Skip to content

sifatulrabbi/ai-agent-experiments

Repository files navigation

AI Agent Experiments

This repository contains experiments and projects exploring different approaches to building AI Agents or LLM Powered applications.

Projects

An intelligent LLM agent that executes TypeScript code and interacts with external capabilities. This project explores code-based capabilities for LLMs - giving AI agents the ability to write and execute code to accomplish tasks, rather than calling pre-defined tool functions directly.

Key Features:

  • Dynamic TypeScript code execution using Bun
  • Extensible capabilities system with automatic discovery
  • Interactive CLI with streaming responses
  • Built with LangChain, LangGraph, and OpenAI GPT models

OpenAI Models

Experiments with OpenAI models and API usage patterns.

About

Experimenting with AI Agent building ideas

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages