Boring: An AI-powered development support tool for autonomous reasoning, planning, and verification. Optimized for uv and agentic workflows.
Project description
Boring for Gemini
Autonomous AI Agent Loop with VibeCoder Experience
✨ The Vibe Coder Experience
No Code Needed. Just describe the vibe.
Boring-Gemini features a Universal Natural Language Router. You don't need to remember 98+ complex tools. Just say what you want:
"Search for authentication logic"
"Review my code for security issues"
"幫我寫測試" (Help me write tests)
🚀 Quick Start (One-Click)
🪄 Zero-Config Wizard
Boring features a smart setup wizard that automatically bridges your IDE (Cursor, VS Code, Claude Desktop) with the Gemini agent.
pip install "boring-aicoding[all]"
boring wizard
💎 Smithery Integration
One-click install for Cursor/Claude Desktop.
npx -y @smithery/cli@latest install boring/boring --client cursor
🧐 Cognitive Evolution (Pillar V)
V11.2.2 transforms Boring from a simple loop into a Self-Improving Intelligence System:
- 🧘♀️ Deep & Critical Thinking: Decomposes complex problems using multi-layered reasoning states (System 2).
- ⚡ Brain Reflex (Active Recall): Instantly recalls past debug patterns. No more "searching"—it remembers how you fixed that
AttributeErrorlast time. - 🏆 Skill Compilation: High-frequency successful patterns are distilled into Strategic Skills, making your local agent uniquely expert in your stack.
- 🛠️ Live Tool Synthesis: The agent can now generate its own tools in Python to solve hyper-specific problems on-the-fly.
- 🌐 Knowledge Swarm: Sync learned patterns across your team via Git-based synchronization.
⚡ Core Capabilities
| Feature | Description |
|---|---|
| 🧠 Autonomous Loop | Runs continuously: thinking → coding → testing → fixing. |
| 🕵️ Context Optimization | 80% token savings via smart chunking and specificity ranking. |
| 🛡️ Shadow Mode | Safe execution sandbox catches destructive operations before they happen. |
| 🧩 Natural Language | Universal Router: "幫我寫測試" or "Fix auth bugs" triggered instantly. |
| 🧪 Vibe Score | Gamified health check: Lint, Security, and Docs tracked over time. |
📦 Usage Modes
As MCP Server (Recommended for IDEs)
{
"mcpServers": {
"boring": { "command": "boring-mcp" }
}
}
Managed CLI Utilities
boring-monitor: Fullscreen TUI dashboard for live agent monitoring.boring-dashboard: Modern web UI for project health and history.boring-setup: Scaffold new Boring-ready projects in seconds.
About boring-route: This command only shows which MCP tool would be selected for your query. To actually execute the tool, use it in your MCP client (Cursor/Claude Desktop).
🔧 Key Features
- 55+ MCP Tools: RAG, Testing, Review, Security, Git, and more
- Multi-Language: Python, JavaScript, TypeScript support
- Quality Gates: CI/CD integration with multi-tier verification
- Memory System: Persistent learning and pattern recognition
- LLM-as-a-Judge: Advanced evaluation with bias monitoring
📚 Documentation
📄 License
Apache 2.0 - See LICENSE
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file boring_aicoding-11.2.11.tar.gz.
File metadata
- Download URL: boring_aicoding-11.2.11.tar.gz
- Upload date:
- Size: 492.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bd98d01e0fbf44d74208c8ce9ca42ee44a0d97460139590e34e4740c341a16b8
|
|
| MD5 |
c7cb47238eca8f73b1145466b8ba6ff1
|
|
| BLAKE2b-256 |
e66b33a6a28079cd22c497f00a0bba9e2f6d062c67a44a0225eeeefaadc417e6
|
File details
Details for the file boring_aicoding-11.2.11-py3-none-any.whl.
File metadata
- Download URL: boring_aicoding-11.2.11-py3-none-any.whl
- Upload date:
- Size: 577.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0001a9e4f60748e269aeec25f866300fe4927d7da5e53787b3f82d750bfe3a78
|
|
| MD5 |
935242868c515ba22487023066d9304f
|
|
| BLAKE2b-256 |
8932297dadd8cf3ebe849d691adfe709dfd6098981f98c61795f035f02e6e65e
|