CliRelay

Self-hosted AI gateway for coding CLIs, one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tenant web console, request logs, and spend quotas.

Runssource: GitHubGoMITcommit 51817dab7636

Go, MIT licensed. The project labels itself: ai gateway, anthropic, api gateway, claude code, gemini cli, go, llm and llm proxy.

CliRelay runs. An Argusic agent installed it in 28 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

With user-compiled PostgreSQL 16.8 and Redis 7.2.5 and remote-management.disable-control-panel set, the CliRelay server (built from this repo) runs on 127.0.0.1:8317 answering /healthz 204, /v1/models 200 and /v1beta/models 200, and the full test suite passes when run sequentially (go test -p 1 -count=1 ./... exit 0, 0 FAIL).

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
$0.26 (measured)
recorded runs
1
last tested
stars
1,052
forks
136
open issues
45
watchers
3
size
77 MB
created
last push

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.

Time lost to each failure while testing CliRelay, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Plain 'go test ./...' failed in internal/watcher with the same EMFILE because parallel packages collectively exceeded the 128 inotify-instance cap46 minutes
  • App startup intermittently died with 'failed to create watcher: too many open files' (EMFILE from inotify_init1) hitting fs.inotify.max_user_instances=128 while the management-panel auto-updater raced startup; ~2 of 4 launches failed23 minutes
Install time
28 minutes
Cold machine to finish
37 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
go test -p 1 -count=1 ./... exited 0 (104 ok packages, 100 no-test files, 0 FAIL); live server at 127.0.0.1:8317 answered /healthz=204, /v1/models=200, /v1beta/models=200 and stayed up across repeated liveness checks; /tmp/CLIProxyAPI -h printed 'CliRelay Version: dev' plus usage.
Model tokens used
184,631
Exact commit tested
51817dab7636
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.

- **Verified**: `go test -p 1 -count=1 ./...` exit 0 (104 ok packages, 0 FAIL); live curl healthz 2…
Timing: I'll estimate install ~42 min (Go toolchain + PG + Redis build), launch verification after.…
Note: the JSON is a single line in my message. The fix strings and minutes per error: EMFILE errors…
Now produce the final line.
exec
/bin/sh -lc 'date +%s' in /work/repo
 succeeded in 0ms:
1791697761
All verification complete. Here is the report.
tokens used
184,631
All verification complete. Here is the 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.
  • Recovered from all 2 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 MIT, as reported by its host.

What did not, or is not known

  • Took 28 minutes to install, slower than the median of the 22 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 23 ai-gateway projects Argusic has installed and timed, CliRelay was the 20th fastest to reach a running state, and 17 of 23 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.26

Topics (from GitHub)

ai-gatewayanthropicapi-gatewayclaude-codegemini-cligollmllm-proxymulti-tenantopenaiopenai-codexself-hosted

Embed the badge

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

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

Questions

Does CliRelay run?
Yes. CliRelay runs. Argusic installed and launched it on a clean machine in 28 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test CliRelay?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 51817dab7636. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test CliRelay?
The run that produced this verdict cost $0.26: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does CliRelay take to install?
28 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 CliRelay need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing CliRelay?
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 CliRelay compare with the alternatives?
Of the 23 ai-gateway projects Argusic has installed and timed, CliRelay was the 20th fastest to reach a running state, and 17 of 23 reached one at all.
Where is the evidence for CliRelay?
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.

Discussion