Stars
SGLang is a high-performance serving framework for large language models and multimodal models.
Skills for Real Engineers. Straight from my .agents directory.
The collaboration layer for AI teams: domain experts annotate and review agent behavior, engineers improve the agent from what they find.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Recursive Language Model integration for Claude Code - intelligent multi-provider routing and unbounded context handling
Optimize prompts, code, and more with AI-powered Reflective Optimization
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching,…
Additional packages (components, document stores and the likes) to extend the capabilities of Haystack
AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.
🧪 Experimental features for Haystack
Embeddable Postgres with real-time, reactive bindings.
Split text into semantic chunks, up to a desired chunk size. Supports calculating length by characters and tokens, and is callable from Rust and Python.
A language for constraint-guided and efficient LLM programming.
👩🏻🍳 A collection of example notebooks using Haystack
Automatically generate comprehensive Pull Request descriptions with LLMs
Easily deploy Haystack pipelines as REST APIs and MCP Tools.
data load tool (dlt) is an open source Python library that makes data loading easy 🛠️
Enforce the output format (JSON Schema, Regex etc) of a language model
Efficient Retrieval Augmentation and Generation Framework
🚀 A list of Haystack Integrations, maintained by the community or deepset.
[EMNLP 2023 Demo] fabricator - annotating and generating datasets with large language models.
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
🚀 This repo is a showcase of how you can use models deployed on AWS SageMaker in your Haystack Retrieval Augmented Generative AI pipelines
Forward-Looking Active REtrieval-augmented generation (FLARE)
Unofficial python bindings for the rust llm library. 🐍❤️🦀