[PLATFORM]

The platform

One brain that learns every app you have. Your planning and measurement system runs on top of it.

The brain

Connect your repositories and Omnibrain builds one encrypted knowledge graph across all of them. Each repo gets its own live brain that updates at every merge. Review, chat, and measurement all run on this layer.

Context Engine

The brain itself: an encrypted knowledge graph that maps every file, function, type, and dependency across all your repositories.

How it works

Omnibrain parses your repositories and builds a persistent graph of relationships: which functions call which, which types flow where, which modules depend on what. The graph is encrypted and versioned, and any tool can query it over HTTP or MCP.

What makes it different

  • Multi-repo native. Not bolted on. The graph spans your entire organization from day one.
  • Token-smart streaming. Omnibrain compresses and filters context before it touches an LLM, so a request costs a fraction of what stuffing whole files into the prompt would.
  • Provider agnostic. HTTP and MCP endpoints give every tool the same context: IDE extensions, CI pipelines, custom scripts.

It's why reviews see the blast radius and plans reference real files. Everything on this page runs on the same graph.

context_engine
$ omnibrain init --repos ./api ./frontend ./shared-libs
→ Scanning 2,847 files across 3 repositories...
→ Building cross-repo knowledge graph...
→ Indexing symbols and relationships...
✓ 34,291 symbols indexed
✓ 8,102 cross-repo relationships mapped
✓ Context API ready
Supported:
TypeScriptJavaScriptPythonGoRustJavaC++C#RubyPHPSwiftKotlin

Live Brain

Every repo you connect gets its own live brain, so the graph is never stale.

Every merge triggers a delta update. Omnibrain diffs the changes, updates only what changed, and propagates relationship updates across repos. No full re-index. No scheduled jobs. No drift.

  • → Sub-20 second updates for repos up to 500 files
  • → Branch-aware: feature branch graphs stay isolated
  • → Merge-triggered via the GitHub App, no CI setup needed
  • → Relationship propagation: rename a type and all references update
live brain
$ omnibrain update # triggered on every merge
→ Detected 3 changed files
→ Updating knowledge graph...
→ Propagating to 2 dependent repos...
✓ Graph updated in 4.2s

Deep Code Review

The only review that reads the diff, the blast radius, and the plan.

Most tools parse the diff. Omnibrain reviews from the brain: it traces every change through the knowledge graph to find what breaks, then checks it against your active goals to tell you what the work is for. One comment per PR, posted seconds after it opens, updated on every push. When the PR merges, the same brain absorbs the change.

What it catches that others don't

Goal alignment

Omnibrain matches every PR to the goal or task it serves, with a confidence score. Shaky matches stay hidden, and the author or goal owner can dispute any match in one click.

Cross-repo breaking changes

You renamed a type in the shared library. Omnibrain finds the 4 repos that import it and tells you exactly which files break.

Security surface analysis

Add a new endpoint and Omnibrain checks it for rate limiting, input validation, auth middleware, and audit logging, based on what your other endpoints do.

Pattern violations

Your team uses the repository pattern for DB access. A new hire wrote a raw query in the handler. Omnibrain flags it and points to the convention.

Complexity tracking

A function went from 12 to 23 cyclomatic complexity. Omnibrain suggests a split point based on logical boundaries.

github.com · PR #212 · shared-libs
omnibrain[bot] commented
Goal alignment
Matches: Unify auth session handling (confidence 0.87)
→ Linked task: Migrate UserSession to shared-libs
Code quality
ERROR UserSession type changed: 4 downstream consumers break
→ mobile-app/src/services/auth.swift:42
→ admin-panel/src/api/session.ts:19
WARNING /api/auth/reset-password missing rate limiting (other auth endpoints use 5 req/min)
INFO validateToken() branches 8 → 19, consider splitting at the token-type boundary
1 error · 1 warning · 1 info · one comment per PR, updated not recreated
omnibrain · contributions
Omnibrain contributions feed: merged pull requests, each showing the repository, branch and summary, the task it was matched to with a confidence percentage, and a Dispute control.
Every match lands here with its score and a one-click dispute, so the record stays arguable rather than imposed.
you:

How does authentication work across the API and mobile app?

omnibrain:

Authentication flows through 3 services:

  1. api/src/auth/oauth.ts:23 · Issues JWT tokens (RS256)
    Signs with private key from config/keys/
  2. api/src/middleware/auth.ts:15 · Validates on every request
    Checks expiry, extracts user_id, attaches to context
  3. mobile/src/services/auth.swift:42 · Stores token in Keychain
    Refreshes via api/src/auth/refresh.ts:31 when < 5min remaining

Shared types defined in:
shared-libs/src/types/auth.ts → UserSession, TokenPayload

Omnibrain Chat

Ask the brain anything, about any app on the system. Answers come grounded in actual code, with file paths, line numbers, and impact analysis.

