coai
🚀 Next Gen Multi-tenant AI One-Stop Solution. Builtin Admin & Billing System. Enterprise-Grade Unified LLM Gateway Support for 200+ Models And 35+ Providers, Load Balacing w/ Priority-base Routing, Cost Management, Chat Share, Cloud Sync, Credit/Subscription Billing, All File Parsing, Web Search, Built-in Model Cache.
Runssource: GitHubhomepageTypeScriptApache-2.0commit 3048a493eedc
TypeScript, Apache-2.0 licensed. The project labels itself: ai gateway, api, chat, chatgpt, cross platform, gemini, golang and llm gateway.
coai runs. An Argusic agent installed it in 17 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
CoAI.Dev builds and runs on port 8094 using SQLite (no MySQL) and a fake Redis mock, with login, user info, admin analytics, quota, subscription, channel management, and model listing endpoints all responding correctly.
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Redis not available (server requires Redis)5 minutes
- pnpm ignored build scripts for @swc/core and esbuild4 minutes
- Go not installed in container2 minutes
- pnpm not installed1 minute
- SQLite migration error (duplicate column name)1 minute
- Install time
- 17 minutes
- Cold machine to finish
- 18 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- Server launched on port 8094; curl / returned 200 with frontend HTML; curl /api/login -X POST {root/chatnio123456} returned 200 with JWT token; curl /api/admin/analytics/info with Bearer token returned {billing_today:0,...}; curl /api/quota returned {quota:0,status:true}; curl /api/subscription returned subscription object; curl /api/admin/channel/list returned {data:null,status:true}
- Model tokens used
- 674,473
- Exact commit tested
- 3048a493eedc
- 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.
3. **Server runs** on port 8094 with SQLite (no MySQL) + fake Redis (no real Redis) 4. **Fixes applied**: - Fixed `validSqlError` in `db_migration.go` to handle SQLite's "duplicate column name" error fo… - Created a fake Redis server in Python to mock Redis dependencies - Fixed `pnpm-workspace.yaml` to allow build scripts for `@swc/core` and `esbuild` 5. **Verified endpoints work**: static page (200), API root, login (JWT token), user info, admin an… Let me clean up the processes and provide the ARGUSIC_RESULT. exec /bin/sh -lc 'pkill -f chatnio 2>/dev/null; pkill -f fakeredis 2>/dev/null; sleep 1; echo "cleaned"'… exited 143 in 0ms: tokens used 674,473
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 5 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 Apache-2.0, as reported by its host.
What did not, or is not known
- Took 17 minutes to install, slower than the median of the 3 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 4 ai-gateway projects Argusic has installed and timed, coai was the 3rd fastest to reach a running state, and 3 of 4 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
Topics (from GitHub)
ai-gatewayapichatchatgptcross-platformgeminigolangllm-gatewayopenaiproxyreact
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/coai)Questions
- Does coai run?
- Yes. coai runs. Argusic installed and launched it on a clean machine in 17 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test coai?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3048a493eedc. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test coai?
- The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does coai 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 coai need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing coai?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does coai compare with the alternatives?
- Of the 4 ai-gateway projects Argusic has installed and timed, coai was the 3rd fastest to reach a running state, and 3 of 4 reached one at all.
- Where is the evidence for coai?
- 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.