AI Infra agents

Free & open-source AI research-paper writer: 19 agents draft 20k-word academic papers in ~10 min with citations verified against CrossRef/OpenAlex/Semantic Scholar. Export PDF/Word/LaTeX. Hosted at openpaper.dev

Doctor is a tool for discovering, crawl, and indexing web sites to be exposed as an MCP server for LLM agents.

A curated collection of resources, tools, and frameworks for developing GUI Agents.

A curated collection of learning resources for Generative AI, Machine Learning, Agentic AI, LLMs, RAG, Fine-tuning, MLOps, and more.

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

WarAgent: LLM-based Multi-Agent Simulation of World Wars

Flink Agents is an Agentic AI framework based on Apache Flink

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java26. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

[EMNLP 2025] Awesome RAG Reasoning Resources

SPECA: Specification-to-Checklist Agentic Auditing Framework

Large language model evaluation and workflow framework from Phase AI.

Open-source generalized AI agent for everyday task automations.

Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborate, build new capabilities, and operate safely within defined guardrails.

Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborate, build new capabilities, and operate safely within defined guardrails.

Llama Agents + Workflows are an event-driven, async-first, step-based way to control the execution flow of AI applications like agents.

gradio region:us

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

A simple, fast and robust program-aware agentic inference system.

A python native agent framework

LightningRAG is a full-stack Vue + Gin starter with a decoupled frontend and backend, plus built-in, extensible RAG (retrieval-augmented generation): knowledge bases, vector search, and integrations with many LLM and vector-store providers

You can now generate creatures directly within your project. Drop the open-source into your Agent, and start prompting what you want.

A curated list of retrieval-augmented generation (RAG) in large language models

Large Language Models for All, 🦙 Cult and More, Stay in touch !

MindSQL: A Python Text-to-SQL RAG Library simplifying database interactions. Seamlessly integrates with PostgreSQL, MySQL, SQLite, Snowflake, and BigQuery. Powered by GPT-4 and Llama 2, it enables natural language queries. Supports ChromaDB and Faiss for context-aware responses.

Build reliable AI Workflows and Agents with humans in the loop, structured outputs and durable execution.

Harness-oriented agent system framework for production-grade LLM agent applications

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

A tiny implementation of an autonomous agent powered by LLMs (OpenAI GPT-4)

Ultra-lightweight AI Agent

Transform any idea into a running AI-powered company

Agentic RAG R1 Framework via Reinforcement Learning

A universal flight control tuning framework

🤖 An AI agent framework built with Rust.

多平台模型接入，可扩展，多种输出格式，提供大语言模型聊天服务的插件 | A bot plugin for LLM chat with multi-model integration, extensibility, and various output formats

Drop a book, start asking question.

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.

Android BYOK LLM client with multi-provider access, agentic workflows, and remote device control.

gradio region:us

Open-source AI Employee Platform — Create AI employees that collaborate with your real team in WeCom, DingTalk, and Feishu, just like hiring a few more colleagues.

Paper list for Personal LLM Agents

ChatGPTやCopilotなど各種生成AI用の「日本語]の Prompt のサンプル

Self-Programming AI Assistant. Capture, automate, and refine all your workflows.

From thought to skill. From signal to structure.

A tool for generating function arguments and choosing what function to call with local LLMs

[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration

The Data Explorer gives you fast, safe access to data stored in Cassandra, Dynomite, and Redis.

Agentic RAG R1 Framework via Reinforcement Learning

中文论文常用排版格式Skills，适用于课程论文、数模竞赛、毕业论文等场景，让llm agent写word论文或者将.md转.docx时可调用

Code and data for GeneGPT.

Console supporting tracing, prompt engineering and evaluation for Agents developed with Spring AI Alibaba.

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

🚀 LangChain for Swift. Optimized for iOS, macOS, watchOS (part) and visionOS.(beta)

A command-line interface for LLMs written in Bash.

The application framework for vertical AI SaaS — auth, workspaces, billing, credits, execution boundary, page registry. You build the agent.

LangStream. Event-Driven Developer Platform for Building and Running LLM AI Apps. Powered by Kubernetes and Kafka.

基于大语言模型(LLM)和多智能体(Multi-Agent)，探究AI写小说能力的边界

Open Agent Spec (Agent Spec) is a framework-agnostic declarative language for defining agentic systems. It defines building blocks for standalone agents and structured agentic workflows as well as common ways of composing them into multi-agent systems.

Unlock 650+ MCP servers tools in your favorite agentic framework.

[ICML 2026] Let LLMs invent and evolve languages for efficient reasoning.

Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.

AG2 Visualized - Build Multi-Agentic Apps with Drag-and-Drop.

AG2 Visualized - Build Multi-Agentic Apps with Drag-and-Drop.

A Meta-Skill for Private-First Distribution of Agentics (Skills, Agents, and Prompts) across your Agents, Devices, and Teams.

See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.

南鸢写真提示词 Agent Skill

RuoYi-AI user frontend for AI conversations, agent interactions, and knowledge-base Q&A.

A fast responsive, machine learning, conversational dialog engine for creating chat bots, written in Go.

Command your browser with GPT

Azure AI Search + Azure OpenAI Accelerator to build Agents

Fully neural approach for text chunking

一款集合多家大模型能力的客户端。拥有丰富的个性化功能。现已支持：OpenAI，Ollama，谷歌 Gemini，讯飞星火，百度文心，阿里通义，天工，月之暗面，智谱，阶跃星辰，DeepSeek 🎉🎉🎉。A collection of large model capabilities of the client. Has a wealth of personalized functions. English UI support.

WenShape文枢(原NOVIX写作):深度上下文感知的智能体小说创作系统/A Deep Context-Aware Agent-Based Novel Creation System

AgentKit is a toolkit that gives AI agents access to crypto wallets and onchain functionality. Powered by the 0xGasless AgentKit SDK.

Lightweight LLM Interaction Framework

TopicGPT: A Prompt-Based Framework for Topic Modeling [NAACL'24]

transformers safetensors qwen3 text-generation conversational en

Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models

Build robust LLM applications with true composability 🔗

AlphaAgent is an autonomous alpha mining framework.

Enhance LLM agents with rich tool APIs

Talk with your notes in Claude. RAG over your Apple Notes using Model Context Protocol.

Giving LLMs like GPT-4 the ability to plan and execute terminal commands

pykoi: Active learning in one unified interface

🦖 X—LLM: Cutting Edge & Easy LLM Finetuning

RAG evaluation without the need for "golden answers"

Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.

Build your own ChatPDF and run it locally

Flexible and powerful multi-agent AI framework

Your Engineering Gen AI Team member 🧬🤖💻

Jarvis AI is a Python Module which is able to perform task like Chatbot, Assistant etc. It provides base functionality for any assistant application. This JarvisAI is built using Tensorflow, Pytorch, Transformers and other opensource libraries and frameworks.

Odyssey: Empowering Minecraft Agents with Open-World Skills

🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.

Disciplined AI Collaboration: a method for building software with AI. One loop at every size, rules held by checks rather than attention, state derived rather than written, evidence in place of claims. Includes the PAG grammar, an architecture and a queryable ontology. Every page is also served as Markdown and JSON at banes-lab.com.

AutoHarness: Automated Harness Engineering for AI Agents

Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar

🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.

[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning