AI Infra agents

AgentX · Next-generation open-source AI agent development framework and runtime platform ｜ 下一代 AI 智能体开发框架和运行时平台

Arena: A General Evaluation Platform and Building Toolkit for Single/Multi-Agent Intelligence. AAAI 2020.

Automatically adds User Agent CSS classes to the document allowing variations for specific browsers without resorting to CSS hacks.

LangChain chat model abstractions for dynamic failover, load balancing, chaos engineering, and more!

Python library for building durable and scalable multi-agent orchestrations.

An AI bot with RAG capability for Topics, Chat & Customer Support in Discourse, currently powered by OpenAI

A RAG (Retrieval-Augmented Generation) solution Based on Advanced Pre-generated QA Pairs. 基于高级 QA 问答对预生成的 RAG 知识库解决方案

Turn GitHub repositories into LLM tools. (ACL 2025)

Hands‑on hackathon challenges to build intelligent multi‑agent financial compliance workflows using the Microsoft Agent Framework

A multi-agent framework for autonomous end-to-end development of radiomics and deep learning models for medical imaging

Your Desktop AI Staffs.

AgentTrace is a lightweight observability library to trace and evaluate agentic systems.

SemaClaw is an open-source framework for general-purpose personal AI agents.

Survey paper: From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents.

A Context Engineering Framework for AI-Assisted Multi Agent Applications Development

Local-first Windows tray app for monitoring Claude Code and Codex tokens, costs, sessions, and rate limits

OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, managed at scale, and the channels you already use.

Visualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost.

基于 Django + Vue 的 RAG 知识库问答系统，支持 Agent 推理、知识图谱、Wiki 自动生成和跨会话记忆。

🥇 Not Just Another Agent Framework, But a Bayesian Evolution Layer That Can Work Across Harnesses

docker leaderboard region:us

A curated, continuously updated reading list of 200+ papers on LLM agents: planning, memory, tool use, multi-agent, evaluation & safety. Companion to the survey 'LLM Agents: A Survey'.

Premium, zero-configuration local AI inference & agentic workspace running completely offline on Windows, macOS, and Linux.

AI trading bot crypto LLM agent quantitative trading automated trading algorithmic trading Binance Gate.io TypeScript Node.js VoltAgent crypto bot risk management multi-strategy

AGIUI for Browser Extension

agentcraft 可以帮助您快速构建各类应用场景的ai agent应用

This project is a Local RAG system built for the NYU Machine Learning course.

A Toolkit for building AI agent for web3.

用于多机覆盖路径规划流程化算法 Algorithm for Streamlining Multi-Agent Coverage Path Planning

Autogen studio docker

AI agent with RAG+ReAct on Indian Constitution & BNS

Agent Waystation · Agent 驿站 — a stopover for AI agents, builders, tools, and field reports

A multi-agent chatroom for AutoGen agents

AI agent grounded with search and extract tools to reduce hallucination.

An example of a RAG backend plus UI

[ACM Multimedia 2025] "Multi-Agent System for Comprehensive Soccer Understanding"

🧨 TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?

A personalized web workbench for Hermes Agent with setup packs, artifacts, memory-aware onboarding, and local+remote model workflows.

Awesome Agentic AI Learning Resource by DevKay is a curated roadmap for mastering Agentic AI—from ML foundations to production-ready agents. Features a 0–12+ month path, hands-on projects, top resources, agent architectures, and tools like LangChain and AutoGen.

Utility and fun cogs for Red

A Go library for building performant, type-safe AI agents that execute structured reasoning workflows.

ASK MIRAGE is an offline AI-powered chatbot that allows users to upload PDFs and ask natural language questions. Built with LLaMA, FAISS, and LangChain, it delivers fast, accurate, and context-aware responses without needing an internet connection. Ideal for students and professionals working with large documents.

Graphon is a Python graph execution engine for agentic AI workflows.

AI agentic skills framework for spec-driven development, built on the organizational model of mafia.

Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.

A unified anti-dead-loop toolkit for LLM agents — loop detection, budget ceiling, state stasis guard, and circuit breaker in one library.

transformers pytorch safetensors mistral text-generation LLMs

A framework for building intelligent agents

A Step-by-Step Implementation of Google Veo 3 Architecture from Scratch

A lightweight AI browser automation agent framework

Record and replay LLM interactions for langchain

Reinforced Multi-LLM Agents training

Get your lists of User-Agent Strings here

Next.js-like framework building AI Agents that are payment-native. Bootstrap your agent with A2A, MCP, x402 payments, and ERC-8004 identity.

MPO: Boosting LLM Agents with Meta Plan Optimization (EMNLP 2025 Findings)

A Settlers of Catan framework built in Python with AI agents

LLM agents done right, no over-engeneering and redundant complexity

Lightweight Python framework for creating intelligent AI agents with ease.

A simple RAG and Function Calling demo based on WPF and Semantic Kernel.

Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning

This Guidance demonstrates how to address the complexity of troubleshooting Amazon EKS environments with multiple metrics and logs by implementing an agentic AI workflow that uses generative AI with RAG-enabled knowledge bases and chat interfaces to accelerate problem diagnosis.

PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.

Friendly Environment for Neural Networks (fenn) is a simple Python framework for building ML/DL workflows and LLM agents faster, with prebuilt trainers, agent templates, logging, configuration management, and much more.

Continual Learning for AI agents, helping your agents self-improve with every run

[ICML 26] An evaluation framework assessing long-context retention and long-horizon memory performance for agentic applications (AMA-bench).

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

A curated list of awesome open source projects for creating agentic operating systems, AI agents, and tools for the future of autonomous computing.

gradio region:us

gradio leaderboard modality:text eval:generation language:polish judge:auto test:public submission:manual

Tesla multi-intent in-car agent (RAG + Skills)

A framework for Ruby Gems to expose LLM context.

DSH Web 插件 · 提示词优化器 0.6（主线）：你照常说话，它在你发送前把"这一轮到底要什么"理清楚，再把这份理解交给工作 AI —— 原话不改写，每轮独立产目标（不遗传），条条带逐字依据。含控制界面（档位/权限/模型/上下文/只读工具）、拦截浮层（思维层+产出层）与真实 token 用量。

AI, fully local on your computer.

Quant infrastructure for AI agents — a free, open-source macOS workspace where your Claude Code or Codex turns a trading idea into a backtested strategy and runs it live.

ASP-X (Agent Safe Probe X) — An open-source framework for automated safety evaluation of intelligent agents, providing systematic, extensible tools for probing and assessing AI safety across diverse environments.

A framework for Ruby Gems to expose LLM context.

A Reinforcement Learning (RL) agent for Coverage Path Planning.

Synapse enables you to remotely manage a large number of hosts. It brings together features of Configuration Management and Orchestration in a lightweight framework. Written in Python and using AMQP for messaging between the nodes.

A declarative way to control LLMs.

A RL approach to enable cost-effective, intelligent interactions between a local agent and a remote LLM

Official implementation of MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems

Multi-agent (path finding) planning framework

This template deploys a Generative AI Virtual Assistant using Azure OpenAI and Bot Framework.

SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning

Interact with any LLM service

Agent Sessions is a desktop app for managing multiple AI agent sessions at once, written in Rust.

Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs

All-in-one local AI hub for Obsidian — LLM chat with vault tools, MCP servers, RAG, workflow automation, encryption, and edit history. Fully private, no cloud required.

Can AI Agents Build Bespoke LLM Serving Systems?

A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.

First LLM Studio: local-first LLM workbench for Apple Silicon + MLX. 本地优先 LLM 工作台，覆盖 Agent、对比、微调、评测与运行时遥测。

gradio region:us

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

OpenAI document chatbot using llama-index, pinecone and chainlit. With incremental features, giving you the tools to go from a basic RAG into an advanced one.

An AI-powered assistant for your company's docs.

✨🦋 illufly - 【幻蝶】基于记忆蒸馏、资料检索的自我进化智能体

VerifAI initiative to build open-source easy-to-deploy generative question-answering engine that can reference and verify answers for correctness (using posteriori model)

Desktop Tiny Agent is a lightweight, modular desktop intelligent agent framework. It offers plugin extensibility, task scheduling (sync/async), configuration management, and unified logging, supporting dynamic plugin loading for task execution. With an out-of-the-box CLI and examples, it’s ideal for quickly building extensible automation assistants

a chatbot framework based on rails

Amazon MCP server to search & buy products using the L402