@corbat-tech/coco 1.3.0 β†’ 1.5.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (6) hide show
  1. package/README.md +176 -201
  2. package/README.old.md +310 -0
  3. package/dist/cli/index.js +1441 -1024
  4. package/dist/cli/index.js.map +1 -1
  5. package/dist/index.js.map +1 -1
  6. package/package.json +1 -1
package/README.md CHANGED
@@ -1,200 +1,181 @@
1
- <p align="center">
2
- <img src="https://img.shields.io/badge/v1.2.3-stable-blueviolet?style=for-the-badge" alt="Version">
3
- <img src="https://img.shields.io/badge/TypeScript-5.7-3178c6?style=for-the-badge&logo=typescript&logoColor=white" alt="TypeScript">
4
- <img src="https://img.shields.io/badge/Node.js-22+-339933?style=for-the-badge&logo=nodedotjs&logoColor=white" alt="Node.js">
5
- <img src="https://img.shields.io/badge/License-MIT-f5c542?style=for-the-badge" alt="MIT License">
6
- <img src="https://img.shields.io/badge/Tests-4350%2B_passing-22c55e?style=for-the-badge" alt="Tests">
7
- </p>
1
+ <div align="center">
8
2
 
9
- <h1 align="center">πŸ₯₯ Corbat-Coco</h1>
3
+ # πŸ₯₯ Coco
10
4
 
11
- <p align="center">
12
- <strong>The open-source coding agent that iterates on your code until it's actually production-ready.</strong>
13
- </p>
5
+ **The AI coding agent that actually delivers production-ready code**
14
6
 
15
- <p align="center">
16
- <em>Generate β†’ Test β†’ Measure β†’ Fix β†’ Repeat β€” autonomously.</em>
17
- </p>
7
+ [Features](#-features) β€’
8
+ [Quick Start](#-quick-start) β€’
9
+ [How It Works](#-how-it-works) β€’
10
+ [Commands](#-commands) β€’
11
+ [Documentation](#-documentation)
18
12
 
19
- ---
13
+ [![NPM Version](https://img.shields.io/npm/v/@corbat-tech/coco?style=flat-square&color=blueviolet)](https://www.npmjs.com/package/@corbat-tech/coco)
14
+ [![License](https://img.shields.io/badge/license-MIT-f5c542?style=flat-square)](LICENSE)
15
+ [![TypeScript](https://img.shields.io/badge/TypeScript-5.7-3178c6?style=flat-square&logo=typescript&logoColor=white)](https://www.typescriptlang.org/)
16
+ [![Node](https://img.shields.io/badge/Node.js-22+-339933?style=flat-square&logo=nodedotjs&logoColor=white)](https://nodejs.org/)
17
+ [![Tests](https://img.shields.io/badge/tests-4350%2B-22c55e?style=flat-square)](https://github.com/corbat/corbat-coco/actions)
20
18
 
21
- ## Why Coco?
19
+ </div>
22
20
 
23
- Most AI coding tools generate code and hand it to you. If something breaks β€” tests fail, types don't match, a security issue slips in β€” that's your problem.
21
+ ---
24
22
 
25
- Coco takes a different approach. After generating code, it **runs your tests, measures quality across 12 dimensions, diagnoses what's wrong, and fixes it** β€” in a loop, autonomously β€” until the code actually meets a quality bar you define.
23
+ ## The Problem
26
24
 
27
- ```
28
- β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
29
- β”‚ Generate β”‚ ──► β”‚ Test β”‚ ──► β”‚ Measure β”‚ ──► β”‚ Fix β”‚
30
- β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
31
- β”‚
32
- Score < 85? β”‚ ──► Loop back
33
- Score β‰₯ 85? β”‚ ──► Done βœ…
34
- ```
25
+ Most AI coding tools generate code and walk away. If tests fail, types don't match, or security issues creep in β€” **that's on you**.
35
26
 
36
- This is the **Quality Convergence Loop** β€” Coco's core differentiator.
27
+ ## The Solution
37
28
 
38
- ---
39
-
40
- ## Quick Start
29
+ **Coco doesn't just generate code. It iterates until it's right.**
41
30
 
