selfhost-ai
š Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier/Make alternative.
Could not verifysource: GitHubhomepageShellApache-2.0commit d608f52fc907
Shell, Apache-2.0 licensed. The project labels itself: ai, ai agents, automation, chatgpt alternative, dify, docker, flowise and homelab.
Argusic could not get selfhost-ai running. An Argusic agent installed it in 11 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The repository is structurally valid (Docker Compose YAML, shell scripts, JSON configs, Python files) but cannot install or launch because Docker is absent and cannot be installed without root privileges in this container.
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 15 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.
- Docker and Docker Compose not installed; no root access to install them; user namespaces disabled preventing rootless Docker11 minutes
- newuidmap binary from Ubuntu noble (libc 2.39) required an older version of the uidmap package than the one initially downloaded (which needed GLIBC 2.43)2 minutes
- apt-get not usable (no passwordless sudo); cannot install dependencies like uidmap, iptables
- Install time
- 11 minutes
- Cold machine to finish
- 13 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- docker-compose -f docker-compose.yml --profile n8n --profile monitoring config exited 0; bash -n passed on all 25 scripts; json.load/yaml.safe_load passed on all config files; start_services.py and python-runner/main.py compiled without errors; .env generated with all required keys populated
- Model tokens used
- 115,861
- Exact commit tested
- d608f52fc907
- 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
- Whether it works at all
- this run verified nothing, so this page makes no claim either way
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
ā n8n/Dockerfile.n8n: 11 lines, valid ā n8n/Dockerfile.runner: 15 lines, valid ā Caddyfile: 342 lines, 35 imports, 77 service blocks ā Prometheus: 3 scrape configs ā n8n-task-runners.json: 1 entries ======================================== Overall: ALL VALID ======================================== Now I have a complete picture. Let me produce the final structured report. tokens used 115,861 Now I have a complete picture. Let me produce the final structured 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
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- An agent with no time limit did not get it running.
- Took 11 minutes to install, slower than the median of the 36 comparable projects Argusic has measured.
Of the 37 ai projects Argusic has installed and timed, selfhost-ai was the 30th fastest to reach a running state, and 30 of 37 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 | Did not run | 20.00 | 0.08 | |
| Argusic Runner | 1/3 | Did not run | 10.00 | 0.17 |
Topics (from GitHub)
aiai-agentsautomationchatgpt-alternativedifydockerflowisehomelabllmlocal-llmmake-alternativen8nno-codeollamaopen-webuiqdrantragself-hostedvector-databasezapier-alternative
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/selfhost-ai)Questions
- Does selfhost-ai run?
- Argusic could not verify that selfhost-ai runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test selfhost-ai?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d608f52fc907. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test selfhost-ai?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does selfhost-ai take to install?
- 11 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 selfhost-ai need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing selfhost-ai?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does selfhost-ai compare with the alternatives?
- Of the 37 ai projects Argusic has installed and timed, selfhost-ai was the 30th fastest to reach a running state, and 30 of 37 reached one at all.
- Where is the evidence for selfhost-ai?
- 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.