ERROR codex_core::session: failed to record rollout items: thread 01a17…
2026-10-26T19:37:01.907615Z ERROR codex_core::session: failed to record rollout items: thread 01a17…
tokens used
563,284
All systems verified. Here is the final report: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 2.6 minutes, faster than the median of the 7 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 8 a2a projects Argusic has installed and timed, antirion was the 3rd fastest to reach a running state, and 8 of 8 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 2.6 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
Topics (from GitHub)
a2aai-gatewayanthropicapi-gatewaybifrost-alternativeguardrailslitellm-alternativellmllm-gatewayllm-proxymcpmcp-gatewayobservabilityopenaiopenai-proxyrate-limitingrustself-hosted
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/antirion)Questions
- Does antirion run?
- Yes. antirion runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test antirion?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 08ad3b6a6199. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test antirion?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does antirion take to install?
- 2.6 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 antirion need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing antirion?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does antirion compare with the alternatives?
- Of the 8 a2a projects Argusic has installed and timed, antirion was the 3rd fastest to reach a running state, and 8 of 8 reached one at all.
- Where is the evidence for antirion?
- 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.