zypher-agent  by corespeed-io

Production-ready AI agents for application integration

Created 10 months ago
915 stars

Top 39.8% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

Zypher Agent provides a production-ready framework for embedding reactive AI agents directly within applications, moving beyond simple workflow automation. It empowers developers to build dynamic AI functionalities that can reason, adapt, and manage their own state through features like Git-based versioning and an extensible tool system. The agent supports multiple LLM providers and integrates with the Model Context Protocol, offering a flexible and robust solution for complex AI-driven application features.

How It Works

The core of Zypher Agent is its reactive loop, enabling agents to dynamically decide subsequent actions based on LLM reasoning, rather than following predefined workflows. This approach is complemented by Git-based checkpoints, which allow for the tracking, review, and reversion of agent states, akin to code version control. Its extensible tool system includes built-in utilities for file operations, search, and terminal commands, with clear support for custom tool integration. Furthermore, the agent offers native support for Model Context Protocol (MCP) servers, including OAuth authentication, and abstracts away differences between multiple LLM providers like Anthropic Claude and OpenAI GPT through a unified interface.

Quick Start & Requirements

  • Primary install: deno add jsr:@corespeed/zypher (npm support is planned).
  • Prerequisites: Requires API keys for supported LLM providers (e.g., Anthropic, OpenAI) and a Deno runtime environment.
  • Links: Official documentation and API reference are available for detailed usage examples.

Highlighted Details

  • Git-Based Checkpoints: Enables robust state management by tracking, reviewing, and reverting agent changes, offering a powerful audit trail.
  • Model Context Protocol (MCP): Native integration with MCP servers, including OAuth authentication, facilitates standardized context exchange.
  • Multi-Provider Support: Seamlessly works with Anthropic Claude and OpenAI GPT models through a unified interface, simplifying model selection.
  • Production Readiness: Features configurable timeouts, concurrency protection, and comprehensive error handling for reliable deployment in application environments.

Maintenance & Community

No specific details regarding contributors, sponsorships, or community channels (like Discord/Slack) were found in the provided README content.

Licensing & Compatibility

  • License: Apache License, Version 2.0.
  • Compatibility: The Apache 2.0 license is generally permissive for commercial use and integration into closed-source projects, though users should consult the full license text.

Limitations & Caveats

  • The primary installation method targets the Deno runtime; official npm package support is noted as "coming soon."
  • Requires users to manage and provide API keys for the chosen LLM providers.
Health Check
Last Commit

2 days ago

Responsiveness

Inactive

Pull Requests (30d)
17
Issues (30d)
0
Star History
125 stars in the last 30 days

Explore Similar Projects

Starred by Elie Bursztein Elie Bursztein(Cybersecurity Lead at Google DeepMind), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
7 more.

SuperAGI by TransformerOptimus

0.2%
17k
Open-source framework for autonomous AI agent development
Created 2 years ago
Updated 11 months ago
Feedback? Help us improve.