Stars
Redis' official collection of agent skills
Open Policy Agent (OPA) is an open source, general-purpose policy engine.
OpenShell is the safe, private runtime for autonomous AI agents.
A flexible distributed key-value database that is optimized for caching and other realtime workloads.
For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.
Artificial Life in Cellular Encoding (ALICE): optimizing NCAs to preserve information in a noisy environment.
Fast and streamable Excalidraw MCP App
RedisShake is a Valkey/Redis data processing and migration tool.
Fast and flexible memory for agents and AI applications using Redis
Feathr – A scalable, unified data and AI engineering platform for enterprise
TRITONCACHE implementation of a Redis cache
Implementation of a local in-memory cache for Triton Inference Server's TRITONCACHE API
A simple mobile banking application using Redis Enterprise.
System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge
Training setup for Langchain's Open Deep Research
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Interactive RAG workbench to demonstrate Redis features and enhancements for improving accuracy, speed, cost, and reliability of LLM applications.
AgentSociety 2 is a modern, LLM-native agent simulation platform designed for social science research and experimental design. It provides a flexible framework for creating and managing intelligent…
Get your documents ready for gen AI
Sample notebooks and prompts for LLM evaluation
A package for statistically rigorous scientific discovery using machine learning. Implements prediction-powered inference.
A statistical toolkit for scientific discovery using machine learning
syftr is an agent optimizer that helps you find the best agentic workflows for your budget.
Main reference implementation for NLWeb, implemented in Python.
SkyRL: A Modular Full-stack RL Library for LLMs