AI Infra agents

Navigating a maze using LLM agent

a personal journaling app where you can chat with your entries locally

MultiAgent Chat UI

llm-based robot that intervenes only when needed

Your local AI counselor. LLM app that runs offline from a single binary.

An AI-driven network automation tool

A sample for implementing retrieval augmented generation using Azure Open AI to generate embeddings, Azure Cosmos DB for MongoDB vCore to perform vector search, and semantic kernel.

Unofficial PowerShell Module for OpenAI, Azure OpenAI and almost all the GPT services or even local LLMs

🚀 Scale your RAG pipeline using Ragswift: A scalable centralized embeddings management platform

C^3-Bench: The Things Real Disturbing LLM based Agent in Multi-Tasking

A comprehensive framework for benchmarking single and multi-agent systems across a wide range of tasks—evaluating performance, accuracy, and efficiency with built-in visualization and tool integration.

(: SMILE! The positive prompt language for structured prompt engineering — used for complex prompts, multi-turn pipelines, agentic engineering. Modular & maintainable prompts for powerful Large Language Model responses.

Annoucing Instructor Cloud

A simple, modern, and reliable Go library for interacting with multiple LLM providers

🔎 A deep-dive into HyDE for Advanced LLM RAG + 💡 Introducing AutoHyDE, a semi-supervised framework to improve the effectiveness, coverage and applicability of HyDE

Agentic Workflow Platform

Connect to MCP servers right from your shell. Plugin for simonw/llm.

cgpt - cli for LLM operations

A Gradio web UI for Large Language Models. Supports LoRA/QLoRA finetuning,RAG(Retrieval-augmented generation) and Chat

Local-first RAG desktop app & official MCP Server. Let any AI instantly search your private Markdown, PDF, and 1290+ document formats. (本地优先的 RAG 桌面端与官方 MCP 服务器。让任意 AI 瞬间检索你的私有 Markdown、PDF 及 1290+ 种文档格式。)

A Framework for Evaluating AI Agent Safety in Realistic Environments

LLM based Agent

Agentic Graph RAG: Skeleton Indexing + VectorCypher + Agentic Router with Self-Correction

A Golang autonomous AI agent framework for assisting real work

AI Github assistant for your repo. Your proactive GitHub bot that auto-detects duplicates using OpenAI embeddings and Supabase magic!

Make open-weight LLM agents play the game "Among Us", and study how the models learn and express lying and deception in the game.

Crash course tutorial for crew ai framework

[ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents

AI Runtime Kernel — a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back.

Enterprise-grade distributed AI agent framework | Develop → Deploy → Observe | K8s-native | Dynamic DI | Auto-failover | Multi-LLM | Python + Java + TypeScript | MCP + A2A + REST

SPY put-credit validation and real-money control plane with broker-backed ledgers, deterministic risk gates, hybrid RAG, reconciliation, and $1k/mo after-tax evidence tracking.

TMLR | This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms.

A framework-agnostic UI kit of production-ready components for building AI and LLM chat interfaces.

Privacy middleware for LLM & RAG pipelines - consistent pseudonymization, encrypted vault, SSE streaming rehydration.

An end-to-end demo of an autonomous agentic mobile manipulator for warehouse robotics, showcasing fully on-device perception, reasoning, and natural language control in a ROS 2 simulation using AMD Ryzen™ AI hardware.

Integration toolkit for connecting AI agents to the Visa Intelligent Commerce platform.

The LLM Council works together to answer your hardest questions

The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.

Cortex Space is a local-first developer workspace built with Tauri v2 + React. Replace static terminals with a fluid, keyboard-driven environment featuring recursive split layouts, drag-and-drop panes, AI agent workflows, command snippets, and automatic port detection.

From Agent to Agency — 一个 AI 做不了的事，一群 AI 可以。Multi-Agent Collaboration Platform.

Official Repository for our paper: PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Run MoE LLMs on Apple Silicone via MLX that your Mac should not normally be able to run

A living literature repository for Token Economics for LLM Agents: A Dual-View Study from Computing and Economics.

Pixel-native visual RAG ported to Rust on the ruvector ANN substrate (HNSW + IVF-Flat) — screenshot/document retrieval over visual embeddings, a Rust port of PixelRAG, with a metaharness benchmark CLI: npx rupixel

Introduction course for the Microsoft Agent Framework in C#

Cloak, Honey, Trap: Proactive Defenses Against LLM Agents

gradio leaderboard region:us

Build AI, agents and workflows with RAG, MCP, harnesses, & multi-agent orchestration in a 3-week cohort

Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency

A curated reading list on harness engineering for recursive self-improvement of LLM agents (EN/ZH).

