GitHub agents

The first open-source @base agent.

AgentWard – Built for all, hardened for OpenClaw.

Mozek – lokální sémantická druhá paměť (RAG) s MCP pro AI agenty. Multijazyčné, Obsidian-kompatibilní, soukromé (běží u tebe).

A decentralized micro-settlement protocol enabling autonomous AI agents to pay publishers for premium content via Circle Programmable Wallets and x402 nanopayments.

Agentic Kernel Optimization — advanced & eXtensible: a closed-loop, campaign-based multi-agent system for optimizing GPU kernels (benchmark-swappable; default flashinfer-bench).

The ATLAS Agent helps answer questions about the MITRE ATLAS Framework by leveraging the ATLAS Knowledge Graph.

Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants

Living Memory Coordinate-5: five-axis memory architecture for long-running LLM agents. Minimal SQLite + production PostgreSQL/pgvector reference impls, multi-channel recall pipeline, LLM-proposed hippocampus, persona policies, VPS 7×24 deployment shape. Not another vector DB.

OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Qwen2.5-VL-72B with 73% fewer frames on LVBench.

Claude Code 源码深度研究，包括 Foundations/Execution/Infrastructure 三大章节和 23 个子系统的架构分析拆解。

🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for securing AI agent tool use and skill ecosystems

Web UI Coding Agent | ReAct Loop | Mobile Supported

Take the 100 Days of AI challenge - learn one AI concept a day, from machine learning basics to AI agents in production, in 100 days.

Local-only web GUI for inspecting agent skills (SKILL.md) across user, project, plugin, cache, and marketplace sources

A command line for Z-Library. Search, download and send to Kindle.

Tamper-evident runtime evidence for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.

A portable AI-assisted Knowledge OS starter kit for Obsidian, Codex, Claude Code, and compatible AI coding agents.

CLI toolkit for AI agents — turns search queries into structured web evidence (JSON). Provider-extensible architecture, designed to be called from Agent Skills (Claude Code, Codex, Cursor, etc.).

Official Pulumi Agent Skills for writing, migrating, and operating infrastructure with AI coding agents

Collection of skills giving agents guidance on design/eng concepts LLMs aren't trained on.

Visual navigation maps for Expo/React Native apps: agent-explored screenshots, flows, and an interactive .appmap visualiser

A Complete Open Source Agent AI Framework For Unity

Rust Agent Development Kit

This code is an implementation of a chatbot using LLM chat model API and Langchain.

A collection of the best uses and tools achieved with GPT4 from OpenAI 💡

A lightweight Python library that allows any LLM agent to self-improve through feedback, without retraining models.

Appwrite's AI assistant 🧠

Official code for the paper: Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

prompt to app ai coding agent

AI Agent Team SKILL - 基于 newtype-profile 架构的 AI Agent 协作系统

LangGraph-GUI backend with fastapi

The long-term memory for your Superagents 🥷and LLMs 🤖. Built with GraphRAG, Knowledge graphs and autonomous ai agents

Opinionated DevPod workspace configs for agentic engineering — Claude Code, shared secrets, VS Code extensions, ready on first launch.

Magic Resume 是一个由 AI 驱动的智能简历优化器。它基于 Next.js 构建，旨在帮助用户根据目标岗位（JD）的要求，智能地分析、优化个人简历，并提供专业建议。

The ChatGPT Long Term Memory package is a powerful tool designed to empower your projects with the ability to handle a large number of simultaneous users and external sources.

Grapheteria: A structured framework bringing uniformity to agent orchestration!

A SDK for building and deploying your own chatbot using NextJS in Vercel. This chatbot SDK helps you to build a gpt chatbot using the OpenAI Assistant API, in few clicks you can get a chatbot deployed in Vercel and Iframable in your website for any use case. Created by OpenAssistantGPT.

This repository contains a fullstack chatbot project based on the ChatGPT `gpt-3.5-turbo` model.

保险行业回访外呼机器人

Open Source React Chat Widget. Ready for use and can be connected to any backend like Chatbot/NLP/Live Chat engine or messenger.

