An agent that works through pull requests.
Forge is an autonomous GitHub coding agent. It investigates issues and opens fixes, reviews pull requests across quality and security lenses, and runs deterministic scanners before it ever calls a model.
It never merges and never approves — every change is a PR you control.
Unvalidated URL passed to server-side fetch
src/checkout/webhook.ts:64
Session token written to the request log
src/lib/logger.ts:22
Retry loop lacks an upper bound
src/http/client.ts:118
3 findings · check run neutral · nothing merged
Deterministic first, the model second.
The cheap, exact checks run before anything is sent to a provider — so the model spends its budget on the findings only a model can reach.
- 01
A GitHub event arrives
An issue label, a comment command, a new pull request, or a cron routine. Forge clones the repository into a disposable sandbox.
- 02
Scanners run first
Secrets, infrastructure, and source scanners execute before any model call — deterministic, instant, and free of token cost.
- 03
The agent loop reasons
A tool allowlist strips unused schemas from every turn, context compaction elides stale output, and prompt caching bills repeated context at roughly a tenth of the input rate.
- 04
Tests verify the change
The suite runs inside the sandbox. On forge/* branches, failing CI is read, corrected, and re-run as a ci-fix commit.
- 05
Findings merge into one review
Scanner output and model findings are deduplicated and grouped by rule, then posted as inline comments plus a single summary verdict.
Every trigger, and what comes back.
Forge is driven from the places you already work — a label, a comment, a mention, or a key in agent.yml. Pick one to see the transcript it produces.
The issue never gets a paragraph of advice. It gets a branch, a passing suite, and a pull request that closes it.
Meet Forge, your agent on GitHub.
ShipIt Agent lives inside your project. Forge lives on your repository — an autonomous coding agent that fixes issues, opens pull requests, and reviews them with a security pass. Self-hosted, multi-provider, and vision-aware.
It never merges and never approves — every change is a PR you control.
Fix an issue, open a PR
Investigates the repository, writes the fix on a branch, runs the tests, and opens a pull request that closes the issue.
label agent-fix · /fixReview a pull request
Inline comments plus a summary verdict, across quality and security lenses, scoped strictly to the files that changed.
/review · /review alwaysSecurity review
Flags SSRF, injection, secrets, and authz gaps — each with a severity, a CWE, and a suggested-fix block.
automatic on PRs · /securityDeterministic scanners
Secrets, infrastructure, and source scanners run before the model at no token cost, then merge into its findings.
automatic · /secretsWhole-repo audit
Maps entry points, follows untrusted input through to dangerous sinks, and files one grouped report.
/auditRoutines and skills
Eight built-in prompt packs with enforced tool allowlists, plus saved routines on cron, on demand, or any repo event.
routines: in agent.yml · /run- 401
- tests passing
- 9
- LLM providers
- 8
- built-in skills
- MIT
- open source