CodeSync Knack
The free, private judgment model behind CodeSync.
Every time you send CodeSync a message or it runs a shell command, it makes dozens of quick calls: Is this command risky? Will it run forever? Are you asking to continue earlier work? Is this a question or a task? Which mode fits? Knack makes those calls on your own machine, in about 10 milliseconds.
- Free. Ships with every CodeSync install. No API key, no account, no usage limits.
- Private. Runs locally. Your prompts and commands never leave your machine to be judged.
- Fast. About 10 ms per decision on a GPU, about 250 ms on a plain CPU.
- Small. About 1 GB on disk. Installs itself in the background after CodeSync starts.
- Accurate where it matters. Trained on real CodeSync sessions, with extra focus on the rare cases that cost the most when missed: destructive deletes, commands that never exit, resuming interrupted work, refactor / test / documentation requests.
Results
Measured on CodeSync's own judgments (version v3, November 2026):
| Benchmark | Knack v3 | What it measures |
|---|---|---|
| Hand-labelled set | 97.9% | 233 decisions labelled by hand |
| Held-out set | 95.5% | 3,267 decisions from real sessions, never trained on |
| Rare-case set | 93.7% | 4,120 decisions on the hardest, rarest cases |
| Latency | 13 ms | median per request on a laptop GPU |
How to get it
Install CodeSync. That's it.
curl -fsSL https://app.devshub.ai/install.sh | bash
The installer stays as fast as before. On first start, CodeSync downloads Knack in the background and keeps working while it does. Once Knack is ready it becomes CodeSync's first judgment engine, and new versions are picked up automatically.
To turn it off: CODESYNC_KNACK_DISABLED=1.
What it decides
Knack answers CodeSync's fixed set of 29 decisions:
- Every turn (21): task intent, routing and reasoning depth, plan / ask / build mode, new task vs continuing work, resume requests, screencast start and stop, browser and messaging needs, whether the request is chat or a task, and more.
- Every shell command (8): risk level, activity type, long-running or not, whether it verifies, mutates the repo, deploys, needs a running app, or starts a server.
It only answers the questions it was trained on. Anything else is passed to CodeSync's cloud judgment service, so a new kind of question never gets a guess.
Files
| File | Purpose |
|---|---|
manifest.json |
current version, archive URL, sha256 (read by CodeSync) |
knack-<version>.tar.gz |
the model folder |