Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway

Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory

Python package and backend for the Elysia platform app.

Deep Agents in JS

Roo Code gives you a whole dev team of AI agents in your code editor.

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Cache-Augmented Generation: A Simple, Efficient Alternative to RAG

Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Document to Markdown OCR library with Llama 3.2 vision

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

Anthropic's educational courses

Framework to build resilient language agents as graphs.

Swarm.js is a Node.js implementation of OpenAI’s experimental Swarm framework. This SDK allows developers to orchestrate multi-agent systems using OpenAI’s API in a lightweight and ergonomic way, w…

A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.

Langchain + Docker + Neo4j + Ollama

Run the latest LLMs and VLMs across GPU, NPU, and CPU with PC (Python/C++) & mobile (Android & iOS) support, running quickly with OpenAI gpt-oss, Granite4, Qwen3VL, Gemma 3n and more.

Aligning pretrained language models with instruction data generated by themselves.

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

MiniCPM on Android platform.

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

High-performance In-browser LLM Inference Engine

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.