RTLScout is a agentic RTL optimization framework

A beginner-friendly, notebook-first educational project: building LLM Agent Execution Harnesses from scratch with runtime observability. / 面向零基础的 Notebook 教学向项目：从零构建大模型 Agent Execution Harnesses (执行基础设施)与运行时可观测性。

A simple, local-first RAG framework for building document Q&A applications

tiny_fnc_engine is a minimal python library that provides a flexible engine for calling functions extracted from a LLM.

多功能ai集成yunzai插件，支持openai/claude/gemini等llm多模态集成，0成本访问大模型

AI Chatbot with Streamlit, Langchain, and Mistral7b

✸ CryptoGPT — An experiment for LLMs achieving Financial Autonomy.

NGOAgent-SystemAgent

Simple, opinionated, JSON-typed, and traced LLM framework for TypeScript.

Demonstrate how to use DeepSeek-R1 models GitHub Models, Azure or Ollama

Chat with your PDF documents using this AI-powered SaaS - leveraging TypeScript, Next.js 14, Tailwind CSS, Pinecone, and Langchain.

LLM-Blender: Ensembling framework that maximizes LLM performance via pairwise ranking. Employs PairRanker to rank candidates and GenFuser to merge outputs, generating superior responses by combining the diverse strengths of multiple open-source models.

Scientific Document Insight Q/A

Foundation is a flexible, modular, and composable framework to model socio-economic behaviors and dynamics with both agents and governments. This framework can be used in conjunction with reinforcement learning to learn optimal economic policies, as done by the AI Economist (https://www.einstein.ai/the-ai-economist).

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (EMNLP'2024)

Automatic prompt optimization framework for multi-step agent tasks.

Chatbot based on Rasa Framework

Build a Dialogflow chatbot frontend using Django framework and deploy it on App Engine.

Lightweight RAG provenance middleware. Verifies every claim in an LLM response is grounded in a retrieved source - without an LLM call.

TME: Structured memory engine for LLM agents to plan, rollback, and reason across multi-step tasks.

🤖 Kubernetes for AI Agents. Self-hosted, production-grade runtime for orchestrating LLM swarms and autonomous agents. TypeScript-native.

AI Coworker that lives in slack

An end-to-end pipeline to optimize and host LLM for 100K parallel queries

TutorAI is a RAG system capable of assisting with learning academic subjects and using the curriculum and citing it. The project revolves around building an application that ingests a textbook in most formats and facilitates efficient learning of the course material.

A TypeScript library for building orchestrated framework-agnostic multi-agent AI systems

Reference Implementations for the RAG bootcamp

这是为希望学习FAISS向量数据库的同学准备的全面入门指导，帮助你快速建立相关概念，更好地阅读官方文档。

[CVPR 2025] Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval

An AI agent framework which uses hawkinsdb as long term memory

LLM agent for Obsidian with multi-turn tool-use for plugin/theme development and automation.

A framework (not only) for large-scale agent-based models

Extensions to the ML-Agents toolkit, focusing on humanoid control in Unity

A directory of practical and usable AI agents resources from applications and platforms to frameworks and utilities and other parts of the growing ecosystem

Cognitive training practices for AI agents. Self-applied. Open source. Built by an independent Vancouver yoga studio.

Learning journey - Your ultimate 1-stop learning platform to generate the best learning courses tailored to your needs using Open AI's immensely powerful LLM - GPT4

[ACL'26 Main Conference] Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning

Uses an AI agent (powered by Google Gemini via the Agno framework) to intelligently propose and execute a plan for organizing files within a specified directory on your computer.

erfect for LLM Applications! A Flutter package optimized for beautiful AI text streaming with ChatGPT and Claude-style animations.

Understanding Large Language Transformer Architecture like a child

[WWW'2025] "RTBAgent: A LLM-based Agent System for Real-Time Bidding"

Awesome-AI-Meets-Biology is a collection of state-of-the-art, novel, exciting LLMs and agents on biomedical and bioinformatic fields.

Where agents live, and flourish. 🌿

A simple IM framework based on Satori Protocol. 基于 Satori 跨平台协议的 IM 框架

Repeatable AI workflow pipelines in YAML. Export to Docker/K8s/ISO/Binary.

Visual, demo-ready multi-agent orchestration patterns powered by Foundry Local and Microsoft Agent Framework. Six runnable demos with live D3.js graph animations, real-time message tracing, and event replay

Empowering Multi-Agents, Crafting a Collaborative Future