character-arc

CharacterArc(弧光) AI 小说创作应用,集项目设定、角色关系、剧情大纲、章节写作与多模型 AI 协作于一体

Runssource: GitHubTypeScriptMITcommit 36b7be9d61a9

TypeScript, MIT licensed. The project labels itself: agent, ai, ai tools, cross platform, fiction writing, human ai collaboration, novel and novel writing.

character-arc runs. An Argusic agent installed it in 10 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

CharacterArc installs, builds with pnpm run build, passes all 187 tests via the Electron test runner with the added loader, and its desktop app launches on the virtual display, initializing a 37-table SQLite workspace database.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.11 (measured)
recorded runs
1
last tested
stars
606
forks
87
open issues
4
watchers
0
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 character-arc, 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.

  • 4 of 43 test files failed with ERR_MODULE_NOT_FOUND: extensionless relative imports (e.g. '../codex-cli', './proxy-fetch') and the '@shared/*' alias are unresolved by Node's ESM loader when tests import .ts sources directly4 minutes
  • pnpm run build failed with 'crypto.hash is not a function' in @vitejs/plugin-vue because system Node is 18.19.1 (Vite 7 requires Node >=20.19)2 minutes
  • pnpm not installed on system; installed pnpm 10.33.2 to ~/.npm-global via npm install -g1 minute
  • Electron 37 SUID chrome-sandbox not configured (no root): 'The SUID sandbox helper binary was found, but is not configured correctly'1 minute
  • npm script 'test' uses Windows-only 'set ELECTRON_RUN_AS_NODE=1&&' syntax, unusable on Linux/macOS shell1 minute
Install time
10 minutes
Cold machine to finish
10 minutes
Errors hit and fixed
5 hit, 5 fixed with no human help
How the result was proved
ELECTRON_RUN_AS_NODE=1 electron --experimental-transform-types --loader scripts/node-esm-loader.mjs --test <43 files> exited 0 (176 pass, 0 fail); added 7/7 skill-policy and 4/4 conversation-scroll; pnpm run build exited 0 (typecheck + main/preload/renderer bundles); launcher kept alive with window 'CharacterArc' 1152x720 on Xvfb and populated 37 SQLite tables
Model tokens used
471,235
Exact commit tested
36b7be9d61a9
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.

- Test suite: 43 test files, 176/176 pass (via Electron `--test` + loader + `--experimental-transfo…
- Verified the app as a desktop app: production launch created a real `CharacterArc` window (1152x7…
- `pnpm run build` needed Node ≥20.19 (crypto.hash) — installed Node 22.21.1 locally; build exited …
- `pnpm run dev` also worked: Vite at `127.0.0.1:5173`, Electron ran until timeout.
- Repo gap: the `test` script hardcodes Windows `set ...&&` syntax and raw ESM needs the loader; th…
exec
/bin/sh -lc 'date -u +%H:%M; echo "minutes estimate: start 16:16, now check"' in /work/repo
 succeeded in 0ms:
16:26
minutes estimate: start 16:16, now check
tokens used
471,235

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 5 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 10 minutes to install, slower than the median of the 140 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 141 agent projects Argusic has installed and timed, character-arc was the 92nd fastest to reach a running state, and 94 of 141 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.
  • A quick evaluation: it was running 10 minutes after the clone.

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 Runner1/3Runs100.000.11

Topics (from GitHub)

agentaiai-toolscross-platformfiction-writinghuman-ai-collaborationnovelnovel-writingstory-writingvibe-writingwriting-tool

Embed the badge

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

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

Questions

Does character-arc run?
Yes. character-arc runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test character-arc?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 36b7be9d61a9. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test character-arc?
The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does character-arc take to install?
10 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 character-arc need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing character-arc?
5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does character-arc compare with the alternatives?
Of the 141 agent projects Argusic has installed and timed, character-arc was the 92nd fastest to reach a running state, and 94 of 141 reached one at all.
Where is the evidence for character-arc?
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.

Discussion