corbell

Name: corbell
Author: corbell-ai

bycorbell-ai· 2 MCP servers

Stars

464

Forks

How to install corbell?

corbell-ai/corbell

$git clone https://github.com/corbell-ai/corbell

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install corbell by running `git clone https://github.com/corbell-ai/corbell`, then use it for the current task and follow its documentation at https://github.com/corbell-ai/corbell.

Files · 1

View on GitHub

README.md

1	<div align="center">
2	<img src="assets/logo.png" width="300" alt="Corbell Logo" />
3	<h1>Corbell</h1>
4	<p><strong>Multi-repo architecture graph, AI-powered spec generation, and architecture review — for backend teams that ship to production.</strong></p>
5	<p>
6	<a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License"/></a>
7	<a href="CONTRIBUTING.md"><img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg" alt="PRs Welcome"/></a>
8	<a href="https://agentseal.org/mcp/corbell"><img src="https://agentseal.org/api/v1/mcp/corbell/badge" alt="AgentSeal MCP"/></a>
9	</p>
10	</div>
11
12	---
13
14	## What problem does this solve?
15
16	You're a staff engineer or architect at a company where features touch 5–10 repositories.<br/>
17	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?"
18
19	The decisions live in Confluence pages nobody reads, Slack messages nobody can find, and the memories of engineers who've since left.
20
21	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.
22
23	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.
24
25	---
26
27	## How it looks
28
29	<p align="center">
30	<img src="assets/corbell_ui.png" width="48%" alt="Corbell UI" />
31	<img src="assets/mermaid_diagram.png" width="48%" alt="Mermaid Diagram" />
32	</p>
33
34	## Star History (thank you)
35	<p align="center">
36	<img src="assets/star_history.png" width="70%" alt="Corbell Star History" />
37	</p>
38
39	## How it works
40
41	```
42	Your repos → [graph:build] → Service graph (SQLite)
43	Your docs → [docs:scan] → Design pattern extraction
44	↓
45	[spec new --feature "Payment Retry" --prd-file prd.md]
46	→ Generates 3-4 PRD-driven code search queries (LLM or regex)
47	→ Auto-discovers relevant services via embedding similarity
48	→ Injects graph topology + real code snippets
49	→ Applies your team's established design patterns
50	→ Calls Claude / GPT-4o to write the full design doc
51	→ Displays token usage and estimated cost
52	→ specs/payment-retry.md ✓
53	↓
54	[spec review] → Checks claims against graph → .review.md
55	[spec decompose] → Parallel task tracks YAML
56	[export linear] → Linear issues with full method/service context
57	[export jira] → Jira issues via REST API v3 (reads from workspace.yaml)
58	```
59
60	No servers. No cloud setup. Runs entirely from your laptop against local repos.
61
62	---
63
64	## Installation
65
66	```bash
67	pip install corbell
68
69	# With LLM support (pick one):
70	pip install "corbell[anthropic]" # Claude (recommended)
71	pip install "corbell[openai]" # GPT-4o
72
73	# With exports:
74	pip install "corbell[notion,linear,jira]"
75
76	# Everything:
77	pip install "corbell[anthropic,openai,notion,linear,jira]"
78	```
79
80	Requirements: Python ≥ 3.11
81
82	---
83
84	## 🚀 Quick Setup (2 minutes)
85
86	### Prerequisites
87	- Python 3.8+ or Node.js 16+ or Go 1.19+ (based on your project)
88	- Git repository with source code
89
90	### Essential Steps
91
92	1. Initialize Corbell workspace
93	```bash
94	corbell init
95	```
96	✅ Creates `workspace.yaml` in your project root
97
98	2. Generate your first design document
99	```bash
100	corbell spec new --prd "Add user authentication feature"
101	```
102	✅ Creates design document with auto-discovered services
103
104	3. View architecture graph (optional)
105	```bash
106	corbell ui serve
107	```
108	✅ Opens browser at http://localhost:7433
109
110	### Verify Setup
111	- [ ] `workspace.yaml` e

6 picks

Type

corbell

bycorbell-ai· 2 MCP servers

Stars

464

Forks

How to install corbell?

corbell-ai/corbell

$git clone https://github.com/corbell-ai/corbell

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install corbell by running `git clone https://github.com/corbell-ai/corbell`, then use it for the current task and follow its documentation at https://github.com/corbell-ai/corbell.

