Stars
The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
Working memory for Claude Code - persistent context and multi-instance coordination
🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
The only AI app builder that knows backend
A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence…
A framework for few-shot evaluation of language models.
The official Python SDK for Model Context Protocol servers and clients
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
The Security Toolkit for LLM Interactions
Open-source implementation of AlphaEvolve
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
A library for mechanistic interpretability of GPT-style language models
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
SynthLang is a hyper-efficient prompt language designed to optimize interactions with Large Language Models (LLMs) like GPT-4o by leveraging logographical scripts and symbolic constructs.
A curated list of awesome data labeling tools
A lightweight web application for brushing labels onto time series data; useful for building training sets.
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
Problem-Oriented Segmentation and Retrieval EMNLP 2024 Findings
The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.
Knowledge Table is an open-source package designed to simplify extracting and exploring structured data from unstructured documents.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.