42
- ```bash
43
- npm install -g @corbat-tech/coco
44
- coco # Opens interactive REPL β€” guided setup on first run
45
- ```
31
+ After writing code, Coco automatically:
32
+ - βœ… Runs your tests
33
+ - πŸ“Š Measures quality across 12 dimensions
34
+ - πŸ” Diagnoses what's wrong
35
+ - πŸ”§ Fixes issues and repeats
46
36
 
47
- That's it. Coco walks you through provider configuration on first launch.
37
+ **Until your code hits production-quality standards you define.**
48
38
 
49
- ```bash
50
- # Or use it directly:
51
- coco "Add a REST API endpoint for user authentication with tests"
39
+ ```
40
+ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
41
+ β”‚ Generate β”‚ ──► β”‚ Test β”‚ ──► β”‚ Measure β”‚ ──► β”‚ Fix β”‚
42
+ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
43
+ β”‚
44
+ Score < 85? β”‚ ──► Loop
45
+ Score β‰₯ 85? β”‚ ──► Done βœ…
52
46
  ```
53
47
 
54
48
  ---
55
49
 
56
- ## What You Can Do
50
+ ## ✨ Features
57
51
 
58
- Coco works from the interactive REPL (`coco`). You can use **slash commands** or just **talk naturally** β€” Coco understands both.
52
+ ### πŸ”„ **Quality Convergence Loop** (COCO Mode)
59
53
 
60
- ### Slash Commands
61
-
62
- | Command | What it does | Example |
63
- |---------|-------------|---------|
64
- | `/help` | Show available commands and usage | `/help review` |
65
- | `/status` | Project status, git info, session stats | `/status` |
66
- | `/review` | Code review with severity-rated findings | `/review --base main` |
67
- | `/diff` | Visual diff with syntax highlighting | `/diff --staged` |
68
- | `/ship` | Full release pipeline: review β†’ test β†’ lint β†’ branch β†’ version β†’ commit β†’ PR β†’ CI β†’ merge | `/ship --minor` |
69
- | `/compact` | Reduce context when conversation gets long | `/compact` |
70
- | `/clear` | Clear conversation history | `/clear` |
54
+ Not just code generation β€” **iterative quality improvement**:
71
55
 
72
- ### Natural Language
56
+ | Iteration | Score | Status |
57
+ |:---------:|:-----:|--------|
58
+ | **1** | 52 | Code generated β€” 3 tests failing, no error handling |
59
+ | **2** | 71 | Tests fixed, security vulnerability found |
60
+ | **3** | 84 | Security patched, coverage 82% |
61
+ | **4** | **91** | βœ… **All green β€” quality converged** |
73
62
 
74
- You don't need to memorize commands. Just describe what you want:
63
+ > Enable with `/coco` β€” now **on by default** for better results
75
64
 
76
- | What you say | What happens |
77
- |-------------|-------------|
78
- | "review the code" / "revisa el cΓ³digo" | Runs `/review` |
79
- | "let's ship it" / "publica los cambios" | Runs `/ship` |
80
- | "how are we doing?" / "cΓ³mo va?" | Runs `/status` |
81
- | "create a PR" / "crea un pull request" | Runs `/ship` |
82
- | "show me the diff" / "muΓ©strame los cambios" | Runs `/diff` |
83
- | "help" / "ayuda" | Runs `/help` |
65
+ ### πŸ“Š **12-Dimension Quality Scoring**
84
66
 
85
- ### `/ship` β€” Release Pipeline
67
+ Real metrics, not guesses:
86
68
 
87
- The most powerful command. Orchestrates the entire release flow in one step:
69
+ | Dimension | How It's Measured |
70
+ |-----------|-------------------|
71
+ | Test Coverage | c8/v8 instrumentation |
72
+ | Security | Pattern matching + optional Snyk |
73
+ | Complexity | Cyclomatic complexity (AST) |
74
+ | Duplication | Line-based similarity |
75
+ | Correctness | Test pass rate + build verification |
76
+ | Style | oxlint / eslint / biome |
77
+ | Documentation | JSDoc coverage |
78
+ | + 5 more | Readability, Maintainability, Test Quality, Completeness, Robustness |
88
79
 
89
- ```
90
- /ship # Full pipeline (10 steps)
91
- /ship --skip-tests # Skip test step
92
- /ship --draft # Create draft PR
93
- /ship --patch # Force patch version bump
94
- /ship --minor # Force minor version bump
95
- /ship --major # Force major version bump
96
- /ship --no-version # Skip version bumping
97
- /ship -m "feat: add auth" # Pre-set commit message
98
- ```
80
+ ### πŸš€ **Full Release Pipeline**
99
81
 
100
- Pipeline: **Preflight β†’ Review β†’ Tests β†’ Lint β†’ Branch β†’ Version β†’ Commit β†’ PR β†’ CI β†’ Merge & Release**
82
+ Ship with confidence using `/ship`:
101
83
 
102
- Each step is interactive β€” Coco asks before proceeding when decisions are needed. Press `Ctrl+C` at any point to cancel safely.
84
+ ```bash
85
+ /ship # Complete 10-step pipeline
86
+ ```
103
87
 
104
- ---
88
+ **Pipeline:** Preflight β†’ Review β†’ Tests β†’ Lint β†’ Branch β†’ Version β†’ Commit β†’ PR β†’ CI β†’ Merge
105
89
 
106
- ## What Coco Does Well
90
+ Each step is interactive β€” press `Ctrl+C` anytime to safely cancel.
107
91
 
108
- ### Quality Convergence Loop
92
+ ### πŸ€– **Multi-Agent Architecture**
109
93
 
110
- Coco doesn't just generate code β€” it iterates until quality converges:
94
+ Six specialized agents with automatic routing:
111
95
 
112
- | Iteration | Score | What happened |
113
- |:---------:|:-----:|---------------|
114
- | 1 | 52 | Code generated β€” 3 tests failing, no error handling |
115
- | 2 | 71 | Tests fixed, security vulnerability found |
116
- | 3 | 84 | Security patched, coverage improved to 82% |
117
- | 4 | 91 | All green β€” quality converged βœ… |
96
+ - **Researcher** β€” Codebase exploration and analysis
97
+ - **Coder** β€” Code implementation (default)
98
+ - **Tester** β€” Test generation and coverage
99
+ - **Reviewer** β€” Quality auditing and code review
100
+ - **Optimizer** β€” Refactoring and performance
101
+ - **Planner** β€” Architecture and task decomposition
118
102
 
119
- The quality bar is yours to set:
103
+ ### 🌐 **Multi-Provider Support**
120
104
 
121
- ```bash
122
- coco build --min-quality 90 # Per-run override
123
- coco config set quality.minScore 90 # Persist in project config
124
- ```
105
+ Bring your own API key:
125
106
 
126
- Default is **85** (senior-level). You can also configure max iterations, convergence threshold, coverage targets, and security requirements β€” see `coco config init`.
107
+ | Provider | Auth | Models |
108
+ |----------|------|--------|
109
+ | **Anthropic** | API key / OAuth | Claude Opus, Sonnet, Haiku |
110
+ | **OpenAI** | API key | GPT-5.3 Codex, GPT-4.1, o4-mini |
111
+ | **Google** | API key / gcloud | Gemini 3, 2.5 Pro/Flash |
112
+ | **Ollama** | Local | Any local model |
113
+ | **LM Studio** | Local | Any GGUF model |
114
+ | **Moonshot** | API key | Kimi models |
127
115
 
128
- ### 12-Dimension Quality Scoring
116
+ ### ⚑ **Modern Terminal UX**
129
117
 
130
- Every iteration measures your code across 12 dimensions using real static analysis:
118
+ - **Ghost-text completion** β€” Tab to accept suggestions
119
+ - **Image paste** β€” `Ctrl+V` to paste screenshots
120
+ - **Intent recognition** β€” Natural language β†’ commands
121
+ - **Full-access mode** β€” `/full-access` for auto-approvals (with safety guards)
122
+ - **Self-update** β€” Type "update coco" anytime
131
123
 
132
- | Dimension | How it's measured |
133
- |-----------|-------------------|
134
- | Test Coverage | c8/v8 instrumentation |
135
- | Security | Pattern matching + optional Snyk |
136
- | Complexity | Cyclomatic complexity via AST parsing |
137
- | Duplication | Line-based similarity detection |
138
- | Correctness | Test pass rate + build verification |
139
- | Style | oxlint / eslint / biome integration |
140
- | Documentation | JSDoc coverage analysis |
141
- | Readability | AST: naming quality, function length, nesting |
142
- | Maintainability | AST: file size, coupling, function count |
143
- | Test Quality | Assertion density, edge case coverage |
144
- | Completeness | Export density + test file coverage |
145
- | Robustness | Error handling pattern detection |
124
+ ---
146
125
 
147
- > **Transparency note**: 7 dimensions use instrumented measurements. 5 use heuristic-based static analysis. We label which is which β€” no black boxes.
126
+ ## πŸš€ Quick Start
148
127
 
149
- ### Multi-Provider Support
128
+ ```bash
129
+ # Install globally
130
+ npm install -g @corbat-tech/coco
150
131
 
