AI Infra agents

Open-source observability tool that uses AI agents to self-heal your software

Bringing together outstanding artificial intelligence (AI) open source projects from around the world.

One Query. All Search Skill. 聚合 Gemini、Grok、豆包、元宝等平台原生 AI 搜索能力，免费获取科技趋势、行业舆情、热点追踪、旅行规划、日常问题统一接进自己的 Agent 与工作流，指定链接免费爬取

A tiny library for coding with large language models.

Open-source tool to visualise your RAG 🔮

This repository contains a collection of the best system prompts for ChatGPT, a conversational AI model developed by OpenAI. Star this repository to help us reach 5,000 stars!

Search, understand, reproduce, and improve an idea with ease

An Obsidian plugin to interact with your privacy focused AI-Assistant making your second brain even smarter!

Multi-Agent System Framework For Complex Tasks

MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025

💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.

PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference.

Use LLMs to hide messages inside normal looking conversations

A collection of autonomous agents 🤖️ powered by LLM.

A generalized information-seeking agent system with Large Language Models (LLMs).

🤖 / 🏪 Agent Index - This is the agent index for LobeChat. It accesses index.json from this repository to display a list of available agents for LobeChat to the agent market.

Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.

Awesome AI GPTs, OpenAI GPTs, GPT-4, ChatGPT, GPTs, Prompts, plugins, Prompts leaking

Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.

A single interface to use and evaluate different agent frameworks

[JMLR 2026] "UQLM: A Python Package for Uncertainty Quantification in Large Language Models"

Inkdown is a WYSIWYG editor and an LLM dialogue tool, fully compatible with GitHub Flavored Markdown Spec.

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

Open CLI for integrating AI search, recommendation, and conversational retrieval into agent systems and business systems

A minimal LLM chat app that runs entirely in your browser

Lightweight Long-Term Memory for LLM Agents.

Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

The most Token-efficient open-source AI Agent

LangChain powered shell command generator and runner CLI

Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime.

1000+ GPTs and 10 categories. 80+ Leaked Prompt，Awesome，chatgpt，Ai，prompt

A-MEM: Agentic Memory for LLM Agents

Building Apps with LLMs

Wasabi A/B Testing service is an open source project that is no longer under active development or being supported

Open Source Semantic Search for your AI Agent

OpenTelemetry Instrumentation for AI Observability

The AI Application Framework for Javascript

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

The TypeScript framework for AI development

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

transformers pytorch safetensors llama text-generation facebook

AxisAgentic: An Extensible Runtime and Trajectory-Collection Framework for Long-Horizon Agents.

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

把最丝滑的通用 Agent 体验带进你的工作流，为 100x 专业用户而生的未来产品，正在实现 proactive Agent 阶段。基于 Claude Agent SDK 的完整开源实践，原生支持飞书群聊调用、灵活接入任意大模型供应商 —— 让顶级 Agent 能力真正跑在你每天用的地方。

A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust.

An autonomous agent that takes work, does work, gets paid, and gets better at it.

Curated AI Prompts for Cursor Rules, Cline, Windsurf and Github Copilot

Native A2UI Renderer for iOS/Android/HarmonyOS. High performance streaming Generative UI. Custom Components, Styles and more.

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

Your Software Factory - build faster and better with multi node agents that work 24/7

A hierarchical memory framework for personalized presentation agents. Try it at memslides.com.

Chat with your documents using local AI

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.

Unified interface for AI chat, Agentic workflows and more ...

For students, scholars, interviewees and lifelong learners. Let LLMs assist you in learning 🎓

C# implementation of LangChain. We try to be as close to the original as possible in terms of abstractions, but are open to new entities.

Dynamiq is an orchestration framework for agentic AI and LLM applications

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Build agents which are controlled by LLMs

On-premises conversational RAG with configurable containers

streamlit region:us

[ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds

Autonomous GPT-4 agent platform

Use sidecar next to CLI agents for diffs, file trees, conversation history, and task management with td

🐙 关于提示词工程（prompt）的指南、论文、讲座、笔记本和资源大全（自动持续更新）

AxisRL is an agentic RL post-training framework built on SGLang rollout, Megatron training, and real-world agent workflows.

A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture

The Buildkite Agent is an open-source toolkit written in Go for securely running build jobs on any device or network

🐝 The First Self-Improving agents with RL / Prompting Optimization

The Microsoft 365 Agent SDK simplifies building full stack, multichannel, trusted agents for platforms including M365, Teams, Copilot Studio, and Webchat.

A repository of Generative AI prompts for product managers using agents such as ChatGPT, Claude, & Gemini

A security scanner for your LLM agentic workflows

Auto-GPT on the browser

Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.

[NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web" -- the first LLM-based web agent and benchmark for generalist web agents

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

LangSmith Client SDK Implementations

Web UI for AutoGen (A Framework Multi-Agent LLM Applications)

The leading agentic finance toolkit for AI agents

Open-source alternative to Claude Agent SDK, ChatGPT Agents, and Manus.

Folder structure as agent architecture. ICM replaces framework-level orchestration with filesystem structure.

A demo of an GPT-based agent existing in an RPG-like environment

AI agent for building React Native apps

gradio region:us

Rust library for generating vector embeddings, reranking locally!

Parsing-free RAG supported by VLMs

Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A

Active learning for systematic reviews

♾️ 开源数字永生框架 — 从聊天记录蒸馏任何人的七维数字分身。支持微信/飞书/iMessage/Telegram等12+平台，7种角色模板，对齐 OpenClaw Soul Spec 标准。一行指令让你的AI学会蒸馏。

ActiveAgent Rails framework for Agent Apps

Official repo for MM-REACT

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.

AgentSims is an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in.

List of Molecular and Material design using Generative AI and Deep Learning

Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks