Skip to content

desonet/typescript-agent-framework

 
 

Repository files navigation

🌐 Null Shot - Typescript Agent Framework

Building the future of AI Agent Interoperability

Pre-Alpha: This project is in active development.

Discord License: MIT

Welcome to a new paradigm in AI development. MCP provides the foundation for building intelligent, interoperable agents that can communicate, evolve, and generate value at the edge of the network.

Vision

We're extending Cloudflare's vision for AI Agents with a focus on web3 and MCPs as plugins:

  • 🤝 AI Agents as teammates/organizations generating revenue and performing advanced operations
  • 💰 Cost-effective shared hosting options
  • 🔒 Secure sensitive assets (trading agents, treasuries, etc.)
  • 📈 Self-improving agents based on collective usage
  • 💸 Drive MCP usage revenue to open source contributors
  • 💼 Monetization avenues for closed-source MCP use cases
  • ⚙️ Seamless configuration options
  • 🚀 Quick iteration on ideas locally and in-cloud
  • 🔓 No vendor lock-in, self-hosting and personal account options

Project Status

This project is in pre-alpha and actively evolving. Current focus areas:

Ready for Use

  • ✅ Core MCP Framework
  • ✅ Multi Session & Authentication Patterns
  • ✅ Official MCP WebSocket Support and HTTP Streaming Support
  • ✅ Agent Framework (AI SDK)
  • ✅ Seamless MCP Plugins (mcp.json) for Agents = ✅ Playground UI for LLMs + MCPs

In Development

  • ☁️ Cloudflare Service Examples (KV, D1, DO state, Analytics, Workflows, Schema Migrations)
  • 🤖 LangChain and Agent SDK examples coming soon
  • 📄 Cloudflare Pages (SSE / Fullstack) Examples
  • 🔑 Authentication (OAuth, JWT)

Quick Start

🚧 Coming Soon! We're working hard to provide a seamless getting started experience.

Documentation

📚 Coming Soon! Comprehensive documentation and guides are under development.

Release Process

This repository uses an automated release workflow following semantic versioning:

  1. Pull Request Testing - When you create a PR, it automatically runs tests and a semantic-release dry run
  2. Automated Publishing - When merged to main, changed packages are automatically published to npm
  3. Versioning - Package versions are determined by Conventional Commits standards

For detailed information about our release process, see .github/RELEASE_PROCESS.md.

Contributing

We welcome contributions! Our vision is to create a collaborative ecosystem where AI and human developers work together. Soon, we'll have an AI agent to audit and govern contributions based on our shared vision.

If you're interested in contributing, please:

  1. Join our Discord community
  2. Watch this repository for updates
  3. Star the project if you find it interesting

License

MIT License - see the LICENSE file for details.


Built with ❤️ by the Xava DAO Community

About

Null Shot's Typescript Vibework (Framework) for Serverless AI Agents

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • TypeScript 89.4%
  • CSS 4.8%
  • JavaScript 3.8%
  • Shell 2.0%