151
- Bring your own API keys. Coco works with:
132
+ # Start interactive mode
133
+ coco
152
134
 
153
- | Provider | Auth | Models |
154
- |----------|------|--------|
155
- | **Anthropic** | API key / OAuth PKCE | Claude Opus, Sonnet, Haiku |
156
- | **OpenAI** | API key | GPT-5.3 Codex, GPT-4.1, o4-mini |
157
- | **Google** | API key / gcloud ADC | Gemini 3, 2.5 Pro/Flash |
158
- | **Ollama** | Local | Any local model (8-24GB RAM) |
159
- | **LM Studio** | Local | Any GGUF model (8-32GB RAM) |
160
- | **Moonshot** | API key | Kimi models |
135
+ # Or use directly
136
+ coco "Add user authentication with tests"
137
+ ```
161
138
 
162
- ### Multi-Agent Architecture
139
+ That's it. Coco walks you through provider setup on first launch.
163
140
 
164
- Six specialized agents with weighted-scoring routing:
141
+ ---
165
142
 
166
- - **Researcher** β€” Explores, analyzes, maps the codebase
167
- - **Coder** β€” Writes and edits code (default route)
168
- - **Tester** β€” Generates tests, improves coverage
169
- - **Reviewer** β€” Code review, quality auditing
170
- - **Optimizer** β€” Refactoring and performance
171
- - **Planner** β€” Architecture design, task decomposition
143
+ ## πŸ’¬ Commands
172
144
 
173
- Coco picks the right agent for each task automatically. When confidence is low, it defaults to the coder β€” no guessing games.
145
+ ### Slash Commands
174
146
 
175
- ### Interactive REPL
147
+ | Command | What it does |
148
+ |---------|-------------|
149
+ | `/help` | Show available commands |
150
+ | `/status` | Project status, git info, session stats |
151
+ | `/review` | Code review with severity-rated findings |
152
+ | `/diff` | Visual diff with syntax highlighting |
153
+ | `/ship` | Full release pipeline (review β†’ test β†’ PR β†’ merge) |
154
+ | `/coco [on\|off]` | Toggle quality mode (default: ON) |
155
+ | `/full-access [on\|off]` | Auto-approve safe commands |
156
+ | `/compact` | Reduce context when conversation grows |
157
+ | `/clear` | Clear conversation history |
176
158
 
177
- A terminal-first experience with:
159
+ ### Natural Language
178
160
 
179
- - **Ghost-text completion** β€” Tab to accept inline suggestions
180
- - **Slash commands** β€” `/ship`, `/review`, `/diff`, `/status`, `/help`, `/compact`, `/clear`
181
- - **Image paste** β€” `Ctrl+V` to paste screenshots for visual context
182
- - **Intent recognition** β€” Natural language mapped to commands
183
- - **Context management** β€” Automatic compaction when context grows large
161
+ You don't need slash commands. Just talk:
184
162
 
185
- ### Production Hardening
163
+ | You say | Coco does |
164
+ |---------|-----------|
165
+ | "review the code" | Runs `/review` |
166
+ | "let's ship it" | Runs `/ship` |
167
+ | "show me the changes" | Runs `/diff` |
168
+ | **"update coco"** | **Runs `/update-coco`** |
186
169
 
187
- - **Error recovery** with typed error strategies and exponential backoff
188
- - **Checkpoint/Resume** β€” `Ctrl+C` saves state, `coco resume` picks up where you left off
189
- - **AST validation** β€” Syntax-checks generated code before saving
190
- - **Convergence analysis** β€” Detects oscillation, diminishing returns, and stuck patterns
191
- - **Path sandboxing** β€” Tools can only access files within the project
170
+ Bilingual support (English/Spanish).
192
171
 
193
172
  ---
194
173
 
195
- ## COCO Methodology
174
+ ## 🎯 How It Works
196
175
 
197
- Four phases, each with a dedicated executor:
176
+ ### COCO Methodology
177
+
178
+ Four phases for production-ready output:
198
179
 
199
180
  ```
200
181
  CONVERGE ORCHESTRATE COMPLETE OUTPUT
@@ -210,101 +191,95 @@ Four phases, each with a dedicated executor:
210
191
  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
211
192
  ```
212
193
 
213
- 1. **Converge** β€” Understand what needs to be built. Gather requirements, produce a spec.
214
- 2. **Orchestrate** β€” Design the architecture, decompose into a task backlog.
215
- 3. **Complete** β€” Execute each task with the quality convergence loop.
216
- 4. **Output** β€” Generate CI/CD pipelines, documentation, and deployment config.
194
+ 1. **Converge** β€” Understand requirements
195
+ 2. **Orchestrate** β€” Design architecture
196
+ 3. **Complete** β€” Build with quality iteration
197
+ 4. **Output** β€” Generate deployment config
217
198
 
218
199
  ---
219
200
 
220
- ## Use Cases
221
-
222
- Coco is designed for developers who want AI assistance with **accountability**:
201
+ ## πŸ“– Documentation
223
202
 
224
- - **Feature development** β€” Describe what you want, get tested and reviewed code
225
- - **Vibe coding** β€” Explore ideas interactively; Coco handles the quality checks
226
- - **Refactoring** β€” Point at code and say "make this better" β€” Coco iterates until metrics improve
227
- - **Test generation** β€” Improve coverage with meaningful tests, not boilerplate
228
- - **Code review** β€” Get multi-dimensional quality feedback on existing code
229
- - **Learning** β€” See how code quality improves across iterations
203
+ - [Configuration Guide](docs/guides/CONFIGURATION.md)
204
+ - [Quick Start Tutorial](docs/guides/QUICK_START.md)
205
+ - [Troubleshooting](docs/guides/TROUBLESHOOTING.md)
206
+ - [API Reference](docs/API.md)
207
+ - [MCP Integration](docs/MCP.md)
230
208
 
231
209
  ---
232
210
 
233
- ## Development
211
+ ## πŸ§‘β€πŸ’» Development
234
212
 
235
213
  ```bash
236
214
  git clone https://github.com/corbat/corbat-coco
237
215
  cd corbat-coco
238
216
  pnpm install
239
- pnpm dev # Run in dev mode (tsx)
240
- pnpm test # 4,350+ tests via Vitest
241
- pnpm check # typecheck + lint + test
242
- pnpm build # Production build (tsup)
217
+ pnpm dev # Run in dev mode
218
+ pnpm test # 4,350+ tests
219
+ pnpm check # Typecheck + lint + test
243
220
  ```
244
221
 
245
222
  ### Project Structure
246
223
 
247
224
  ```
248
225
  src/
249
- β”œβ”€β”€ agents/ # Multi-agent coordination + weighted routing
250
- β”œβ”€β”€ cli/ # REPL, commands, input handling, output rendering
251
- β”œβ”€β”€ orchestrator/ # Phase coordinator + state recovery
252
- β”œβ”€β”€ phases/ # COCO phases (converge/orchestrate/complete/output)
253
- β”œβ”€β”€ quality/ # 12 quality analyzers + convergence engine
254
- β”œβ”€β”€ providers/ # 7 LLM providers + OAuth flows
255
- β”œβ”€β”€ tools/ # 20+ tool implementations
256
- β”œβ”€β”€ hooks/ # Lifecycle hooks (safety, lint, format, audit)
257
- β”œβ”€β”€ mcp/ # MCP server for external integration
258
- └── config/ # Zod-validated configuration system
226
+ β”œβ”€β”€ agents/ # Multi-agent coordination
227
+ β”œβ”€β”€ cli/ # REPL + commands
228
+ β”œβ”€β”€ phases/ # COCO phases
229
+ β”œβ”€β”€ quality/ # 12-dimension scoring
230
+ β”œβ”€β”€ providers/ # LLM provider integrations
231
+ └── tools/ # File ops, git, tests, etc.
259
232
  ```
260
233
 
261
- ### Technology Stack
234
+ **Stack:** TypeScript + Node.js 22 + Vitest + oxlint/oxfmt + Zod
262
235
 
263
- | Component | Technology |
264
- |-----------|-----------|
265
- | Language | TypeScript (ESM, strict mode) |
266
- | Runtime | Node.js 22+ |
267
- | Testing | Vitest (4,350+ tests) |
268
- | Linting | oxlint |
269
- | Formatting | oxfmt |
270
- | Build | tsup |
271
- | Schema validation | Zod |
236
+ ---
237
+
238
+ ## πŸŽ“ Use Cases
239
+
240
+ - **Feature development** β€” Get tested, reviewed code
241
+ - **Refactoring** β€” Improve quality with measurable progress
242
+ - **Test generation** β€” Meaningful tests, not boilerplate
243
+ - **Code review** β€” 12-dimensional quality feedback
244
+ - **Learning** β€” See how quality improves across iterations
272
245
 
273
246
  ---
274
247
 
275
- ## Known Limitations
248
+ ## ⚠️ Known Limitations
276
249
 
277
250
  We'd rather you know upfront:
278
251
 
279
- - **TypeScript/JavaScript first** β€” Other languages have basic support but fewer analyzers
280
- - **CLI-only** β€” No IDE extension yet (VS Code integration is planned)
281
- - **Iteration takes time** β€” The convergence loop adds 2-5 minutes per task. For quick one-line fixes, a simpler tool may be faster
282
- - **Heuristic analyzers** β€” 5 of 12 quality dimensions use pattern-based heuristics, not deep semantic analysis
283
- - **LLM-dependent** β€” Output quality depends on the model you connect. Larger models produce better results
284
- - **Early stage** β€” Actively developed. Not yet battle-tested at large enterprise scale
252
+ - **TypeScript/JavaScript first** β€” Other languages have basic support
253
+ - **CLI-only** β€” No IDE extension yet (VS Code planned)
254
+ - **Iteration takes time** β€” Convergence adds 2-5 min per task
255
+ - **LLM-dependent** β€” Quality depends on your model choice
256
+ - **Early stage** β€” Not yet battle-tested at enterprise scale
285
257
 
286
258
  ---
287
259
 
288
- ## Contributing
260
+ ## 🀝 Contributing
261
+
262
+ Contributions welcome:
289
263
 
290
- We welcome contributions of all kinds:
264
+ - πŸ› Bug reports and feature requests
265
+ - πŸ”¬ New quality analyzers
266
+ - πŸ”Œ Additional LLM providers
267
+ - πŸ“š Documentation and examples
268
+
269
+ See [CONTRIBUTING.md](./CONTRIBUTING.md).
270
+
271
+ ---
291
272
 
292
- - Bug reports and feature requests
293
- - New quality analyzers
294
- - Additional LLM provider integrations
295
- - Documentation and examples
296
- - Real-world usage feedback
273
+ ## πŸ“„ License
297
274
 
298
- See [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines.
275
+ MIT Β© [Corbat](https://corbat.tech)
299
276
 
300
277
  ---
301
278
 
302
- ## About
279
+ <div align="center">
303
280
 
304
- Corbat-Coco is built by [Corbat](https://corbat.tech), a technology consultancy that believes AI coding tools should be transparent, measurable, and open source.
281
+ **Built by developers who measure before they ship** πŸ₯₯
305
282
 
306
- <p align="center">
307
- <a href="https://github.com/corbat/corbat-coco">GitHub</a> Β· <a href="https://corbat.tech">corbat.tech</a>
308
- </p>
283
+ [GitHub](https://github.com/corbat/corbat-coco) Β· [corbat.tech](https://corbat.tech) Β· [npm](https://www.npmjs.com/package/@corbat-tech/coco)
309
284
 
310
- <p align="center"><strong>MIT License</strong> Β· Made by developers who measure before they ship. πŸ₯₯</p>
285
+ </div>