Documentation Index
Fetch the complete documentation index at: https://docs.sigilix.ai/llms.txt
Use this file to discover all available pages before exploring further.
Sigilix
Sigilix is a multi-agent code review GitHub App. Every pull request is read in parallel by four domain specialists — Glyph (architecture), Warden (security), Spark (performance), and Weave (semantics) — and a synthesizer (Core) that cross-checks their findings, deduplicates noise, and posts a single coherent review. The output looks like one comment from a senior engineer who’s read everything carefully. Behind that comment, five models did the work.Quickstart
Install the GitHub App, point it at a repo, and get your first review in under five minutes.
The Ensemble
Why five specialists beats one generalist — the architectural argument with diagrams.
Configuration
The full
sigilix.yaml schema — disable specialists, ignore paths, tune severity.GitHub Integration
Permissions, scopes, branch protection, and how Sigilix interacts with checks.
What Sigilix is not
- Not a chat tool. Sigilix doesn’t answer questions in a conversation interface. It posts structured review comments on pull requests.
- Not a code generator. Sigilix surfaces findings with line references and suggested patches. Your team decides what to merge.
- Not training on your code. Code is sent to model providers under their data-use commitments and discarded after the review. We don’t fine-tune on customer repositories.
What you’ll see on every PR
When Sigilix reviews a PR, you get one comment fromsigilix[bot] containing:
- A synthesizer summary — what changed, what concerns survived dedup, and whether the verdict is Approved or Request changes.
- Inline findings anchored to specific lines, tagged by specialist (Glyph, Warden, Spark, Weave) and severity (Critical / Warning / Info).
- Suggested patches for findings where a clean fix is in scope.