<div align="center"> <img src="assets/logo.png" width="300" alt="Corbell Logo" /> <h1>Corbell</h1> Multi-repo architecture graph, AI-powered spec generation, and architecture review — for backend teams that ship to production. <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License"/></a> <a href="CONTRIBUTING.md"><img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg" alt="PRs Welcome"/></a> </div>

What problem does this solve?

You're a staff engineer or architect at a company where features touch 5–10 repositories. Every quarter your team re-litigates the same architectural decisions: "should we use Kafka or SQS?", "why do we have three different auth patterns?", "who owns the rate-limiting layer?"

The decisions live in Confluence pages nobody reads, Slack messages nobody can find, and the memories of engineers who've since left.

When a new engineer joins—or even when you return to a service you haven't touched in 6 months—you're starting from scratch.

Corbell gives your team a living knowledge graph of your architecture — built from the actual code in your repos and your team's past design docs. When you need a new spec, Corbell generates one that respects your established patterns instead of inventing new ones. When you push to Linear, each task carries the exact method signatures, call paths, and cross-service impacts an AI coding agent needs to work autonomously.

How it looks

Star History (thank you)

How it works

Your repos → [graph:build] → Service graph (SQLite)
Your docs  → [docs:scan]   → Design pattern extraction
              ↓
  [spec new --feature "Payment Retry" --prd-file prd.md]
                 →  Generates 3-4 PRD-driven code search queries (LLM or regex)
                 →  Auto-discovers relevant services via embedding similarity
                 →  Injects graph topology + real code snippets
                 →  Applies your team's established design patterns
                 →  Calls Claude / GPT-4o to write the full design doc
                 →  Displays token usage and estimated cost
                 →  specs/payment-retry.md ✓
              ↓
  [spec review]    → Checks claims against graph → .review.md
  [spec decompose] → Parallel task tracks YAML
  [export linear]  → Linear issues with full method/service context

No servers. No cloud setup. Runs entirely from your laptop against local repos.

Installation

pip install corbell

# With LLM support (pick one):
pip install "corbell[anthropic]"    # Claude (recommended)
pip install "corbell[openai]"       # GPT-4o

# With exports:
pip install "corbell[notion,linear]"

# Everything:
pip install "corbell[anthropic,openai,notion,linear]"

Requirements: Python ≥ 3.11

🚀 Quick Setup (2 minutes)

Prerequisites

Python 3.8+ or Node.js 16+ or Go 1.19+ (based on your project)
Git repository with source code

Essential Steps

Initialize Corbell workspace
```
corbell init
```
✅ Creates workspace.yaml in your project root
Generate your first design document
```
corbell spec new --prd "Add user authentication feature"
```
✅ Creates design document with auto-discovered services
View architecture graph (optional)
```
corbell ui serve
```
✅ Opens browser at http://localhost:7433

Verify Setup

[ ] workspace.yaml exists in your project
[ ] Design document generated successfully
[ ] Architecture graph loads (if using UI)

Need more details? See Full Documentation below.

📖 Full Documentation

<details> <summary>Advanced Usage Guide</summary>

1. Initialize a workspace

cd ~/my-platform   # wherever your repos live
corbell init

Edit corbell-data/workspace.yaml:

workspace:
  name: my-platform

services:
  - id: payments-service
    repo: ../payments-service
    language: python        # python | javascript | typescript | go | java | csharp | rust | ruby | php

  - id: auth-service
    repo: ../auth-service
    language: go

llm:
  provider: anthropic   # or: openai, ollama
  model: claude-sonnet-4-5-20250929
  api_key: ${ANTHROPIC_API_KEY}

2. Build the knowledge graph

corbell graph build --methods    # service + dependency graph + call graph, typed signatures, flows
corbell embeddings build         # code chunk index for semantic search
corbell docs scan && corbell docs learn   # extract patterns from existing RFCs/ADRs

3. Generate a design document

export ANTHROPIC_API_KEY="sk-ant-..."

