Custom agents

Open bridge layer connecting local AI Agent CLIs to web, H5, mini programs, apps, IM, and custom clients.

JARVIS AI is an open-source AI assistant built for automation, productivity, and intelligent workflows. Featuring natural conversations, customizable tools, API integrations, memory, and a modern interface, it provides a powerful foundation for building personal assistants, AI agents, and next-generation applications.

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

Jarvis - The AI teammate inside ERPNext.

Let Claude edit your Figma file for you — bulk-rename layers, swap variants, bind colour variables, pour in real copy. Describe the change in plain words, watch it land in the file in seconds. A small plugin keeps Figma talking to your terminal.

DeepSeek Harness (dsh) remote access from your phone: Android / iOS mobile client, peer-to-peer over iroh across networks, no server to set up, relay fallback sees only ciphertext; Android can also run dsh locally · 手机远程使用电脑上的 DSH，点对点直连，不用架服务器

SemaPLC is an open-source agentic IDE for generation, verification, and simulation of PLC Programs from natural language.

Agent skills for Sonilo's licensed music, sound-effects, dubbing, and audio-ducking API

DeepSeek V4 Coding Agent extension for Visual Studio

ASPIRE: Agentic /Skills Discovery for Robotics

Stateful API logic for agentic applications using vLLM

Agent-first Rust ASR stack built on a real in-process pure-Rust Whisper engine (no FFI, no Python, no subprocess), with adaptive Bayesian routing across whisper.cpp/insanely-fast-whisper/diarization backends, real-time NDJSON streaming, DTW word timestamps, SQLite run history, and a conformance harness.

A calm agent multiplexer with familiar IDE features, for macOS, with an iPhone app.

🎓 校招网申智能体 - AI驱动的网申表单自动填充Chrome插件

Music generated agent

Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, ownership, handoff, verification, evidence, approval, recovery) enforced in code, plus a reproducible conformance benchmark. Apache-2.0 code, CC BY 4.0 specification, zero dependencies, Node 18+.

A multi-agent academic paper workflow for structured writing, iterative polishing, fact-checking and rule-based academic compliance optimization. Suitable for 0–30 pages course papers and seminar theses.

Android No-Root Linux Runtime · Native Agent Harness · PTY Terminal · Workspace & Tool Ecosystem

mo-code 是 mortis 从零实现 Claude Code 核心功能的实验项目，目标是实现一个可运行、可解释，并重点研究安全边界的终端 Coding Agent。

LLM agent skill files for PyMC and PyTensor

Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya

Myriad is a self-hosted homepage and creative studio: aggregate your platforms, show a library, and run a site-wide persona, 2.5D face, and Tapp apps you own.

Bounded, evidence-driven SKILL.md evolution under frozen evaluation and safety contracts.

ADHD-friendly study companion agent for Claude Code: spaced repetition, small-chunk teaching, Feynman reflection

反推爆款带货短视频 → 即梦/Seedance 重生成 → 剪映草稿交付的 agent 流水线。单日 16 条实战验证。作者:汪自立,7 年抖音直播操盘手(生鲜/珠宝/烘焙,单场 GMV 306 万),踩坑与打法全部固化成可复用 skill。

Give Grok Bot or Muse the sites you are already signed into in Chrome. A Manifest V3 extension and a local native host, no password pasted anywhere.

AAI (Agent App Interface) is an open protocol that makes any app accessible to AI Agents. One aai.json descriptor makes your desktop or web app(SaaS) instantly discoverable and callable. Skip slow GUI automation; go from invisible to Agent-native in milliseconds.

A beginner foundation skill for AI coding agents — from product idea, data and Git to security, deployment and launch.

Structured project progress and safe cross-agent handoffs in one local Markdown file

Evaluate GitHub projects from an outside contributor's perspective. An agent skill with a read-only collector and evidence-based methodology.

