GitHub AI Open Source Reviews

Minimal tool for running large language models locally

Efficient LLM inference engine implemented in C++

Inference code for Llama models

Port of OpenAI's Whisper model in C/C++

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

The official Python library for the OpenAI API

Build resilient agents.

Integrate cutting-edge LLM technology quickly and easily into your apps

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

A coding agent for open models like Kimi K3

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Framework for building LLM applications

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

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, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

Stable Diffusion web UI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Search infrastructure for AI

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

open-source coding agent

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Microsoft's multi-agent collaboration framework

A Python-based AI agent framework designed to adapt and evolve alongside users through integration with major LLM providers.

TensorFlow is a widely used open-source framework for machine learning and deep learning applications developed by Google.

Prompts.chat is a community-driven platform for sharing and discovering AI prompts, offering open-source self-hosting options for privacy-focused organizations.

A Python framework facilitating the development and deployment of transformer models across text, vision, audio, and multimodal machine learning tasks.

Firecrawl is a TypeScript-based API designed to search, scrape, and interact with web data at scale for AI applications.

Dify is an open-source platform for building agentic workflows and RAG pipelines with multi-model support and flexible deployment options for teams.

Open WebUI is a user-friendly AI interface supporting Ollama and OpenAI APIs for self-hosted LLM management.

PyTorch is a widely adopted open-source machine learning framework offering tensor computation with GPU acceleration and dynamic neural network capabilities.

This project provides a step-by-step guide to implementing a ChatGPT-like large language model using PyTorch from scratch.

A Claude Code skill designed to reduce token usage by approximately 65% through simplified caveman-style communication prompts.

OpenAI's open-source speech recognition model

OpenCV is a widely used open-source computer vision and image processing library written primarily in C++ with bindings for other languages.

A comprehensive twelve-week curriculum designed to teach machine learning fundamentals through lessons, quizzes, and Jupyter notebooks for beginners.

A comprehensive curated list of computer science courses featuring video lectures across various technical domains and disciplines.

A comprehensive educational repository providing roadmaps and Colab notebooks for learning Large Language Models and machine learning concepts.

Netdata delivers real-time, AI-powered full stack observability for infrastructure and applications, offering deep insights with minimal resource consumption for lean teams.

Deer-flow is an open-source SuperAgent harness enabling long-horizon tasks through sandboxes, memories, and subagents for researching, coding, and creating.

A Chinese-language deep learning textbook with runnable code used by hundreds of universities worldwide for teaching machine learning concepts.

A comprehensive collection of guides, papers, and resources focused on prompt engineering, context engineering, RAG, and AI agents for developers.

Tesseract is a widely used open-source OCR engine written in C++ that supports multiple languages and machine learning models.

LlamaFactory is a unified framework for efficient fine-tuning of over 100 large language and vision models, supporting various training methods.

Role-playing multi-agent orchestration framework

A curated collection of resources focused on scalable, reliable, and performant large-scale system design patterns for developers and architects.

OpenBB is a Python-based open data platform designed for financial analysts, quants, and AI agents to access market data.

This repository provides annotated Python implementations of deep learning papers, featuring detailed explanations alongside code for transformers, GANs, and optimizers.

Scikit-learn provides efficient tools for data analysis and machine learning in Python, built on NumPy, SciPy, and matplotlib.

A Python library and proxy that compresses LLM inputs like logs and JSON to reduce token usage while maintaining answer quality.

Keras is a high-level neural network library enabling rapid prototyping across TensorFlow, JAX, and PyTorch backends for machine learning practitioners.

Microsoft's educational repository offering a structured 12-week course covering machine learning, deep learning, and AI fundamentals via interactive notebooks.

Anthropic's official MCP Servers repository provides reference implementations of the Model Context Protocol, establishing a standardized interface for LLM agents to securely connect to tools, databases, and external systems through a unified JSON-RPC-based transport layer.

Browser Use is a production-grade open-source framework that bridges large language models with real-world web environments through autonomous browser control, enabling AI agents to navigate, interact with, and extract data from websites with human-like precision.

Mem0 is a universal memory layer for AI agents that provides structured long-term and short-term memory management, enabling personalized agent behavior across multi-session interactions through a token-efficient memory algorithm achieving 92.5 on LoCoMo and 94.4 on LongMemEval benchmarks.

LLM data framework and RAG engine

The Anthropic Cookbook is the official, authoritative reference repository for Claude prompt engineering, tool use, and agent architecture patterns, offering 50+ production-ready Jupyter notebooks that codify best practices for RAG, structured outputs, multi-tool orchestration, and autonomous agent design.

Anthropic's Interactive Prompt Engineering Tutorial is a canonical, MIT-licensed educational repository that systematically teaches prompt engineering fundamentals through 9 progressive chapters with hands-on exercises, serving as the definitive learning path for Claude API developers.

Fabric is a Go-based open-source AI augmentation framework that pioneered the modular Markdown prompt pattern paradigm, enabling humans to compose, share, and execute crowdsourced AI prompts across any LLM provider with a unified CLI and REST API interface.

Agno (formerly Phidata) is a comprehensive Python-based framework and runtime for building, deploying, and managing multi-model AI agent platforms, featuring a unified SDK, AgentOS runtime with MCP server support, JWT-based RBAC, and a full-stack control plane for enterprise-grade autonomous agent orchestration.

STORM is Stanford's open-source LLM-powered knowledge curation system that autonomously researches topics through multi-perspective question asking, iterative retrieval, and structured report generation with citations, now extended with Co-STORM for human-AI collaborative workflows.

smolagents is Hugging Face's minimalist, code-first AI agent framework that enables agents to reason and act through Python code generation, offering a lightweight alternative to verbose prompt-heavy agent architectures with native tool/skill integration, sandboxed execution, and a clean compositional design.

