ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

Official repository for "NoLiMa: Long-Context Evaluation Beyond Literal Matching"

Beautiful, open source, WebGPU-based charting library

Codex/ChatGPT account load balancer & proxy with usage tracking and dashboard

Our library for RL environments + evals

Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.

Algorithm powering the For You feed on X

Cloud-Native distributed storage built on and for Kubernetes

The terminal for orchestrating agents - Run a team of Claude Code, OpenCode, or any other CLI agents on your machine

JSON Schema Type Builder with Static Type Resolution for TypeScript

Specification and documentation for Agent Skills

Minimal CLI coding agent by Mistral

Vercel AI SDK community provider for Gemini CLI - Free use via Gemini Code Assist License

⬅️ ES6 string tag that strips indentation from multi-line strings.

Run GEPA on your favorite non-python libraries.

Spawn ephemeral, parallel versions of your codebase to ship faster with AI.

🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

Browser automation CLI for AI agents

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

The open agent skills tool

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Vercel AI SDK and middleware for models that do not support function calls (Part of Project Wrench)

Lighweight CLI to interact with MCP servers

A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.

🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.