Extensions, skills, prompts, themes, and developer tools for the Pi coding agent.

ctx-wire runs your commands, compresses the output with declarative filters, scrubs secrets, and hands your agent a short result. The full log stays on disk for when something actually fails. Cut the noise on the wire.

120 patterns that make writing read like AI slop, with an agent skill for Claude Code and Codex.

ORA: Open Robot-Use Agents

A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they spend your usage window. It reads your plan's usage, counts agents across every session, and asks in Claude Code's own dialog.

REA (Reverse Engineer Anything) 深度技术调研：让 AI coding agent 无源码逆向软件的 MCP 工具链

nsq — run several AI coding agents in your terminal and stop babysitting them. Open-source CLI by NeuroSquad.

Kubernetes-native runtime for persistent, collaborative AI agents.

Python MCP server for SolidWorks: lets Claude and other AI agents build parts, assemblies and drawings through the SolidWorks COM API (pywin32).

Your agent finally sees the Compose UI it builds. Jetpack Compose and Compose Multiplatform Previews in your browser, redrawn a second after every save — no Android Studio, no build.

WebJs is an AI-first full-stack JavaScript web components framework. You get production-ready architecture from your very first prompt.

知识图谱 neo4j 答案查找 + 机器学习 分类模型 问题分析 = 电影知识库问答机器人

jemma & her ai agents that build software

Make your whatsapp BOT talk like a human using ChatGPT!

Create AI support agents with your documents.

Zabbix agent for Arduino

Learn to create agents in Unity ML using Deep Reinforcement Learning with Tensorflow.

An open-source, configurable sdk for creating an agent that can play in the Adventure.Fun world.

MCP OAuth Proxy incl. dynamic client registration (DCR), MCP prompt analytics and MCP firewall to build enterprise grade MCP servers.

一个用于BiliBili网站实时热点&舆情分析的AI 智能体

An implementation of "Generative Agents: Interactive Simulacra of Human Behavior"

Function Calling Benchmark & Testing

An interactive logic studio for building agent systems

Multiple instructed-LLMs engage in multi-round "self-questioning" to seek the optimal solution, borrowing from the idea of debate, iteratively refining the current problem-solving process, and finally selecting the optimal solution to give a conclusion.

An instrumentation java agent that is able to inject itself into the running process

Open source endpoint agent providing host information to Zeek. [v2]

Evolutionary Reinforcement Learning for Dino Game: Train an AI agent to master Google Chrome's Dino Game using a genetic algorithm and reinforcement learning.

星搭小星 - AI微信小程序智能助手.

AI agent that searches job platforms for openings matching your profile and exports the results as a scored CSV

Efficient Large-Scale Multi-Drone Delivery Using Transit Networks

Code for training embodied agents using IL and RL finetuning at scale for ObjectNav

{ "releases": { "2.0.4": [ "[Fixed] Refresh for Enterprise repositories did not handle API error querying branches - #7713", "[Fixed] Missing \"Discard all changes\" context menu in Changes header - #7696", "[Fixed] \"Select all\" keyboard shortcut not firing on Windows - #7759" ], "2.0.4-beta1": [ "[Fixed] Refresh for Enterprise repositories did not handle API error querying branches - #7713", "[Fixed] Missing \"Discard all changes\" context menu in Changes header - #7696", "[Fixed] \"Select all\" keyboard shortcut not firing on Windows - #7759" ], "2.0.4-beta0": [ "[Added] Extend crash reports with more information about application state for troubleshooting - #7693", "[Fixed] Crash when attempting to update pull requests with partially updated repository information - #7688", "[Fixed] Crash when loading repositories after signing in through the welcome flow - #7699" ], "2.0.3": [ "[Fixed] Crash when loading repositories after signing in through the welcome flow - #7699" ], "2.0.2": [ "[Added] Extend crash reports with more information about application state for troubleshooting - #7693" ], "2.0.1": [ "[Fixed] Crash when attempting to update pull requests with partially updated repository information - #7688" ], "2.0.0": [ "[New] You can now choose to bring your changes with you to a new branch or stash them on the current branch when switching branches - #6107", "[New] Rebase your current branch onto another branch using a guided flow - #5953", "[New] Repositories grouped by owner, and recent repositories listed at top - #6923 #7132", "[New] Suggested next steps now includes suggestion to create a pull request after publishing a branch - #7505", "[Added] .resx syntax highlighting - #7235. Thanks @say25!", "[Added] \"Exit\" menu item now has accelerator and access key - #6507. Thanks @AndreiMaga!",

🚀 Clone your OpenClaw AI Agent to a new device in ~25 minutes — configs, memory, skills, everything.

