Stars
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
The Security Toolkit for LLM Interactions
An open-source visual programming environment for battle-testing prompts to LLMs.
Adding guardrails to large language models.
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
ChatGPT + DALL-E + WhatsApp = AI Assistant 🚀 🤖
🧙♀️ Move Fast and Break Nothing. End-to-end typesafe APIs made easy.
A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.
Building Open-Ended Embodied Agents with Internet-Scale Knowledge
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
LlamaIndex is the leading document agent and OCR platform
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
A playbook for systematically maximizing the performance of deep learning models.
Storybook is the industry standard workshop for building, documenting, and testing UI components in isolation
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
TypeScript ORM for Node.js based on Data Mapper, Unit of Work and Identity Map patterns. Supports MongoDB, MySQL, MariaDB, MS SQL Server, PostgreSQL and SQLite/libSQL databases.
Create agents that monitor and act on your behalf. Your agents are standing by!