Microsoft Guidance is a paradigm-shifting framework that introduces constrained decoding via regex and CFG grammars, enabling deterministic structured generation from LLMs while interleaving Python control flow with model inference for production-grade agent architectures.

CAMEL is a pioneering open-source multi-agent framework that introduces role-playing-based autonomous agent communication, enabling scalable agent collaboration through structured prompt engineering, tool orchestration, and cross-model interoperability for research and production deployments.

Microsoft Prompt Flow is a comprehensive open-source LLMOps framework that provides a visual DAG-based workflow engine, structured prompt engineering toolkit, evaluation harness, and production deployment pipeline for building, testing, and monitoring LLM-powered applications at enterprise scale.

E2B is an open-source, Apache-2.0 licensed infrastructure platform providing secure, isolated sandbox environments for AI agents to execute arbitrary code (Python/JS) in the cloud. With dual Python and TypeScript SDKs, it enables enterprise-grade agent architectures by solving the critical problem of safely running LLM-generated code without compromising host systems.

High-throughput LLM inference and serving engine

The Gemini Cookbook is Google's official open-source reference repository for the Gemini API, providing a structured learning path spanning prompt engineering, function calling, multimodal agent development, and advanced reasoning workflows across Gemini 3.7 Flash, Omni Flash, Nano-Banana 2, and Lyria 3 models.

Instructor is the standard library for structured LLM outputs, leveraging Pydantic for strict schema validation, automatic retry-based error correction, and robust agent skill argument extraction.

Outlines is the premier framework for guided LLM generation, compiling regular expressions and context-free grammars (CFGs) into decoding-level finite state machines (FSM) for 100% guaranteed structured text.

Composio is a production-grade tooling and skills infrastructure for AI agents, offering 250+ pre-built integrations (GitHub, Slack, Jira, Salesforce, Gmail) with managed authentication, schema routing, and execution.

Aider is the premier terminal-based AI pair programming agent, pioneering Tree-sitter-based Repository Map prompt engineering, automated atomic git commits, and benchmark-leading multi-file editing precision.

SWE-agent is a state-of-the-art autonomous software engineering agent from Princeton NLP, pioneering the Agent-Computer Interface (ACI) tailored for LLMs to browse, edit, and resolve real-world GitHub issues.

ChatDev is a virtual software company multi-agent framework by Tsinghua & OpenBMB, orchestrating role-playing agents (CEO, CTO, Programmer, Tester) across waterfall phases to synthesize full software systems from single prompts.

Promptfoo is the industry-leading CLI toolkit for LLM prompt engineering, agent skill evaluation, and automated red teaming, offering matrix testing, semantic assertions, and native CI/CD quality gates.

Mirascope is an elegant, modular Pythonic LLM toolkit advocating 'colocation' of prompts and logic, providing first-class typing, modular prompt templates, and clean agent skill abstractions.

AgentOps is the premier observability and session replay platform built specifically for autonomous AI agents, offering one-line tracking for tool calls, token spend, infinite loop detection, and graphical replays.

AI software-engineering agent

Anthropic Quickstarts is the official repository of deployable reference applications and agent skill blueprints by Anthropic, featuring Computer Use, MCP agents, and enterprise Claude architectures.

Langfuse is the leading open-source LLM engineering platform, delivering centralized prompt management and versioning, multi-agent distributed tracing, cost analytics, and automated evaluations.

Letta (formerly MemGPT) is a stateful agent platform from UC Berkeley, pioneering OS-inspired hierarchical virtual memory paging for lifelong, self-editing agent memory and persona persistence.

PydanticAI is the official Pythonic agent framework by the Pydantic team, pioneering type-safe Dependency Injection, dynamic system prompts, and strict schema validation for production GenAI.

AutoCodeRover is an autonomous program repair agent by National University of Singapore (NUS), pioneering Abstract Syntax Tree (AST)-aware code navigation and spectrum-based fault localization for precise bug resolution.

Anthropic's official reference server collection for the Model Context Protocol (MCP), providing canonical implementations that expose files, databases, APIs, and tool skills to LLM agents via a standardized JSON-RPC capability-negotiation layer.

Browser Use is a Python-native open-source framework that lets LLM agents operate web browsers autonomously via DOM extraction, accessibility tree mapping, and structured action primitives, enabling reliable form filling, navigation, and multi-step web automation.

Mem0 is a universal memory layer for AI agents, providing personalized long-term memory, multi-session state retrieval, and token-efficient context management across LLM ecosystems.

Anthropic's official open-source repository demonstrating advanced prompt engineering, tool use, and agentic workflows with the Claude API.

Anthropic's official interactive prompt engineering curriculum that codifies prompt design as a reproducible software engineering discipline across nine progressive chapters, leveraging Claude 3 Haiku for cost-efficient pedagogical iteration and XML-structured output patterns for production-grade reliability.

LLM programming framework with declarative prompt optimization

Fabric is a modular, Markdown-driven prompt engineering framework that treats AI prompts as versioned, composable, crowdsourced artifacts—decoupling domain-specific reasoning scaffolds from any single LLM vendor or application runtime.

Agno (formerly Phidata) is a production-oriented, Apache-2.0 agent platform framework that separates SDK-based agent construction, the AgentOS runtime, and a governance UI—delivering Postgres-backed relational memory, native MCP server support, JWT RBAC, and Docker-first deployment for organizations seeking to own their agent infrastructure.