See the repo.
Then see what matters.
DiffSwarm reviews a pull request like a programmer would: changed files, live issues, and plain-English activity in one local terminal app. Your code stays local. Your models stay yours.
Anthropic charges $25 per review. CodeRabbit charges per seat. DiffSwarm: $14.99/mo, unlimited reviews, your own API keys. See the comparison
From Pull Request to Clear Next Steps
Parse
Read a local diff or GitHub PR and map changed ranges.
Review Files
Walk the changed files and keep the run anchored to the code that actually moved.
Verify Issues
Surface likely problems, test them against nearby context, and keep only the issues that still matter.
Ship A Report
Finish with a clean markdown and JSON report plus an OpenTUI summary you can follow in real time.
Choose Your Vector
Find Logic & Edge Cases
Track the changed files, follow the live issue list, and inspect exact code or diff context while DiffSwarm checks correctness risks.
- Repo-first UI with Files, Issues, and Activity
- Exact code and diff evidence for each issue
- Adaptive budgets and explicit rerun guards
OWASP & CWE Precision
Focus the same repo-first workflow on auth, input handling, config, and crypto changes so security issues stay readable and actionable.
- Auth, input handling, config, and crypto issue coverage
- Plain-English status with severity-aware color cues
- OWASP/CWE metadata in surfaced findings
Engineered for CI & Local dev
Bring Your Own Model (BYOK)
DiffSwarm supports Anthropic Claude Code and OpenAI Codex CLI. You provide the credentials to the local engine. We do not proxy your API calls, ensuring maximum privacy and zero markup on token costs.
CI/CD Integration
Run headless in actions. Use --comment to automatically post verified findings to your GitHub PR.
Auto-tuned Budgets
Pass --time-budget-minutes 60 and the reviewer will scale passes and fleet size to fit the window. Repeated expensive reruns must be explicitly approved.
100% Local Execution
The DiffSwarm terminal app and review backend run locally. Your proprietary code never touches our servers. PR URL runs use a bounded local snapshot of changed files when no checkout is available, and the only DiffSwarm network calls are entitlement checks.
FAQ
What API keys do I need?
You need either Anthropic Claude Code or OpenAI Codex CLI installed and authenticated. DiffSwarm uses your existing credentials to orchestrate the review. No additional API keys from us.
How much do AI tokens cost on top?
Token costs depend on PR size and your AI provider's rates. A typical balanced review uses roughly the same tokens as a normal Claude Code or Codex session. DiffSwarm never marks up or proxies your API calls — you pay your provider directly.
Does my code leave my machine?
Never. DiffSwarm runs 100% locally. The only network calls are entitlement checks to verify your subscription. Your code is reviewed on your machine by your AI engine.
How is this different from Anthropic's Code Review?
Anthropic's Code Review costs $15–25 per review, requires a Team or Enterprise plan, and runs in their cloud. DiffSwarm costs $14.99/mo for unlimited reviews, works with your existing Claude Code or Codex subscription, runs locally, and includes a dedicated OWASP security audit mode. Full comparison here.
Can I try before I subscribe?
Yes. Run diffswarm diff sample.diff --dry-run to see the full terminal UI and review flow without a subscription or LLM calls.