# From a PRD file — services are auto-discovered, no --service flag needed
corbell spec new \
  --feature "Payment Retry with Exponential Backoff" \
  --prd-file docs/payment-retry-prd.md

# Spec with full call graph and infrastructure context
corbell spec new --feature "Auth Flow" --prd-file prd.md --full-graph

# Inline PRD
corbell spec new --feature "Rate Limiting" --prd "Tier 1: 100 req/min..."

# Document your existing codebase with no PRD at all
corbell spec new --existing

# Add existing design docs as context (ADRs, Confluence exports, RFCs)
corbell spec new --feature "Auth Token Refresh" --prd-file prd.md \
  --design-doc docs/auth-design-2023.md

Token usage and estimated cost are shown after every LLM call. Template mode (no LLM key) generates a structured skeleton with graph context filled in.

4. Document architecture constraints

Add a constraints block to any spec and all future specs will respect it:

<!-- CORBELL_CONSTRAINTS_START -->
- **Cloud provider**: Only Azure — no AWS services permitted
- **Latency SLO**: p99 < 200ms for all synchronous API calls
- **Security**: All PII encrypted at rest (AES-256) and in transit (TLS 1.2+)
<!-- CORBELL_CONSTRAINTS_END -->

corbell spec review checks proposed designs against these constraints. The corbell ui serve graph browser also surfaces them in a persistent bar at the bottom.

5. Review, approve, decompose, export

corbell spec review specs/payment-retry.md     # → .review.md sidecar
corbell spec approve specs/payment-retry.md

corbell spec decompose specs/payment-retry.md  # → .tasks.yaml

export CORBELL_LINEAR_API_KEY="lin_api_..."
corbell export linear specs/payment-retry.tasks.yaml

</details> <details> <summary>Architecture graph browser</summary>

corbell ui serve          # opens http://localhost:7433 · Ctrl+C to stop
corbell ui serve --port 8080 --no-browser

An interactive local graph view — no cloud, no sign-in, reads from your existing SQLite store:

Force-directed graph — services (sized by method count), data stores, queues, execution flows. Zoom, pan, drag.
Detail panel — click any service to see: language, dependencies, HTTP callers, typed method signatures, execution flows (e.g. LoginFlow), git change coupling pairs with strength %.
Constraints bar — all CORBELL_CONSTRAINTS_START blocks from your spec files shown as persistent amber pills at the bottom. Click to expand.
Sidebar — filterable service list, stores, queues, flows with search.

</details> <details> <summary>CLI Reference</summary>

graph       Service dependency graph
  build       --methods for call graph + typed signatures + git coupling + flows
  services    List discovered services
  deps        Show service dependencies
  callpath    Find call paths between methods

embeddings  Code embedding index
  build       Index code chunks
  query       Semantic search

docs        Design doc patterns
  scan / learn / patterns

spec        Design spec lifecycle
  new         --feature --prd-file --prd --design-doc --existing --no-llm
  lint        Validate structure (--ci exits 1)
  review      Check spec vs graph → .review.md
  approve / decompose / context

export      notion | linear

ui          Architecture graph browser
  serve       --port (default 7433) --no-browser

mcp         Model Context Protocol server
  serve       stdio transport for Claude Desktop / Cursor

init        Create workspace.yaml

</details> <details> <summary>MCP – Model Context Protocol</summary>

Corbell exposes its architecture graph, code embeddings, and spec tools via MCP, so external AI platforms (Cursor, Claude Desktop, Antigravity) can query your codebase context directly.

Available Tools

| Tool | Description | |---|---| | graph_query | Query service dependencies, methods, and call paths | | get_architecture_context | Auto-discover relevant services for a feature description | | code_search | Semantic search across the code embedding index | | list_services | List all services in the workspace graph |

Usage

# Default: stdio transport (for IDE integrations)
corbell mcp serve

# SSE transport (for web-based MCP clients / MCP Inspector)
corbell mcp serve --transport sse --port 8000

IDE Configuration

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "corbell": {
      "command": "corbell",
      "args": ["mcp", "serve"]
    }
  }
}

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "corbell": {
      "command": "corbell",
      "args": ["mcp", "serve"]
    }
  }
}

If your IDE overrides the working directory, set the CORBELL_WORKSPACE environment variable:

env CORBELL_WORKSPACE=/path/to/my-platform corbell mcp serve

</details> <details> <summary>Auto service discovery</summary>

When you r

Corbell

Install / Use

README