The AI That Builds Itself: Recursive Claude Spawning via Meta-MCP
Project description
🏭 Context Foundry
The AI That Builds Itself: Recursive Claude Spawning via Meta-MCP Context Foundry uses Claude Code to spawn fresh Claude instances that autonomously build complete projects. Walk away and come back to production-ready software.
Version 2.4.0 - November 2025 🎯 BAML JSON-First Architecture: First-Try Success!
🚀 Quick Start
Get up and running in 2 minutes.
🤔 What is Context Foundry?
Context Foundry is an MCP (Model Context Protocol) server that empowers Claude Code CLI to build complete software projects autonomously with self-healing test loops and automatic GitHub deployment.
Unlike traditional AI coding tools that require constant supervision, Context Foundry lets you describe what you want and walk away while it researches, designs, builds, tests, documents, and deploys your application.
Real Example:
User: "Build a Mario platformer game in JavaScript"
[User walks away for 7 minutes]
Result: ✅ Complete game deployed to GitHub, all tests passing
✨ Key Features
Context Foundry is packed with innovations to make autonomous development reliable and powerful.
- BAML Type-Safe Outputs: Structured JSON outputs for reliable, first-try success.
- Mission Control TUI: A terminal user interface for real-time build monitoring and chat.
- Context Codex: Database-backed self-learning system that remembers patterns and fixes.
- Intelligent Parallel Build: AI automatically decides when to spawn parallel agents for faster builds.
- Self-Healing Test Loop: Automatically fixes test failures without human intervention.
- Meta-MCP Architecture: Recursively spawns fresh Claude instances with full context windows.
🏗️ Architecture
Context Foundry uses a unique Meta-MCP architecture that allows Claude to orchestrate itself.
graph LR
A[Your Claude Session] -->|"Build a weather app"| B[MCP Server]
B -->|Spawns| C[Fresh Claude Instance #1]
C -->|Spawns| D[Fresh Claude Instance #2]
C -->|Spawns| E[Fresh Claude Instance #3]
D -->|100% Complete| C
E -->|100% Complete| C
C -->|✅ Deployed to GitHub| A
👉 Read the Architecture Guide 👉 Explore Innovations
📚 Documentation
- Quick Start: Start here.
- User Guide: Detailed usage instructions.
- Troubleshooting: Common issues and fixes.
- Features: In-depth look at features.
- Architecture: How it works under the hood.
- FAQ: Frequently asked questions.
🤝 Contributing
We welcome contributions! Please see our Contributing Guide for details on how to submit pull requests, report issues, and suggest features.
Project details
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 context_foundry-2.2.1.tar.gz.
File metadata
- Download URL: context_foundry-2.2.1.tar.gz
- Upload date:
- Size: 7.3 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
97e80fa0a5fb08c56d556f865f02d7efa4fd85be4117eaf0006e1f802cc38ec1
|
|
| MD5 |
4aa034bf5913a59f72928a2cfe9df512
|
|
| BLAKE2b-256 |
28d7547c07b475ac7f24bed97d9c63910b1932ca82407cb49599740b779e6ac0
|
File details
Details for the file context_foundry-2.2.1-py3-none-any.whl.
File metadata
- Download URL: context_foundry-2.2.1-py3-none-any.whl
- Upload date:
- Size: 9.4 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2b980b307223069d299f13c8bac36f09d79854e256d74d4472f32ba226ad38be
|
|
| MD5 |
5fe293d802c812e8ad6c7402c0bf55e5
|
|
| BLAKE2b-256 |
d41763d0b9c858b48a72da8a14f7239888d344544671ca676e219197abbf1e99
|