Files · 1

View on GitHub

README.md

1	<div align="center">
2	<img src="assets/logo.png" width="300" alt="Corbell Logo" />
3	<h1>Corbell</h1>
4	<p><strong>Multi-repo architecture graph, AI-powered spec generation, and architecture review — for backend teams that ship to production.</strong></p>
5	<p>
6	<a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License"/></a>
7	<a href="CONTRIBUTING.md"><img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg" alt="PRs Welcome"/></a>
8	<a href="https://agentseal.org/mcp/corbell"><img src="https://agentseal.org/api/v1/mcp/corbell/badge" alt="AgentSeal MCP"/></a>
9	</p>
10	</div>
11
12	---
13
14	## What problem does this solve?
15
16	You're a staff engineer or architect at a company where features touch 5–10 repositories.<br/>
17	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?"
18
19	The decisions live in Confluence pages nobody reads, Slack messages nobody can find, and the memories of engineers who've since left.
20
21	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.
22
23	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.
24
25	---
26
27	## How it looks
28
29	<p align="center">
30	<img src="assets/corbell_ui.png" width="48%" alt="Corbell UI" />
31	<img src="assets/mermaid_diagram.png" width="48%" alt="Mermaid Diagram" />
32	</p>
33
34	## Star History (thank you)
35	<p align="center">
36	<img src="assets/star_history.png" width="70%" alt="Corbell Star History" />
37	</p>
38
39	## How it works
40
41	```
42	Your repos → [graph:build] → Service graph (SQLite)
43	Your docs → [docs:scan] → Design pattern extraction
44	↓
45	[spec new --feature "Payment Retry" --prd-file prd.md]
46	→ Generates 3-4 PRD-driven code search queries (LLM or regex)
47	→ Auto-discovers relevant services via embedding similarity
48	→ Injects graph topology + real code snippets
49	→ Applies your team's established design patterns
50	→ Calls Claude / GPT-4o to write the full design doc
51	→ Displays token usage and estimated cost
52	→ specs/payment-retry.md ✓
53	↓
54	[spec review] → Checks claims against graph → .review.md
55	[spec decompose] → Parallel task tracks YAML
56	[export linear] → Linear issues with full method/service context
57	[export jira] → Jira issues via REST API v3 (reads from workspace.yaml)
58	```
59
60	No servers. No cloud setup. Runs entirely from your laptop against local repos.
61
62	---
63
64	## Installation
65
66	```bash
67	pip install corbell
68
69	# With LLM support (pick one):
70	pip install "corbell[anthropic]" # Claude (recommended)
71	pip install "corbell[openai]" # GPT-4o
72
73	# With exports:
74	pip install "corbell[notion,linear,jira]"
75
76	# Everything:
77	pip install "corbell[anthropic,openai,notion,linear,jira]"
78	```
79
80	Requirements: Python ≥ 3.11
81
82	---
83
84	## 🚀 Quick Setup (2 minutes)
85
86	### Prerequisites
87	- Python 3.8+ or Node.js 16+ or Go 1.19+ (based on your project)
88	- Git repository with source code
89
90	### Essential Steps
91
92	1. Initialize Corbell workspace
93	```bash
94	corbell init
95	```
96	✅ Creates `workspace.yaml` in your project root
97
98	2. Generate your first design document
99	```bash
100	corbell spec new --prd "Add user authentication feature"
101	```
102	✅ Creates design document with auto-discovered services
103
104	3. View architecture graph (optional)
105	```bash
106	corbell ui serve
107	```
108	✅ Opens browser at http://localhost:7433
109
110	### Verify Setup
111	- [ ] `workspace.yaml` e

6 picks

Type

corbell

How to install corbell?

Related

corbell

How to install corbell?

Related