All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI tools & agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

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

kani (カニ) is a highly hackable microframework for chat-based language models with tool use/function calling. (NLP-OSS @ EMNLP 2023)

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

BigCodeBench: Benchmarking Code Generation Towards AGI

Easily create LLM tools and agents using Bash/JavaScript/Python, also a library of commonly used LLM tools and agents.

AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning (NeurIPS 2024)

Anthropic Claude API wrapper for Go

A multimodal chat interface with many tools.

SirChatalot is a Telegram bot leveraging ChatGPT, Claude or YandexGPT. It uses Whisper for speech-to-text and DALL-E, Stability AI or YandexART for image creation. It can use vision capabilities or tools/functions.

Awesome MCP Servers - A curated list of Model Context Protocol servers

VT.ai - Minimal multimodal AI chat app with dynamic conversation routing

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.

tiny_fnc_engine is a minimal python library that provides a flexible engine for calling functions extracted from a LLM.

Tool-use Robotic Benchmark built with Drake Simulation

Using LLMs and rules for a local personal agent

🧩 Proposal to allow user scripts like "expand comments", "hide popups", "fill out this form", etc. to be reusable across pure browser environments, puppeteer, playwright, extensions, AI tools, and many other contexts with minimal adjustment.

Curated resources about automated GUI computer-use via LLMs. Highly opinionated, focus is on quality vs quantity.

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).

Gym tool use environments.