hunk vs no-mistakes
Two of the top projects in Code review and testing, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
hunk
Terminal diff viewer for reviewing code changes, with inline agent notes
no-mistakes
Local git proxy that runs AI review, tests and lint before opening a PR
Verdict
hunk ranks higher, 71 to 70. Of the 5 score parts we measure for both, hunk leads on 2, no-mistakes on 1 and 2 are even.
- Adoptionhunk leads by 6 points, 55 to 49.
- FreshnessEven at 100.
- Maintenancehunk leads by 3 points, 87 to 84: close to even.
- Easy to runEven at 50.
- Agent-readyno-mistakes leads by 15 points, 85 to 70: a wide gap.
Pick hunk if you are
Developers who review diffs or agent-written changes in the terminal
- Opens Git, Jujutsu and Sapling changes, plus GitHub PRs via bundled `hunk gh` with no gh CLI
- Works as a pager for git, jj and Sapling, and reads patches from stdin
Pick no-mistakes if you are
Developers who want agent-checked branches before raising PRs
- Runs in an isolated worktree, so your working directory is not disturbed
- Works with claude, codex, grok, opencode, copilot, cursor and others, with ordered fallbacks
| What we compare | hunk | no-mistakes |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 55, popular | 49, known |
| Freshness | 100, active | 100, active |
| Maintenance | 87, healthy | 84, healthy |
| Easy to run | 50, easy | 50, easy |
| Agent-ready | 70, partly | 85, ready |
| Facts from GitHub and the README | ||
| Stars | 9.6k | 8.9k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Sep 2026 |
| Language | TypeScript | Go |
| Docker | No | No |
| GPU | Not needed | Not stated |
| arm64 or Apple Silicon | Mentioned | Mentioned |
hunk
Hunk is an interactive terminal diff viewer built on OpenTUI and Pierre diffs. It opens Git, Jujutsu and Sapling changes, GitHub pull requests, raw patches from stdin, or two files, in a multi-file stream with a sidebar. A coding agent can use the hunk-review skill to attach notes to a live session, and they show beside the code.
Who it is for: Developers who review diffs or agent-written changes in the terminal
Strengths
- Opens Git, Jujutsu and Sapling changes, plus GitHub PRs via bundled `hunk gh` with no gh CLI
- Works as a pager for git, jj and Sapling, and reads patches from stdin
- Standalone binary via install script, Homebrew, mise or Nix; no Node.js needed
- Extension API and embeddable OpenTUI diff component (`hunkdiff/opentui`)
Weaknesses
- No structural diffing; the README's own comparison table marks it as missing
- No prebuilt binaries for Windows arm64 or musl Linux such as Alpine
- GitHub Enterprise is not supported
- Extension API is experimental and may break between minor releases
- no GPU
- Needs Git (recommended), Node.js 22+ (npm install only), GH_TOKEN or GITHUB_TOKEN (private repos)
no-mistakes
no-mistakes places a local git remote in front of your real one. Pushing to it creates a disposable worktree and runs a pipeline (review, test, docs, lint, push, PR, CI) driven by a coding agent CLI such as claude or codex. The branch is forwarded to the real remote only after every gate passes, and a PR is opened for you. Safe fixes are applied automatically; other findings wait for approval in a TUI.
Who it is for: Developers who want agent-checked branches before raising PRs
Strengths
- Runs in an isolated worktree, so your working directory is not disturbed
- Works with claude, codex, grok, opencode, copilot, cursor and others, with ordered fallbacks
- Three entry points: git push, a TUI, or a /no-mistakes agent skill
- Watches CI after the PR opens and auto-repairs failures
Weaknesses
- Requires a runnable coding agent CLI configured for every gate
- Agent calls spend API quota; RAM and cost figures are unknown
- CI repairs may need another full review pass if revalidate_repairs is set
- Auto PR creation and CI watching are documented only for configured push targets such as GitHub
- Needs git, a coding agent CLI (claude, codex, opencode, etc.)
- Models: claude, codex, grok, rovodev, opencode
More in Code review and testing
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.