Return to Articles

GoFannon: Stop Rewriting AI Tools for Every Framework

Gofannon AI Alliance Project

The Problem: Framework Lock-In Wastes Time

If you’ve built and migrated AI agents, you’ve done this before:

  1. Write a tool for LangChain (e.g., a weather lookup).
  2. Switch to AWS Bedrock—now rewrite it.
  3. Try SmolAgents? Yep, rewrite it again.

This is inefficient. Most AI frameworks use similar underlying specs (like OpenAI’s function calling), but each has its own quirks. GoFannon fixes this by letting you write a tool once and export it to any framework.

 

How GoFannon Works

1. Standardized Tool Definitions

Every GoFannon tool inherits from BaseTool and defines:

  • A definition (following OpenAI’s standards) for inputs/outputs.
  • A fn() method with your core logic.

Example from the on of our example notebooks.


2. One-Line Framework Exports

Convert any tool to your framework of choice:


No rewrites. No boilerplate.

3. Pre-Built Tools

Gofannon includes production-ready tools, like:

  • Wikipedia search
  • Basic math operations

 

Why Developers Are Switching

✅ No More Duplicate Work

✅ Modular Install
Only install what you need:


✅ Easy to Extend
Adding a new tool or framework? We have curated guides.

 

How to Contribute (We Made It Simple)

GoFannon is built for open-source collaboration:

  1. Curated Developer Pathways
  2. Maintained list of ‘Good First Issue’ (Beginner)
  3. Documented path for creating and contributing tools (Intermediate)
  4. Documented path for creating and contributing new agentic frameworks
  5. Gamified Leaderboard
  6. PRs earn points (e.g., +500 for a new tool, +25 for a framework).
  7. Transparent Process
  8. ASFv2 

Try It Now

Explore the docs:

Final Thought

AI frameworks will keep changing. Your tools shouldn’t have to.

Gofannon is by developers, for developers—no hype, just less redundant code.

Star the repo → Try it → Send a PR. Let’s fix this problem together. 🚀


Related Articles

View All

Building AI Agents to Real-World Use Cases

The AI Alliance's open-source projects, AgentLabUI (a practitioner workbench for building AI agents) and Gofannon (a set of agent tools) work together with ATA Systems' front-end development to create production-ready AI applications in days rather than weeks. The approach is demonstrated through a collaborative Grant Matching Agent case study, where researchers can upload their CV and receive curated funding opportunities within minutes, showcasing a complete workflow from agent development to end-user delivery. AgentLabUI serves as a flexible IDE where practitioners can swap models, build modular tools, and integrate various frameworks, while the Agent UI provides a simple interface for non-technical users to interact with deployed agents without needing to understand the underlying complexity. This two-layer system bridges the gap between AI R&D and real-world adoption, making advanced AI capabilities accessible, secure, and practical across organizations.

Building a Deep Research Agent Using MCP-Agent

This article by Sarmad Qadri documents the journey of building a Deep Research Agent with MCP-Agent, highlighting the evolution from an initial Orchestrator design, to an over-engineered Adaptive Workflow, and finally to the streamlined Deep Orchestrator. The author emphasizes that “MCP is all you need,” showing how connecting LLMs to MCP servers with simple design patterns enables agents to perform complex, multi-step research tasks. Key lessons include the importance of simplicity over complexity, leveraging deterministic code-based verification alongside LLM reasoning, external memory for efficiency, and structured prompting for clarity. The resulting Deep Orchestrator balances performance, scalability, and adaptability, proving effective across domains like finance research. Future directions include remote execution, intelligent tool and model selection, and treating memory/knowledge as MCP resources. The open-source project, available on GitHub, offers developers a powerful foundation for creating general-purpose AI research agents.

The AI Alliance releases new AI-powered programming language and industrial AI agent framework, adds new Japanese members, and launches AI Alliance Japan  

The AI Alliance announced three developments: Dana, an AI-powered programming language that generates code from natural language descriptions; OpenDXA, an open-source agent framework for industrial AI applications; and AI Alliance Japan, a regional working group with nine founding members including IBM, NEC, and Panasonic focused on sovereign AI development. Dana introduces intent-driven development where developers describe functionality rather than write traditional code, while OpenDXA targets complex industrial workflows with explainable AI. The Japan initiative will focus on manufacturing, semiconductor, and navigation applications, with their first project supporting LLM-jp, Japan's national language model. All projects are open-source and available through the AI Alliance collaboration.