AI Infra agents

An Agent-Based Modelling (ABM) Framework for Unity3D

Your AI Copilot in Rust

A practical LLM learning path from clear prompting to tool use, IDE collaboration, MCP, Skills, and harness-driven agent workflows.

Amazon Bedrock AgentCore – Multi Framework Examples

Source code for our paper: "Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena"

LLM multi-agent discussion framework for multi-agent/robot situations.

인프런의 "LangGraph를 활용한 AI Agent 개발" 강의 소스코드입니다

Custom Frappe App to integrate AI Agents as DocTypes using CrewAI & Frappe Framework.

Agent Skill to help convert transformer LLMs to mlx-lm

Knowledge chatbot using Agentic Retrieval Augmented Generation (RAG) techniques. Full-stack proof of concept built on langchain, llama-index, django, pgvector, with multiple advanced RAG techniques used.

Examples and guides for building Gen AI applications on the watsonx platform.

A post-retrieval temporal layer for RAG systems — validity filtering, time decay, document kind classification, and hybrid reranking in one pipeline.

Motor de Inteligencia de Enjambre para el mercado hispano 🐟 | Sube cualquier informe, predice el futuro al instante | Adaptación en español por EnPíxeles Lab

Evaluate your agent memory on real-world dialogues, not LLM-simulated dialogues.

A multi-agent recruitment assistant that leverages Microsoft AutoGen framework to streamline hiring processes. The system employs specialized AI agents working in concert to automate resume screening, candidate evaluation, and interview preparation.

Train a 29M parameter GPT from Scratch

Spore Agent——更加友好的人机交互Agent。Spore Agent — An AI agent built for better human interaction.

A Model Context Protocol (MCP) server for platform-agnostic file capabilities, including advanced search/replace and directory tree traversal

Training Recipes for Agentic Reinforcement Learning in LLMs: A Survey

🦞 LobsterPress（龙虾饼） - Cognitive Memory System for AI Agents 基于认知科学的 LLM 永久记忆引擎

智能旅行规划助手 - 基于 LangGraph + MCP + RAG

Voice dictation menu-bar app for macOS. Press a hotkey, speak, transcript appears at the cursor. Whisper runs locally via WhisperKit on Apple Silicon — no audio, text, or telemetry leaves your Mac. MIT, Swift.

Anima: an experimental cognitive architecture that models internal state, conflict, and decision-making. Uses LLMs as an interface, not as the core.

Create and install AI agents to automate your tasks

Capka AI — An open-source, self-hosted sandbox for AI agents. A community-driven alternative to Claude's Cowork

Edu-RAG：面向 K12 / 学科教育场景的轻量化 RAG 智能助教开源框架，依托教材、教辅知识库实现精准答疑、习题解析与个性化导学，有效抑制大模型知识幻觉，开箱即用快速落地 AI 教育应用

RTLScout is a agentic RTL optimization framework

基于Go的轻量的QQ官方机器人框架，此为基于原版Polarix的自用定制版本

An AI Assistant to answer user queries based on your own knowledge base!

OpenclawInterSystem (OIS) - A collaboration framework for multi-agent OpenClaw deployments

Synapse is a powerful package that enables seamless integration and management of AI agents within Laravel applications. Inspired by Langchain and Laravel Saloon, it provides a flexible framework to create, manage, and scale AI agents using customizable memory options, dynamic prompts, and multiple integrations, including OpenAI and Claude.

This repository demonstrates how a simple memory file can be incorporated into an Agents routine using the AutoGen framework.

An interactive integration of yFiles for HTML with LlamaIndex to visualize the knowledge graph used for query resolution.

A collection of prompts, skills, and agent rules for AI-powered development workflows.

LLM-powered autonomous agent with hierarchical task management

Open-source multi-agent platform that structures software engineering as a coordinated team of specialized AI agents. It enforces strict role separation, isolated execution sandboxes, structured communication, and secrets management.

Chatbot for Indian Law using Llama-7B-chat using Langchain integration and Streamlit UI.

TermHub: Open-source native terminal control gateway for AI Agents. Let LLMs/AI Agents fully control & automate iTerm2 / Windows Terminal: manage tabs, panes, sessions, send commands, capture output programmatically.

The Karpathy treatment for OpenClaw - stripped to ε. 515 lines of Python, 6 files, one dependency.

从零构建 AI Agent：LLM 大模型应用开发实践

The purpose of the "Meta Agent with More Agents" project is to dynamically solve complex queries by breaking them down into smaller tasks and assigning each to specialized AI agents. The Meta Agent coordinates the process, leveraging a ReAct Agent for tool-based tasks and a Chain of Thought Agent for reasoning-based tasks. The system's flexibility.

A simple local Retrieval-Augmented Generation (RAG) chatbot that can answer to questions by acquiring information from personal PDF documents.

CS294/194-196 Large Language Model Agents

The repository for the scripts and materials for the paper "Simulating Opinion Dynamics with Networks of LLM-based Agents"."

One agent. Every surface. Your rules.

🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects. It ships as a repo containing a kernel (constitution), CLI tools, and templates — which generates workspaces where you actually work.

Adaptive Reasoning Engine for Efficient and Context-Aware Intelligence

HazelJS - Agent OS for TypeScript backends.

Agent-first Rust/Axum backend harness for SDD-driven Clean/Hexagonal/DDD services, ECS-style runtime composition, counter-service reference chain, progressive local→VPS→k3s topology, and entropy-resistant agent context/naming grammar.