PHP Wechaty is a Conversational SDK for Chatbot Makers Written in PHP https://github.com/wechaty/docker-php-wechaty-getting-started

A voice assistant powered by OpenAI's ChatGPT language model, currently available in six languages.

Open source npm script to talk to your Postgres database with GPT.

CLI tool that generates commit messages from git changes, reviews code for quality issues, and provides debugging assistance. GitHub Action available for automated PR reviews.

Generates reply automaticly for https://x.com, the fastest chrome extension for X/Twitter replies!

Audio to summary with openAI Whisper & GPT 3.5/4 using streamlit

🧨🧨🌟 FREE BOOK @ RailsAI.com: Ship your AI MVP fast with Rails

A corporate law RAG system with innovative retrieval and contextual strategies

AnyGen AI Skills for AI Agents

Perform Data Analysis using Agentic AI - The code to accompany my youtube video

A platform for intelligent agent learning based on a 3D open-world FPS game developed by Inspir.AI.

Fuzzy Logic "Fuzzy Associative Memory" (FAM) for fuzzy control systems, decision-making, artificial intelligence / AI, game agents & bots, etc. Ruby language.

Tilly is a relationship journal. An offline capable PWA that feels really good. It has an AI agent for maximum convenience.

Cody Product Builder is a guided workflow (agent skill) that helps knowledge workers and domain experts turn ideas into real products with AI. It structures your thinking from idea to shipped version so you can build without becoming a developer and without the work collapsing into chaos.

Bridge the gap between your codebase and your AI editor. CCM transforms static source code into a dynamic, queryable Knowledge Graph, enabling AI agents to navigate, understand, and reason about your project with surgical precision

Parallax is ALL YOU NEED? 他山之石，可以攻玉：如何让你的AI Agent更加可靠？How to Make Your AI Agent Truly Reliable?

An agentic macOS desktop tool

Design a control system on Matlab for robots so that they are able to form a defined shape, then Artificial Potential Field method is applied for robots to avoid obstacles

A Multi-agent Learning Framework

PyTorch implementation of Generating Multi-Agent Trajectories using Programmatic Weak Supervision

Claude Code 에이전트 활동을 실시간으로 시각화하는 로컬 대시보드. 나의 활동기반으로 잔디를심고 게임을 곁들인!

Deploy smart and secure conversational agents for your employees, using Azure. Able to use both private and public data.

A tool for fast and accurate summarizing of variant calling format (VCF) files

New Relic CLI is a command line tool which is used to operate New Relic objects(Synthetic monitors, alert policies, conditions, account users etc). You can use it easily to list/get/create/delete these objects. It can be used to backup your New Relic configuration data and restore in the future. It is easy to be used other than calling different REST API endpoints.

I specifically cover the following topics: Java primitive data types, declaration statements, expression statements, importing class libraries, excepting user input, checking for valid input, catching errors in input, math functions, if statement, relational operators, logical operators, ternary operator, switch statement, and looping. How class variables differ from local variables, Java Exception handling, the difference between run time and checked exceptions, Arrays, and UML Diagrams. Monsters gameboard, Java collection classes, Java ArrayLists, Linked Lists, manipulating Strings and StringBuilders, Polymorphism, Inheritance, Protected, Final, Instanceof, interfaces, abstract classes, abstract methods. You need interfaces and abstract classes because Java doesn't allow you to inherit from more than one other class. Java threads, Regular Expressions, Graphical User Interfaces (GUI) using Java Swing and its components, GUI Event Handling, ChangeListener, JOptionPane, combo boxes, list boxes, JLists, DefaultListModel, using JScrollpane with JList, JSpinner, JTree, Flow, Border, and Box Layout Managers. Created a calculator layout with Java Swing's GridLayout, GridBagLayout, GridBagConstraints, Font, and Insets. JLabel, JTextField, JComboBox, JSpinner, JSlider, JRadioButton, ButtonGroup, JCheckBox, JTextArea, JScrollPane, ChangeListener, pack, create and delete files and directories. How to pull lists of files from directories and manipulate them, write to and read character streams from files. PrintWriter, BufferedWriter, FileWriter, BufferedReader, FileReader, common file exceptions Binary Streams - DataOutputStream, FileOutputStream, BufferedOutputStream, all of the reading and writing primitive type methods, setup Java JDBC in Eclipse, connect to a MySQL database, query it and get the results of a query. JTables, JEditorPane Swing component. HyperlinkEvent and HyperlinkListener. Java JApplet, Java Servlets with Tomcat, GET and POST methods, Java Server

