The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM Observability all in one place.

Efficient, Flexible and Portable Structured Generation

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

A library for advanced large language model reasoning

A simple screen parsing tool towards pure vision based GUI agent

A static analysis tool for GitHub Actions

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

LLM powered fuzzing via OSS-Fuzz.

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Official implementation of Language Models as Compilers: Simulating the Execution Of Pseudocode Improves Algorithmic Reasoning in Language Models.

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

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

Code for the paper 🌳 Tree Search for Language Model Agents

Agentless🐱: an agentless approach to automatically solve software development problems

Large Action Model framework to develop AI Web Agents

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

LLM101n: Let's build a Storyteller

Open-source framework to review and patch code using your preferred LLM.

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

llama3 implementation one matrix multiplication at a time

The simplest, fastest repository for training/finetuning medium-sized GPTs.

https://openjdk.org/projects/code-tools/jol

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

Llama-3 agents that can browse the web by following instructions and talking to you

The production-scale datacenter profiler (C/C++, Go, Rust, Python, Java, NodeJS, .NET, PHP, Ruby, Perl, ...)

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

A high-throughput and memory-efficient inference and serving engine for LLMs

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)