Custom agents

Simple Long Horizon Agent - A simple yet effective AI agent for learning, experimentation, and long horizon work.

Atlas — Agent Memory on Elasticsearch. Three indices, hybrid recall with a reranker, supersession, decay, and per-user DLS isolation.

A lightweight, file-based CLI API client with age-encrypted secrets, first-class GraphQL support, and a built-in MCP server for AI agent workflows.

Browse, comment on, and assign Paperclip issues to agents — without leaving Obsidian.

Create speech-to-speech voice agents that deliver personalized self-service experiences and natural-sounding voices, seamlessly integrated with telephony systems.

Vector memory that gets smarter every time your agent uses it.

The base repository to build OmniverseKit USD agents.

GPU terminal with rich inline figures for CLI tools, AI agents, plots, documents, and remote UI.

玄幕安全团队开源汉化和修改的无需docker可在Kali Linux上直接运行的红队AI agent。

Django ER diagrams, N+1 detection, schema drift & migration-risk linting — in VS Code, a CLI and an MCP server. Static analysis: no database, no django.setup(). Free & MIT.

Web tasks that compile. Other browser tools tell your AI agent the click worked. chrome-agent reads the page back after every action and answers in JSON what actually happened. One 3 MB Rust binary, no Node, no cloud.

MCP server for Siemens NX (UG) — AI agents control NX GUI via 47+ tools

Self-designing, durable, self-improving agent orchestration: describe a goal — an agent designs the graph, a fleet of sealed full-agent nodes runs it, and a learning loop makes it better every run.

Native macOS agent control for Codex and Claude — monitor, approve, ask, and jump back from the menu bar.

Codex-verified, Claude-compatible durable local runtime for Claude Code Workflow JS, with resume, checkpoints, budgets, and Git worktrees

Use when making MiniMax H3 video prompts from media + ideas. Agent will do an formatted prompt for you.

Production AI Systems, Agentic AI & Distributed Infrastructure

FTShare financial data Python SDK｜金融数据 Python SDK，支持 market data、quantitative research、MCP、Skill 和 Agent workflows。

Karpathy-inspired Agent Skills collection

Self-evolving browser automation for Codex, Claude Code, and Cursor—learn reusable site knowledge and safely replay verified routines with agent-browser.

Wazuh MCP Server: AI-Driven SOC Automation

AI Skills Buddy, A desktop workspace for managing, installing, and synchronizing Skills and MCP Servers across AI agents.

Test your docs against the Agent-Friendly Documentation Spec

Typed React command-center components, live examples, and a portable coding-agent skill.

A local-first AI desktop planning assistant that turns goals into executable time.

Clarity - an Agent skill for clearer writing

Agent Skills for Neon Severless Postgres

State-Aware Collaboration Protocol: auditable work receipts for AI agents.

MCP server and design skill that grounds coding-agent UI work in real product screens. Two tools, npx-installable.

Run multiple AI agents and untrusted code in isolation. One command spins up a disposable Podman container — your SSH keys, dotfiles, and env files stay safe.

A modular, glass-box coding agent—inspect exactly what your agent sends to the model.

GMP学习AGENT系统

A curated research map of coding agents for robot learning

FlashREINFORCE: Critic-Free, Single-Rollout, Asynchronous RL for Agentic Language Models

安全研究领域的 agent harness

DeepSeek Harness (dsh) 自托管多用户云平台：提供隔离工作空间、持久化存储、访问控制与资源配额。Self-hosted multi-user cloud platform for DeepSeek Harness, with isolated workspaces, persistent storage, access control, and resource quotas.

Self-hosted database performance diagnostics for SQL Server, MySQL & PostgreSQL: trends, AAS insight, Top SQL, plan-change tracking, blocking & deadlock analysis. Single-process deploy, built-in MCP server for AI agents.

Collaborative Memory-Augmented Agentic Recommender System

Zero-LLM cognitive memory architecture for AI agents

An open-source Agent Skill for problem framing and assumption testing across coding, debugging, architecture, scientific research, and product decisions.

Remote coding harness exposed as a secure Streamable HTTP MCP server

Let your AI apps use your Mac: a local server and menu bar app that lets Claude, ChatGPT, Codex and other MCP apps work in your Mac's apps, files, terminal and browser, with approvals you control.

Curated motion design agent skills: GSAP, Motion, Remotion, Lottie and Rive for web animation, programmatic video and motion QA. Installable in Claude Code, Codex, Copilot.

Drop in raw talking-head takes, get back a finished, publishable video. Every rule in this repo was paid for by a rejected render.

XcodePaI is an enhanced app for Xcode 26 that brings code completion and an AI agent to your development workflow.

A Xiaomi MiMo-powered multi-agent evaluation harness for real-world code repositories.