Not another chatbot wrapper. Omnibrain Chat queries the knowledge graph before every response, so the LLM sees exactly the code that matters. Ask about one repo or ten. The context assembles automatically.

  • → Multi-repo sessions: one conversation spans all your repositories
  • → Session memory: context carries forward, no re-explaining
  • → Any LLM backend: GPT, Claude, Llama, Mistral, or your own models
  • → File references you can click, not paragraphs you have to parse

The tracker, on top of the brain

Omnibrain replaces your tracker. Plan the whole company's work as goals, tasks, and issues. Because every merged PR flows through the brain, delivery measures itself at company, team, and engineer level.

Goals, Tasks & AI Planning

Describe the objective. Get a plan grounded in your actual codebase. The plan then tracks itself.

How it works

  1. You describe the objective in conversation with the agent
  2. It asks clarifying questions, and it pulls code from the relevant repos before asking the next one
  3. It builds a goal → task tree with estimates, grounded in the code it just read
  4. From the first merged PR, progress rolls up on its own. No status meetings, no card-dragging

This is your tracker now. Goals, tasks, and issues are first-class in the platform. Bugs and interruptions live next to planned work, and statuses update on their own as PRs land.

  • → Three modes: build goal trees by hand (zero ceremony), generate one in a single shot, or plan deep across many turns
  • → Goals nest by horizon: year → quarter → month → sprint → initiative
  • → Estimates are commitments. Every task carries one, and Omnibrain measures delivery against it
  • → Plans track themselves. Progress rolls up the goal tree, weighted by estimates
planning agent
$ planning session: "Cut checkout p99 below 300ms"
clarifying...
→ Which services sit in the checkout path?
retrieving code before the next question...
→ api-gateway/src/checkout/* · handler chain
→ payment-service/src/intents.ts · external call in hot path
✓ 23 relevant code sections in context
synthesizing...
GOAL [quarter] Cut checkout p99 below 300ms
├─ TASK Read-through cache for price lookups est 3d
├─ TASK Batch inventory checks in checkout path est 2d
├─ TASK Move fraud scoring off the hot path est 4d
└─ TASK Load-test rig + p99 gate in CI est 2d
✓ Plan created. Tracking starts on the next merged PR.
omnibrain · goals · Q3 2026
Omnibrain goals view: nine goals with progress bars, action-item counts and pace badges reading Ahead, On Track or Behind.
…and the plan it produced, tracking itself. Pace comes from delivery, so 'behind' surfaces in week three rather than at the retro.

Engineer Performance

Plan-execution measurement for engineering leadership. Enterprise

The other half of the tracker. When tasks finish and their PRs merge, the brain has already matched the work, so measurement falls out automatically. For directors and VPs who need to answer: are we building what we committed to, and who's delivering? From merged code, not self-reporting.

Not a dashboard reading tracker labels. Measurement computed from the code itself.

omnibrain · ranking · payments platform
Omnibrain ranking view: engineers ordered by estimate-days delivered, weighted by timeliness, honesty and quality, each row showing its attribution coverage.
Where attribution coverage is thin, the product says so rather than quietly scoring anyway.
1
Set goals

Leadership defines goals by horizon (year, quarter, sprint) in conversation with the planning agent or by hand. Goals nest, and teams own subtrees.

2
Teams commit

Goals break into tasks with estimates. The estimate is the commitment, and every task carries one.

3
PRs map automatically

Omnibrain matches every merged PR to the goal, task, or issue it serves, with a confidence score. No manual tagging, no labels, no developer overhead.

4
Four numbers per engineer

Plan delivery rate. On-time rate. Estimate accuracy. Strategic alignment. Per engineer, per team, per goal, over any period.

5
Goal pace

Every goal shows current pace and a predicted completion date, so "we're behind" surfaces in week 3, not in the retro.

6
Engineers can dispute

Every match is visible to the engineer it affects, and the author or goal owner can override it. Measurement, not surveillance.

See it on your codebase

Book a demo. We'll run it on a real repo, not a slide deck.