Bubo 🦉

Agentic AI code review with the LLM of your choice. Bubo reviews your GitLab MRs and GitHub PRs with the model you run, and posts only the findings worth acting on as inline threads — no chatbot noise, no praise, no summaries.

• Self-hosted — code, diffs, and review data stay on your infrastructure
• Bring-your-own-LLM — Codex, Claude, or any model your CLI drives
• SCM — Currently supports Gitlab and Github
• findings — Inline or "all good" if clean
• Governance, provenance & an auditable on-prem report - cosign-signed releases with SBOMs
• Metrics — Opentelemetry

Full documentation → mountainowl.github.io/bubo

Install

uv tool install bubo     # or: pipx install bubo
bubo init                # idempotent; seeds config + workspace + DB
bubo doctor              # verify before the first poll
bubo-poller service start # start the review service (polling + outcome sync)

Prefer a container? docker pull ghcr.io/mountainowl/bubo (multi-arch; the review-agent CLI is BYO). Continue with the recipes and quickstart.

Documentation

Everything lives on the docs site — this README is just the front door.

Recipes	Copy-paste GitLab / GitHub / in-house-model setups.
Features	The full capability list.
Configuration	Every setting, per section, plus a quick-start config.
GitHub Action	Run one synchronous PR review in GitHub Actions.
Operate	Deploy, run the review service, grade outcomes, governance report.
Troubleshooting	Host / infra fixes (sandbox, AppArmor).
Metrics & telemetry	Emitted llm_review.* metrics and dashboards.

Status

• GitLab & GitHub posting via polling — production path, at outcome-metric parity. Set [scm].provider = "github" (or BUBO_PROVIDER=github).
• GitHub Marketplace Action — experimental synchronous review for the PR that triggered a GitHub Actions workflow; start in dry-run mode.
• MCP server (bubo-mcp) — read-only metrics + triggered reviews; stdio or HTTP.
• Codex or Claude — Bubo runs the review through a wrapper around your agent CLI; Codex ships pre-wired.
• Webhook service — not yet; long-running deployments use polling, while the GitHub Action can run one review from a pull_request workflow.

For continuous operation, run the service beside your pipelines. Use the Marketplace Action only when a CI-scoped review is the intended deployment.

Security

• config/env.toml is gitignored and holds tokens. Do not print or commit real values.
• Review-agent stdout is redacted (GITLAB_TOKEN=, OPENAI_API_KEY=, glpat-…, sk-…, credentialed Git URLs) before it touches reports, logs, or the database.
• The reviewer subprocess runs under a strict env allowlist — host secrets aren't handed wholesale to the LLM agent.
• Releases are cosign-signed via Sigstore keyless OIDC, with an SBOM on every release.
• Report vulnerabilities per SECURITY.md.

Community

Contributing · Security policy · Support · Code of conduct · License: MIT