Clean, minimal, accessible reproduction of DeepSeek R1-Zero

SGLang is a fast serving framework for large language models and vision language models.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

Open-source observability for your LLM application, based on OpenTelemetry

DuckDB-powered data lake analytics from Postgres

Columnstore Table in Postgres

PDF to Markdown with vision models

Framework for building scalable agentic applications.

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

Superfast AI decision making and intelligent processing of multi-modal data.

An open-source RAG-based tool for chatting with your documents.

DSPy: The framework for programming—not prompting—language models

The LLM Evaluation Framework

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Adding guardrails to large language models.

AI + Data, online. https://vespa.ai

Repair invalid JSON documents

All Algorithms implemented in Python

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

Entropy Based Sampling and Parallel CoT Decoding

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

Improved file parsing for LLM’s

Awesome Search - this is all about the (e-commerce, but not only) search and its awesomeness

A modular graph-based Retrieval-Augmented Generation (RAG) system

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).