Skip to content

Kramlipi Code Agent

Shipping slows down in review long before it slows down in the editor. Most teams lose roughly five days per PR in waits, nits, and “one more look”—work that never makes it onto the roadmap but always makes it onto the calendar.

Agents changed the shape of that work, not the need for it. Diffs arrive faster now; someone still has to sign off on correctness, intent, and risk. The job was never mostly keystrokes—it was always reading, deciding, and coordinating. AI just made that the visible bottleneck.

Kramlipi handles both sides. For review: a first pass with full repo context, posted as line comments on the PR—not a chatbot paraphrase of the diff. For red CI and coverage gates: read the failure, edit the code, run your tests again, repeat until green. We auto-detect the verify command from your repo (Auto verify); no need to guess pytest vs mvn first. No green, no done.

Code review is free. Try it at kramlipi.github.io, or skip to review a PR in the quick start below.

Download a binary for laptop or CI, bring your own LLM, keep your source inside your boundary.

How kramlipi helps — visual collage →

Quick start

Download Linux / macOS / Windows:

Google Drive · GitHub Releases · Release notes

chmod +x code-agent   # Linux / macOS
# Windows: code-agent.exe

2. ENV (Gemini)

Key from Google AI Studio:

export CODE_AGENT_MODEL=gemini/gemini-2.0-flash
export GEMINI_API_KEY=YOUR_SECRET_KEY

3. What do you want to do? (commands)

Increase code coverage

Pain: Coverage gate blocks merge.
Fix: Agent adds tests; your verify command must still exit 0.

code-agent run "increase unit test coverage" \
  -w /path/to/your-repo \
  --verify-cmd "go test ./..."

Python: --verify-cmd "pytest -q --cov=PACKAGE --cov-fail-under=80" → Use cases → Coverage · Features → Coverage

Fix a broken build / failing tests

Pain: CI failed; log is unreadable; you need a scoped green fix.
Fix: Parse log → edit code → re-run the same CI command.

go test ./... 2>&1 | tee /tmp/ci.log
# or: pytest -q 2>&1 | tee /tmp/ci.log

code-agent experts run bug-fix \
  --log /tmp/ci.log \
  --verify-cmd "go test ./..." \
  -w /path/to/your-repo

Language walkthroughs: Python · Go · Java

Review a PR (inline line comments)

Pain: PRs merge without a first-pass review for bugs / nits / security smells.
Fix: LLM reviews the PR diff and posts GitHub inline comments (comment-only).

export GH_TOKEN=...   # or GITHUB_TOKEN in Actions

code-agent experts run code-review --pr 42 -w /path/to/your-repo
code-agent experts run code-review --pr 42 --dry-run -w /path/to/your-repo

More: Use cases · Features

Other features

I want to… Do this Detail
Run fewer tests on a PR code-agent experts run test-intel --pr N -w . Use cases
Babysit PR until green code-agent experts watch --pr N --verify-cmd "…" -w . Use cases
Find missing metrics code-agent experts run monitoring-expert -w . --dry-run Features
Alert → reliability fix code-agent experts run sre-expert --log alert.json -w . Use cases
Canary / deploy gate code-agent experts run deploy-guard --metrics-file m.json Features
Flag Meaning
-w Repo folder the agent may edit
--verify-cmd Must exit 0 — success is not model opinion

Full walkthrough: Get started (only start page)

Pricing

Free Team $49/mo Business $199/mo
Prove one green verify (capped) Commercial CI + PR babysit / higher volume

→ Get started — Pricing

4. Docker (second choice)

docker pull ghcr.io/kramlipi/code-agent:latest

docker run --rm -it \
  -e CODE_AGENT_MODEL \
  -e GEMINI_API_KEY \
  -v "$PWD:/workspace" \
  ghcr.io/kramlipi/code-agent:latest \
  run "increase unit test coverage" \
  --verify-cmd "go test ./..." \
  -w /workspace

Image: ghcr.io/kramlipi/code-agent:latest · GHCR packages

After the quick commands

Next Why
Get started Binary, ENV, use cases, Docker UI, pricing (only start page)
Use cases Playbooks + pains + Python/Go/Java examples
Features Experts, CLI, recipes, coverage (full reference)
Tutorials & Blog Top nav tab — walkthroughs, Smarter Testing M1, Python/Go/Java
Help Exit codes and failures
Security overview Enterprise trust / data flow
Deployment modes Local binary · CI · local UI
config All config knobs

How verify works

--verify-cmd "pytest -q"
Exit Meaning
0 Success
1 Config / doctor problem
2 Agent ran but verify (or post) failed

The agent refuses to edit .github/workflows/** to cheat CI.

Site