Governed, multi-model code review
that knows your codebase.
Not another per-seat review bot. Palgu review is a council of models that runs in your repo and routes every call through the gateway, so it is metered, budgeted, audited, and grounded in your org's code graph and ADRs. A tool you invoke, not a bot that auto-comments on every PR.
Your keys, your repo, a council, one bill.
It verifies before it flags.
A pipeline ported from a proven local council. An unstable agent never fails the run.
The opposite shape from a SaaS review bot.
CodeRabbit, Copilot, and Greptile are good SaaS review bots. You buy seats, the vendor's bot reads every PR in its cloud, one vendor model comments on every PR. Palgu review is the opposite shape: your keys, your repo, a council, governed on one bill.
| Capability | palgu> | CodeRabbit | GitHub Copilot | Greptile |
|---|---|---|---|---|
| Pricing model | Your model keys, metered at cost (no per-seat review tax) | Per-seat SaaS subscription | Per-seat (Copilot Enterprise) | Per-seat SaaS subscription |
| Where your code runs | Runs from your repo. The diff goes through the gateway to the council models; Palgu never runs your code | Uploaded to vendor cloud | Sent to vendor cloud | Indexed in vendor cloud |
| Multi-model council | Yes. GLM + DeepSeek + Kimi + Claude, you pick | Single vendor model | Single vendor model | Single vendor model |
| Grounded in your code graph | Yes, queries your org's iCPG over the gateway | Repo embeddings (RAG) | Repo + workspace context | Yes, its own codebase graph |
| Reads your ADRs / decisions | Yes, read_adr before flagging or clearing | No | No | No |
| False-positive control | Adversarial refuters must disprove every blocker; no file:line means dropped | Confidence heuristics | Model judgement | Confidence + graph signals |
| Any-size PR | Deterministic chunking. Every call sees a bounded input | Truncates / samples large PRs | Context-window bound | Handles large repos |
| One governed bill | Yes, review spend audited + budgeted with all model traffic | Separate vendor invoice | Separate vendor invoice | Separate vendor invoice |
| Invoke vs auto-comment | A tool you invoke (CLI / CI / MCP), not an always-on bot | Auto-reviews every PR | Auto-reviews every PR | Auto-reviews every PR |
| Self-hostable gateway | Yes, cloud or on-prem, bring your own keys | No | No | Partial (enterprise) |
Compared in good faith, June 2026. These are strong tools; if anything here is out of date, tell us and we will correct it.
Put your hard rules in one file.
docs/REVIEW_SKILL.md is read verbatim and outranks anything in a diff (diffs are untrusted material). Put your hard rules there (tenant isolation, no secrets, parameterized SQL) and every reviewer enforces them.
CLI, CI gate, or from your harness.
Review on your terms, governed by default.
Bring your own keys, run it only when you choose, and get a council that actually understands your codebase, all metered, budgeted, and audited with the rest of your AI traffic. No per-seat review tax, no always-on bot reading every PR.