xiryn
Xiryn, the open-source personal agent. Does everything Muse, Grok Bot and Dots do, on your own computer: each agent gets its own Linux desktop in Docker, any model with your keys, an encrypted vault, and control from Telegram.
Runs with mockssource: GitHubhomepageTypeScriptMITcommit 0a55cd9ecdc9
TypeScript, MIT licensed. The project labels itself: ai agents, ai sdk, anthropic, byok, computer use, docker, firecrawl and llm.
xiryn runs, with stand-ins for the services it depends on. An Argusic agent installed it in 4 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Xiryn v0.5.1 on Next.js 16.4.3 with Node.js 22.13.0: npm install, build, typecheck, lint, and format all pass; the web app starts and serves all routes (200) with a correctly initialized SQLite database (12 tables) and a mock API key in .env; Docker is unavailable in this container so agent workstation features could not be tested.
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 86 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.
- Next.js 16.4.0 had a known security vulnerability that blocked the build2 minutes
- Node.js v18.19.1 was too old (needs >=20.9)1 minute
- Install time
- 4 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- curl -s -o /dev/null -w '%{http_code}' returned 200 on /, /settings, /usage, /templates, /routines; npm run build, typecheck, lint, and format:check all passed; better-sqlite3 confirmed all 12 tables created in data/xiryn.db
- Model tokens used
- 164,608
- Exact commit tested
- 0a55cd9ecdc9
- 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
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 2, 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.
Start epoch: 1792913076 Now: 1792913271 exec /bin/sh -lc 'echo "start: 1792913076 now: $(date +%s) diff: $(( $(date +%s) - 1792913076 )) seconds… succeeded in 0ms: start: 1792913076 now: 1792913275 diff: 199 seconds = 3 minutes Here's the complete summary: All checks passed — Node.js upgraded to v22, Next.js patched to 16.4.3 (security advisory), build s… tokens used 164,608 Here's the complete summary: All checks passed — Node.js upgraded to v22, Next.js patched to 16.4.3 (security advisory), build s…
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
- Installed in 4 minutes, faster than the median of the 98 comparable projects Argusic has measured.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
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.
Of the 99 ai-agents projects Argusic has installed and timed, xiryn was the 34th fastest to reach a running state, and 74 of 99 reached one at all.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.02 | |
| Argusic Runner | 1/3 | Unverified | 80.00 | 0.03 |
Topics (from GitHub)
ai-agentsai-sdkanthropicbyokcomputer-usedockerfirecrawlllmlocal-firstmulti-agentnextjsollamaopen-sourceopenaipersonal-agentprivacyself-hostedsqlitetelegram-bottypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/xiryn)Questions
- Does xiryn run?
- xiryn runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 4 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test xiryn?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0a55cd9ecdc9. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test xiryn?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does xiryn 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 xiryn need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing xiryn?
- 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 xiryn compare with the alternatives?
- Of the 99 ai-agents projects Argusic has installed and timed, xiryn was the 34th fastest to reach a running state, and 74 of 99 reached one at all.
- Where is the evidence for xiryn?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.