openreader

An open-source read-along document reader server with high-quality TTS options, synchronized highlighting, and audiobook export for EPUB, PDF, DOCX, TXT, and MD.

Runs with mockssource: GitHubhomepageTypeScriptMITcommit 8af08e4622db

TypeScript, MIT licensed. The project labels itself: document, epub, epub reader, gpt 4o mini tts, kitten tts, kokoro tts, markdown reader and open ai.

openreader runs, with stand-ins for the services it depends on. An Argusic agent installed it in 20 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Node.js v22.12.0 with pnpm 10.33.4 installed, all 810 unit tests pass (0 failed), TypeScript type checking clean for both main app and compute-worker, production build compiles successfully, linting and boundary checks pass, and the development server starts and serves all pages (root, signin, signup) with HTTP 200.

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 56 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
56 / 100
cost of the verifying run
$0.04 (measured)
recorded runs
2
last tested
stars
594
forks
80
open issues
4
watchers
9
size
11 MB
created
last push

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.

Time lost to each failure while testing openreader, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Node.js v18 too old; vitest v4 requires node:util export styleText (Node 22+)3 minutes
  • pnpm not found in PATH1 minute
  • better-sqlite3 native module compiled for NODE_MODULE_VERSION 108 but Node v22 needs 1271 minute
  • 14 tests failed: admin_providers and admin_settings tables missing1 minute
  • Production build failed: AUTH_SECRET not set1 minute
  • App startup failed: S3_INTERNAL_ENDPOINT required1 minute
Install time
20 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
pnpm test exited 0, 810 passed; pnpm build succeeded; curl http://localhost:3003/ returned 200; curl http://localhost:3003/signin returned 200
Model tokens used
54,884
Exact commit tested
8af08e4622db
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

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

**What I fixed**:
1. **Missing pnpm** — installed `[email protected]` to `~/.local/bin`
2. **Node.js too old (v18)** for vitest v4 — installed `Node.js v22.12.0` via `n`
3. **`better-sqlite3` native module mismatch** after switching Node versions — rebuilt with `npm re…
4. **Missing SQLite tables** causing 14 test failures — ran `pnpm migrate` to create `admin_setting…
5. **App startup** needed `S3_INTERNAL_ENDPOINT` — provided dummy S3 env vars
**Verified working**:
- `pnpm test` — **810 passed, 0 failed, 7 skipped** across 164 test files
- `pnpm exec tsc --noEmit` — clean (both main and compute-worker)
- `pnpm build` — production build succeeds
- `pnpm check:compute-boundary` / `pnpm lint:route-errors` — both pass
- Dev server starts on `:3003` and serves `/` (200), `/signin` (200), `/signup` (200) with valid HT…

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 20 minutes.
  • Recovered from all 6 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.

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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.04
Argusic Runner1/3Did not run20.000.06

Topics (from GitHub)

documentepubepub-readergpt-4o-mini-ttskitten-ttskokoro-ttsmarkdown-readeropen-aiopen-ai-ttsopenai-apiorpheus-ttspdfpdf-readerreplicate-aireplicate-apisupertonictext-to-speechttstts-mcptxt-files

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/openreader.svg)](https://argusic.com/subject/openreader)

Questions

Does openreader run?
openreader runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 20 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test openreader?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8af08e4622db. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test openreader?
The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does openreader take to install?
20 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 openreader need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing openreader?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for openreader?
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.

Discussion