EcomGen
Local-first AI e-commerce image suite generator for individual sellers. Pi Agent storyboards, 25 templates + reusable suites, product-truth pixel protection, OpenAI-compatible & Gemini image providers, AI layering (PNG/PSD), review, edit, and ZIP export. Self-hosted.
Runssource: GitHubTypeScriptMITcommit 894e7fb62d50
TypeScript, MIT licensed. The project labels itself: ai agent, ai image generation, bullmq, ecommerce, fastify, gemini, image editing and local first.
EcomGen runs. An Argusic agent installed it in 14.1 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 11 workspace packages build successfully. Redis 7.4.2 compiled and serves on 127.0.0.1:6379. The API starts and responds 200 on /health. All 615 tests pass (79 test files), and the e2e mock chain (plan-confirm-generate-export-custom template-suite forge-model cast-pattern operations-cancel) passes end-to-end.
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.
- Redis not installed on system (no apt/sudo access)2.5 minutes
- System Node.js v18 - pnpm@11 requires Node 22.13+2 minutes
- sharp native module not loaded - install script skipped because sharp (and its @img/* optional deps) not in pnpm-workspace.yaml allowBuilds list1 minute
- Build failed on packages/ecom-suite-forge - Node 18 doesn't support import.meta.dirname0.5 minutes
- Install time
- 14 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pnpm build (11 workspace packages) completed; all 615 tests passed across 9 packages (contracts 20, core 63, ecom-suite 6, ecom-skill 48, providers 63, agent 61, api 91, worker 85, web 178); pnpm test:e2e:mock passed full mock chain; API server health endpoint at /health returned HTTP 200 with {"status":"ok","webResearchAvailable":false}
- Model tokens used
- 305,340
- Exact commit tested
- 894e7fb62d50
- 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
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 1, 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.
1794046988 exec /bin/sh -lc '# First command was around timestamp 1794046140 (10:09:00 UTC) echo "First command: 1794046140" echo "Current: 1794046988" echo "Elapsed: $((1794046988 - 1794046140)) seconds = $(( (1794046988 - 1794046140) / 60 )) min $((… succeeded in 0ms: First command: 1794046140 Current: 1794046988 Elapsed: 848 seconds = 14 min 8 sec tokens used 305,340
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 4 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 14.1 minutes to install, slower than the median of the 74 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 75 ai-agent projects Argusic has installed and timed, EcomGen was the 58th fastest to reach a running state, and 48 of 75 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-agentai-image-generationbullmqecommercefastifygeminiimage-editinglocal-firstnano-bananaopenai-compatiblepi-agentproduct-imagesproduct-photographyreactredisself-hostedseller-toolssqlitetypescriptvite
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ecomgen)Questions
- Does EcomGen run?
- Yes. EcomGen runs. Argusic installed and launched it on a clean machine in 14 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test EcomGen?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 894e7fb62d50. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test EcomGen?
- The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does EcomGen take to install?
- 14.1 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 EcomGen need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing EcomGen?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does EcomGen compare with the alternatives?
- Of the 75 ai-agent projects Argusic has installed and timed, EcomGen was the 58th fastest to reach a running state, and 48 of 75 reached one at all.
- Where is the evidence for EcomGen?
- 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.