CognetivyCognetivy is an open-source state layer for AI coding assistants that adds workflows, run tracking, and persistent collections - all local.
Automated Code Review & Docs
Consistent, structured code review across every pull request.
Ad-hoc code review is inconsistent. Define a workflow that gives your agent a consistent review checklist - security, performance, style, documentation - and stores findings in a structured collection. Run it on every PR and track quality trends over time.
What you'll achieve
Consistent standards
The same criteria are applied to every PR - no variation based on who reviews.
Quality trends
Aggregate review data shows which issue types recur and which have been resolved.
Documentation coverage
Automatically flag under-documented functions and generate doc stubs as artifacts.
How it works
A repeatable workflow you define once and run any time.
Define review criteria
Encode your team's review standards as workflow steps: security scan, performance check, API contract validation, doc coverage.
Run against changed files
Your agent reads the diff and runs each review criterion, logging findings as structured events.
Generate review artifact
A structured review report is produced - categorized findings with severity levels and line references.
Track quality trends
Collection records accumulate across PRs, letting you surface recurring issue patterns over time.
Cognetivy features you'll use
Everything you need is already in Cognetivy.
Versioned, reusable step-by-step processes for your agent
Schema-backed data stores that persist and accumulate across runs
Structured outputs saved from any run - downloadable and linkable
Full event log of every agent session, with timing and status
Related use cases
Ready to try?
Set up your first structured workflow in under a minute.