INDUSTRY ALERT: The Subprime Code Crisis. A data-driven analysis of how AI assistants inflate a bubble of technical debt. Featuring research on 211M lines of code, this report exposes the "Placebo Analytics" of AI productivity and provides a framework for engineering governance.

Debuggable runtime for AI agent workflows. DAG pipelines, artifact lineage, and replayable runs.

🔍 AI-powered diagnosis for Scikit-learn models: Detect overfitting, data leakage, class imbalance & more with LLM-generated insights

A unified python SDK supports OceanBase or OceanBase seekdb, more efficient and easy-to-use.

Neural Language Model for Go

A RAG API server written in Rust following OpenAI specs

A Go library implementation of LightRAG - an advanced Retrieval-Augmented Generation (RAG) system that uniquely combines vector databases with graph database relationships to enhance knowledge retrieval.

DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats

一款基于 langchain + electron开发的多平台桌面端 Chat 客户端 支持本地知识库，tool调用，多个智能agent调用 目标尽量实现全离线本地可执行的智能agent

Agent Relay Protocol — Stateless WebSocket relay for autonomous agent communication

Distributed model predictive control for multi-agent point-to-point transitions.

A multi-agent reinforcement learning framework for optimizing coverage and connectivity in Space-Air-Ground integrated networks. This project simulates and trains intelligent agents to coordinate satellites, UAVs, and ground stations for efficient network deployment.

An AI agent memory framework that converts an agent’s own interaction traces—both successes and failures—into reusable, high-level reasoning strategies. These strategies are retrieved to guide future decisions, and the loop repeats so the agent self-evolves.

Turn remote MCP servers into local command workflows.

A locally-running multi-agent human in the loop system for deep, interdisciplinary research with only 4 dependencies.

Sektörde Kampüs Kapsamında Üretken Yapay Zeka Yardımı ile Chatbot Geliştirme Temelleri dersinin notlarını bu repository üzerinde paylaşaca…

Framework: Multi-Agent LLMs For Conversational Task-Solving (MALLM)

SpikeAgent is a multimodal LLM-based AI agent that automates and standardizes the spike sorting pipeline

LLMCompiler is an Agent Architecture designed to speed up the execution of agent tasks by executing them quickly in the DAG. It also saves the cost of redundant token use by reducing the number of calls to the LLM.

AI-driven personal finance automation using n8n and Google Drive to extract and categorize PDF expenses into Google Sheets.

Claude Code skill for using Codex CLI as an execution specialist for implementation-heavy coding work, multi-file refactors, and wrapper-based execution flows.

Enzim Coder is a Linux desktop app for working with AI coding threads, workspaces, Git context, file browsing, and agent sessions in one place.

Powerful AI Assistant in Roam Research

Build an embeddable RAG Chatbot for your website using Cloudflare Workers.

Go library for building intelligent, co-operative agentic software and LLM-powered workflows, focusing on improving results for small, open source language models that scales to any LLM.

offical code of paper 'SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding'

MCP server for Claude Desktop to manage your n8n workflows

AI agent platform enhanced with Agent OS architecture inspired by Claude Code, built on DeerFlow

Fun LLM Agent Projects I Designed & Built

Build and Deploy AI Agents with Python, Docker, FastAPI, LangChain, and LangGraph

The Python Harness for Production AI Multi-Agent Systems

Automatic context preservation for Claude Code. Never lose work to compaction again. 7 hooks, 187 semantic patterns, 3 MCP tools.

Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.