feedlog
Open-source AI customer support for SaaS teams, AI agent, help center, shared inbox, and feedback-to-changelog loop in one self-hostable platform.
Runssource: GitHubTypeScriptMITcommit 7d760523d3be
TypeScript, MIT licensed. The project labels itself: ai agent, ai customer support, canny alternative, changelog, customer support, featurebase alternative, help center and helpdesk.
feedlog runs. An Argusic agent installed it in 13 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.
Dependencies installed (pnpm 10.15.0, Node 22.23.4), project builds, full DB schema migrated on PostgreSQL 16 with pgvector, and dev server runs on port 3000 returning 200 on /health and /. 226 of 233 runnable tests pass; 5 pre-existing failures remain. 4 files could not execute due to Nuxt alias extraction limits.
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 95 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.
- No PostgreSQL 17+ available; root not available for apt5 minutes
- Node.js v18 too old for Nuxt 4 (needs 22+)2 minutes
- pnpm not installed1 minute
- 5 pre-existing test failures: agent-v1 AI visibility test (Organization not found fixture issue), 4 inbox-scheduler help-indexing timing tests (race conditions in scheduler)
- Install time
- 13 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 4 hit, 3 fixed with no human help
- How the result was proved
- pnpm build exited 0 -> .output/server/index.mjs (115 MB); pnpm dev on localhost:3000 returned HTTP 200 on /health and / (full SSR HTML); node --test runner: 226 pass, 5 fail, 2 skip across 45 of 49 test files (4 skipped: 2 need Nuxt #layers alias, 2 need dev-server DB==test DB)
- Model tokens used
- 148,173
- Exact commit tested
- 7d760523d3be
- 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.
/bin/sh -lc "echo 'ARGUSIC_RESULT: {\"install_succeeded\":true,\"launch_succeeded\":true,\"install_…
succeeded in 0ms:
The result has been printed as required. Here's a concise summary of what was accomplished:
**Setup:** Fixed three infrastructure gaps (Node 18→22, missing pnpm, no PostgreSQL) by downloading…
**Build & Launch:** `pnpm install` → `pnpm build` → `pnpm migrate` all succeeded. Dev server runs o…
**Tests:** 226 pass, 5 fail, 2 skip across 45 of 49 test files. Four files couldn't run due to Nuxt…
tokens used
148,173
The result has been printed as required. Here's a concise summary of what was accomplished:
**Setup:** Fixed three infrastructure gaps (Node 18→22, missing pnpm, no PostgreSQL) by downloading…
**Build & Launch:** `pnpm install` → `pnpm build` → `pnpm migrate` all succeeded. Dev server runs o…
**Tests:** 226 pass, 5 fail, 2 skip across 45 of 49 test files. Four files couldn't run due to Nuxt…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.
- 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 13 minutes to install, slower than the median of the 74 comparable projects Argusic has measured.
- Hit 4 errors during setup, 1 of which were not solved.
- 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, feedlog was the 52nd 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-customer-supportcanny-alternativechangelogcustomer-supportfeaturebase-alternativehelp-centerhelpdeskintercom-alternativeknowledge-baseproduct-feedbackroadmapself-hosted
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/feedlog)Questions
- Does feedlog run?
- Yes. feedlog runs. Argusic installed and launched it on a clean machine in 13 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test feedlog?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7d760523d3be. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test feedlog?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does feedlog take to install?
- 13 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 feedlog need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing feedlog?
- 4 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 feedlog compare with the alternatives?
- Of the 75 ai-agent projects Argusic has installed and timed, feedlog was the 52nd fastest to reach a running state, and 48 of 75 reached one at all.
- Where is the evidence for feedlog?
- 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.