Apple Documentation Markdown For RAG

SAFi is an open-source runtime governance engine for agentic AI that enforces your policies, governs agent actions, and records every decision for audit.

Best DX + AX for Building the Best UX. An ultra-lightweight (~2.5KB) pure vanilla JavaScript framework with signal-based reactivity and built-in AI agent support.

Save 47% on Manus AI credits automatically. Zero downsides. Pays for itself in ~27 prompts. Free MCP Server (PyPI) + $12 Manus Skill bundle with Fast Navigation (115x speed boost).

面向 AI Agent 入门者的教学项目。通过一个完整的电商客服 Agent，让你亲眼看到每一轮对话中 Agent 内部经历了哪些环节、做了什么决策、调用了什么工具、生成了什么 Prompt。

A demo project that deploys Agent Framework agent to Foundry Hosted Agents

Simple framework for training and evaluating math reasoning agents using local models, GRPO and vLLM.

AI agent for Android. Runs in Termux. Controls your phone via natural language.

Your one-stop repository for 100% free, high-quality AI certifications offered by top universities, companies, and platforms.

一款跨平台智能笔记 Agent 应用，支持多格式笔记、本地知识库、AI 智能助手、向量语义检索 。

An open-source RAG platform to explore the unsealed Jeffrey Epstein court documents.

PowerFM is an open-source repository for foundation models in the power and energy domain. It both maintains original projects and collects community-contributed open-source projects, featuring fine-tuned and domain-trained models for tasks like load forecasting, fault detection, grid simulation, and agent control.

AI evaluators CLI for your AI apps and Agents - Dynatrace AI Observability

A Lisp with first-class LLM primitives, implemented in Rust

static region:us

gradio mcp-server region:us

OTel Plugin for Hermes Agent

Paper List of Agent Memory Systems along Four Axes

Change management, SkillOpt optimization, and evidence-gated evals for agent skills.

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, trade-offs, and numbers, not prompt tips

ZhuLing — Zero-config AI Agent framework for Java. One YAML to launch Agents on Spring AI + DDD, with MCP tools, full observability and a ReAct core. Ai Agent 快速开发框架

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.

An educational macOS app: build and chat with a tiny language model, trained on your Mac

Open-source C# agent runtime for AI NPCs and in-game agents. Structured context, ReAct tool use, complex task planning, memory, and reliable actions for Unity, Godot, Unreal Engine, and servers.

The agent underlying development framework in Rust.

346 reusable character attributes for AI agent personas — compose, measure, and port system-prompt personas. Build once. Keep personality everywhere.

USL is the storage-first reference implementation of the Agent Session Protocol (ASP). ACP handles the live present (editor↔agent interaction); ASP handles the durable past and cross-runtime migration; USL is the storage engine behind ASP.

1802 live x.ai/bot shares for Grok Bot you can Add — bilingual EN/中文 catalog with shelf navigation, field cases, and JSON schema. Not prompt dumps.

Open Source Embeddings Optimisation and Eval Framework for RAG/LLM Applications. Documentations at https://docs.vectorboard.ai/introduction

Python framework for building scalable multi-agent systems with built-in orchestration, LLM integration, and intelligent task processing. Features dynamic scaling, fault tolerance, and advanced load balancing.

網頁聊天機器人 | tensorflow implementation of seq2seq model with bahdanau attention and Word2Vec pretrained embedding

Training & Implementation of chatbots leveraging GPT-like architecture with the aitextgen package to enable dynamic conversations.

AME IS DISCONTINUED, SEE: https://github.com/mochiagents/mochi

Soulscript is a framework-agnostic standard for defining rich agent personalities that evolve over time.

Strawberry Groq is a streamlined demo application showcasing the power of chain of thought reasoning using PocketGroq. Experience the advanced capabilities of Groq's language models, enhanced by reasoning techniques inspired by OpenAI's "Strawberry" o1 LLM.

LLM Dynamic Planner - Combining LLM with PDDL Planners to solve an embodied task

Durable agent runtime. Sessions survive crashes. Agents are just files. One binary, zero dependencies.

这是一个面向 LLM Agent 的知识库脚手架，用于把原始资料逐步编译成可维护、可交叉引用、以中文为主的 Markdown Wiki。

[ACL 2026] LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark

Agentless Lite: RAG-based SWE-Bench software engineering scaffold

CLI for AI-assisted manual code review

[NeurIPS 2025 𝐒𝐩𝐨𝐭𝐥𝐢𝐠𝐡𝐭] AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling

[ICLR 2026] Meta-RL Induces Exploration in Language Agents

Goal-Driven agent for long-running tasks, docker-isolated workers, intelligent task decomposition, and autonomous execution

Agentic AI framework built using LangGraph and Multi-Agent Control Plane (MCP) for building structured, goal-driven multi-agent systems.

Self-hosted & federated platform for AI IDE/Tools Rules and Commands via WebUI & CLI - Generate, browse, store, share AGENTS.md, CLAUDE.md, and more

Agentic AI na Prática: RAG, LLMs e Agentes Inteligentes

Customer Chatbot Solution Accelerator empowers organizations to build intelligent, conversational customer service experiences by leveraging Microsoft Foundry's agent framework.

Build AI agents you can trust in production. AgentFlow4J is a framework and runtime for governed, stateful multi-agent systems on the JVM. Human approvals · Checkpoints · Budget controls · Tool policies · Durable execution