AI prompt & agent skill that gets your money back — subscriptions, digital purchases, bookings. Polite letter first, legal escalation second. 45+ jurisdictions.

Turn successful workflows into resettable, verifiable benchmarks for AI agents.

Lightweight MCP server for sending multichannel alerts from agents to humans.

拆解 Pi Agent 源码设计的学习站点，每章配面试问答

把主线 Linux 移植到安卓手机、平板的 Agent Skill：流程、决策规则与踩坑经验 · Agent skill for porting mainline Linux to Android phones and tablets

AI-powered multi-platform C2C resale toolkit — 8 Claude Code skills + MCP server for automating second-hand selling

한국 세금 계산·세무조정 MCP — 원장 항목을 넣으면 항목 판단→세법상 조정→세무조정(소득처분)까지, 근거 조문·산식 포함 | Korean tax calculator MCP server: ledger-style facts in, item judgments, adjustments and VAT/income/corporate tax out, with statute citations

面向 Agent 的轻量级工具选择与概率决策模型，基于 Qwen3.5-0.8B；DI BFCL 工具名选择准确率 77.39%。

A set of minimal extensions that make the Pi coding agent nicer to use

A coding agent engine and CLI with cache-aware context management.

闪猫造物Flashduck — an open-source ESP32-S3 desktop duck robot with six servos, a single animated eye, wide-stance walking and two interaction systems (voice assistant / DuckClaw local agent).

End-to-end astronomy research agent: a LangGraph state machine that resolves a target, fetches multi-survey data via a 20+ archive toolbox, runs three mandatory modeling iterations with supervisor-issued repair actions, and drafts an ApJ-style manuscript only after an evidence-gated QA pass

DeepSeek API Platform integration for OpenClaw

LangChain LLM chat with streaming response over websockets

A light-weight framework for creating applications using LLMs

WangChanGLM 🐘 - The Multilingual Instruction-Following Model

Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning

a minimalistic template for dynamic self-building AI agents

The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

Code for the paper 'Multi-Agent Reinforcement Learning in NOMA-Aided UAV Networks for Cellular Offloading'

A collection of skills for AI agents by Guy on Simulink.

Browse any app normally. Spectral captures the traffic, understands what each API call does, and generates MCP tools that AI agents can call directly.

[EMNLP 2017] Code for "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog"

Agentic Research and Evaluation Suite

Copper (Cu) CoAP user-agent (JavaScript implementation)

The agent runtime built to operate.

Photoshop for agents

An RL agent for the Google Football environment

A very small user-agent (browser) and device detection library.

Agent Skills for Mojo and MAX development

Akonadi resource agent for Microsoft Exchange using Exchange Web Services (EWS) protocol

Alt util to AWS cloudwatch agent that works w/ systemd journal and sends the data in batches to AWS cloudwatch.

pi extension that exposes agent-browser as a native tool for browser automation

##Note: this is really old now, and the janky pseudo methods are probably only working out of sheer coincidence. This was an early experiment in how jargon & combinations of artificial weights in pseudocode can influence LLM behaviour without retraining. This was probably ahead of its time

ML/AI training/serving and agent sandbox operator and controller for Kubernetes

Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"

ManusMCP is a project that implements AI agent workflows using Flowise. It features specialized AI agents with distinct roles (Planner, FileWizard, CommandRunner, WebNavigator) that can be used for task automation and complex problem-solving.

SNMP Agent built with Arduino

基于Agent技术实现的Java内存马查杀、防护工具。

Open-Source AI-powered web browser. Browse the web with your own LLM API key. Alternative to Dia / Comet.

Transform and optimize your markdown documentation for Large Language Models (LLMs) and RAG systems. Generate llms.txt automatically.

一个支持定义多个角色的 AI 群聊 Web APP

Telegram bot to manage and monitor Proxmox VE from your mobile

[NeurIPS 2024] Personal Agentic AI for MultiAgent Cooperation

A JVM agent that automatically forces a proxy for HTTP(S) connections and trusts MitM certificates, for all major JVM HTTP clients

COVID-ABS: An Agent-Based Model of COVID-19 Epidemic to Simulate Health and Economic Effects of Social Distancing Interventions

Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval

Dartantic is an agentic framework designed to make building client and server-side apps in Dart with generative AI easier and more fun!

A collection of templates integrating Microsoft Teams with various AI agent paradigms.

A flagship 560-billion-parameter open-source MoE model that advances Native Formal Reasoning in Lean4 for Mathematics Formalization and Proving through agentic tool-integrated reasoning.

Ai assistant made with copilotkit ai

oly turns long-running and interactive CLI workflows into persistent, supervised sessions for humans and AI agents. Close the terminal, keep the process alive, get notified when input is needed, and jump back in from anywhere.