tool-use

Gym tool use environments.

Baselines for tool use environments.

Translational workforce roles and persona profiles

OpenAgents: An Open Platform for Language Agents in the Wild

neat is a ReAct-like agent accessing all sorts of data & APIs

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

歇斯底里的双色球！But Chat with LLM

Paper collection on building and evaluating language model agents via executable language grounding

Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to implement complex AI applications through agent collaboration and advanced design patterns.

Versatile LLM Tool Use (Function Calling) package for Laravel, compatible with all LLMs, enabling LLM to execute actual code functions (unlike LLMs' built-in capabilities).

Tool-use Robotic Benchmark built with Drake Simulation

Learn function calling and tool calling from simple tools to full agents.

Task Automation Orchestrator Agent (Tao Agent) using OpenAI Assistants API and function calling

Generate JSON schemas for tool calling or function calling from python functions

LangGraph stateful agent orchestration with tool-use and memory

Using LLMs and rules for a local personal agent

This project demonstrates how to get structured outputs from Deepseek R1 reasoning model and do tool calling using an OpenAI summarization step. It's made using Next.js serverless routes and uses shadcn/ui for the frontend.

Official code for AAAI2023 paper`Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum`

Demonstrates a workflow for LLM function calling evaluation. Uses GitHub Copilot to generate synthetic eval data and Azure AI Foundry for handling results.