lakeday-org/perch has 317 GitHub stars and 18 forks. GitHot measured 0 stars in 24 hours and +2 in 7 days. Last checked 2026-11-18 20:19 UTC. Last push 2026-11-10.
Measured star growth
- in 24h
- 0
- in 7 days
- +2
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
Semantic code and security scanner
Developer ToolsREADME.md
Originalperchscan.com · docs · benchmarks · Discord
Semantic code and security scanner.
Getting started
npm install -g @lakeday/perch
perch login
perch scan
perch login signs you in to Perch Cloud, where the first $5 is free. Since decisions are cached,
running perch again on unchanged code is free. Perch Cloud also scans pull requests in CI, without writing
any workflows.
$ perch scan
checkout.py
ID Line Severity Type Confidence Problem Method
bdc67421 14 P1 (0.8) defect 81% wrong_order place_order
ddc5c917 24 P1 (0.8) defect 92% inverted_condition can_fulfil
cart.py
ID Line Severity Type Confidence Problem Method
287bfb9d 9 P1 (1.0) defect 90% off_by_one subtotal
80d6ebbb 29 P1 (1.4) defect 89% unhandled_null cheapest
✖ 20 problems in 5 files, all failing
Run perch issues to see them worst first, and perch issues <id> to view one.
perch check <id> asks again after you think you've fixed it. It doesn't record anything.
Agent skills
perch setup claude-code # .claude/skills/perch/SKILL.md
perch setup codex # .codex/skills/perch/SKILL.md
perch setup pi # .pi/skills/perch/SKILL.md
perch setup cursor # .cursor/rules/perch.mdc
Semantic linting
You can extend perch with your own linting rules by adding them to perch.yaml:
- name: private-logs
where: "src/**/*.ts"
each: method
ensure: >
Keep passwords and access tokens out of logs.
ReviewBench
ReviewBench is GitHub's benchmark for AI code review. Perch is credited when it flags the method holding
a labelled bug; the leaderboard credits a review comment that a judge model matches to one. The runs, the answers and how to
reproduce them are linked from .benchmarks/reviewbench.
The numbers
| Reviewer | Recall |
|---|---|
| Laude RevEngine Prime | 46.3% |
| Perch · OpenAI Decisions, $0.024 a pull request | 40.0% |
| block/review | 32.6% |
| Klaussy | 29.8% |
| Copilot code review | 26.0% |
| DeepSeek Harness Reviewer | 25.6% |
| Devin AI | 23.8% |
| Qodo | 22.1% |
| Codex | 18.5% |
| Cubic | 16.3% |
| Greptile | 16.2% |
| Cursor | 9.6% |
| Perch · Jev, $0.011 a pull request | 7.9% |
Greptile benchmark
Greptile's benchmark runs code reviewers on 50 pull requests, each with one known bug.
The runs and their labels are linked from .benchmarks/greptile.
Perch is credited when it flags the function holding the known bug. The published tools were credited for a line comment identifying it.
Models
By default, Perch Cloud routes your questions to the best model for answering them. To ask a specific decision model, override the endpoint, key, and model:
export PERCH_BASE_URL=https://api.typesafe.ai/v1/systemone
export PERCH_API_KEY='paste-your-TypeSafe-key-here'
export PERCH_MODEL_ID=jev-latest
| Model | PERCH_BASE_URL |
PERCH_MODEL_ID |
|---|---|---|
| Jev | https://api.typesafe.ai/v1/systemone |
jev-latest |
| Liquid AI d1 | https://api.liquid.ai/decisions/v1/systemone |
d1:free |
| OpenAI gpt-6-luna | https://api.openai.com/v1/decisions |
gpt-6-luna |
| DiffusionGemma Jev on Beam | https://app.beam.cloud/v1/models/jev/diffusiongemma/invoke |
jev/diffusiongemma |
| SemiF on Beam | https://app.beam.cloud/v1/models/jev/semif/invoke |
jev/semif |
Any endpoint that supports the System One format will work, and so does OpenAI's Decisions API: perch recognizes a
PERCH_BASE_URL ending in /decisions and reads its key from OPENAI_API_KEY when PERCH_API_KEY is not set. Each model gets as many questions per request as it says it
takes. For a model that doesn't say, set PERCH_MAX_QUESTIONS. See the
benchmarks for a comparison.
Documentation
| Getting started | Install, sign in, the first scan. |
| Reading issues | The list, the filters, closing what does not matter. |
| Semantic linting | where, each, sees, context, min, gate, and the longhand grammar. |
| Checking a change | perch check on work in progress. |
| perch in CI | What a build can gate on, and what it cannot. |
| Command reference | Every command, its flags, and what each exit code means. |
| Scan internals | The graph walk, the questions, and how probabilities turn into a ranking. |
Perch files
| Location | Contents |
|---|---|
.perch/ |
Generated scan results and cache files, alongside the committed files below. Use --out <directory> to choose another results location. |
.perch/rules/ |
Custom rules split across .yaml and .yml files. Commit these files. |
.perch/closed.jsonl |
Dismissed findings and their reasons. Commit this file. |
perch.yaml |
Custom rules. Updated by perch rules add, edit, and remove. |
.claude/, .codex/, .pi/, .cursor/ |
Instructions installed for the selected assistant by perch setup <assistant>. |
Development
npm install # dependencies
npm run check # lint, typecheck, test
npm run build # bundle src/cli.js into dist/cli.mjs
npm link after a build puts the checkout's perch on your PATH.