RabiRoute
Self-hosted message gateway for AI agents: Codex, QQ, WeChat/WeCom, Feishu, smart devices and desktop automation. | AI 消息网关：连接聊天、智能设备与 Agent，支持定时任务和角色上下文。
Runssource: GitHubTypeScriptMITcommit 366c9f5fed32
TypeScript, MIT licensed. The project labels itself: agent orchestration, ai agents, chatbot, chatops, codex, deepseek harness, desktop automation and feishu.
RabiRoute runs. An Argusic agent installed it in 4 minutes and hit 10 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
A clean-state Linux Host stayed healthy with Manager HTTP 200, businessReady=true, two seeded roles, one ready route, 29 catalog plugins, 33/33 advertised assets returning 200, and a successfully opened NapCat WebSocket, while optional speech capture and NapCat HTTP profile access remained unavailable.
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. 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.
- Windows workspace path comparisons failed on Linux test hosts12 minutes
- Clean-state startup did not seed example data and /api/roles returned HTTP 5008 minutes
- Async timers were unreferenced and allowed awaited preparation or shutdown work to be abandoned6 minutes
- Application shutdown converted a retirement timeout into an unconfirmed AggregateError4 minutes
- System Node v18.19.1 did not satisfy the required >=22.13.03 minutes
- Invalid .gitkeep inside the canonical plan archive directory failed plan-storage validation2 minutes
- Install time
- 4 minutes
- Cold machine to finish
- 45 minutes
- Errors hit and fixed
- 10 hit, 10 fixed with no human help
- How the result was proved
- npm test exited 0: source 5282 tests with 5254 passed, 0 failed, 28 skipped; scripts 236 tests with 129 passed, 0 failed, 73 skipped, 34 todo; check:skills 25 tests with 24 passed, 0 failed, 1 skipped. npm run build exited 0. node scripts/linux-host.mjs --command status --json returned ok:true and state:healthy; curl /health returned 200 with live:true, requiredReady:true, businessReady:true and backgroundIncidentCount:0; /, /meta, /api/roles, /api/gateways, /api/plugins/catalog and /api/roles/Rabi/plans each returned 200; /api/roles returned Rabi and RabiActive; 33/33 advertised assets returned 200; ws://127.0.0.1:8789 opened successfully.
- Model tokens used
- 2,311,509
- Exact commit tested
- 366c9f5fed32
- 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.
M src/plugin-kernel/generationRuntime.ts
M src/routing/remotePersonaClient.ts
M src/shared/codexWorkspaceIdentity.ts
M src/shared/projectPaths.test.ts
BUILD_JS=present
BUILD_HTML=
succeeded in 5967ms:
{"advertised":33,"ok":33,"bad":[]}
napcat_ws=open
2026-11-03T09:29:28.873842Z ERROR codex_core::session: failed to record rollout items: thread 01a1a…
tokens used
2,311,509Replay 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 4 minutes, faster than the median of the 17 comparable projects Argusic has measured.
- Recovered from all 10 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 18 agent-orchestration projects Argusic has installed and timed, RabiRoute was the 6th fastest to reach a running state, and 13 of 18 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 4 minutes after the clone.
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)
agent-orchestrationai-agentschatbotchatopscodexdeepseek-harnessdesktop-automationfeishuhome-assistantmessage-routingnapcatonebotqq-botself-hostedtypescriptwechatwecomworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/rabiroute)Questions
- Does RabiRoute run?
- Yes. RabiRoute runs. Argusic installed and launched it on a clean machine in 4 minutes, hitting 10 errors on the way, and recorded the session.
- How did Argusic test RabiRoute?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 366c9f5fed32. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test RabiRoute?
- The run that produced this verdict cost $1.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does RabiRoute take to install?
- 4 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 RabiRoute need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing RabiRoute?
- 10 things broke in the recorded run, and 10 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does RabiRoute compare with the alternatives?
- Of the 18 agent-orchestration projects Argusic has installed and timed, RabiRoute was the 6th fastest to reach a running state, and 13 of 18 reached one at all.
- Where is the evidence for RabiRoute?
- 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.