Odin Runes, a java-based GPT client, facilitates interaction with your preferred GPT model right through your favorite text editor. There is more: It also facilitates prompt-engineering by extracting context from diverse sources using technologies such as OCR, enhancing overall productivity and saving costs.

🐊 Snappy's unique approach unifies vision-language late interaction with structured OCR for region-level knowledge retrieval. Like the project? Drop a star! ⭐

self-hosted AI agent gateway written in Go, inspired by OpenClaw. Single binary, low memory, fast startup.

A local macOS HTTP API gateway that exposes Apple apps (Reminders, Messages, etc.) to AI agents

[ACL 2025 Findings] Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors

rtfmbro provides always-up-to-date, version-specific package documentation as context for coding agents. An alternative to context7

Memory Agent monorepo

Live view of Claude Code sessions and the ability to search them

Skills for AI agents to process presentations - helpful for teachers and speakers.

Telemetry for OpenClaw - Captures tool calls, LLM usage, agent lifecycle, and message events. Outputs to JSONL file and optionally to syslog for SIEM integration.

My own agent skills for tools I use

Security plugin for OpenClaw agents - prevents secret leaks, PII exposure, and destructive command execution

A Collection of High Quality research papers and open-source projects about LLM-agents

The Vibe Coding++™ platform - orchestrate multiple AI agents, experiment with isolated attempts, ship code you understand. Multi-agent kanban with MCP integration.

AI voice assistant starter app for Flutter built with LiveKit

A skill that convenes a panel of CLI-based AI agents (Claude Code, Codex, Gemini CLI) to deliberate on engineering problems through structured multi-stage discussion, peer review, and synthesis

[NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents

Official Python SDK for the ScrapeGraph AI API. Smart scraping, search, crawling, markdownify, agentic browser automation, scheduled jobs, and structured data extraction

Example for connecting Linear Agents SDK with Claude Managed Agents

A system prompt that turns an LLM into a Senior Product Manager that walks you through creating an agent-ready PRD via chat.

Open Source Agentic Coding Harness

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

A lightweight PHP utility to detect if your code is running inside an AI agent or automated development environment.

CLI tool for managing iKuai routers — network, VPN, firewall, users, QoS and more from the terminal. AI-agent ready.

Three.js MCP server — inspect and edit scenes, materials, shaders, lights in real time from any AI agent

A cross-platform AI agent orchestrator in C++ that turns any device — including your phone — into a self-contained, multi-agent automation platform

基于时序动态的图计算和图谱数据库引擎AbutionGraph，将实体 - 组件 - 系统与基于流的 AI 编程深度结合，构建可演进的数字孪生与世界模型。构建以本体驱动为核心，串联实时数据、业务逻辑与智能 Agent，实现从数据源探知、知识库、记忆编程、智动化工作流到实时业务推理与行动决策的全链路闭环。

This repository stores personal AI Agent skills in a scalable directory layout.

Modular MCP server for OPNsense firewall management - 88 tools providing access to 2000+ methods through AI assistants

Give your AI agent accurate economic data. 330K indicators from FRED, World Bank, IMF, Eurostat & more. MCP server + web UI.

陪伴型ai agent-人机恋适用

A framework for building nexuses of agents -- where intelligence emerges from interaction, not isolation.

Claude Code skill that enables Claude to extract, analyze, reverse engineer iOS apps

Open skill for capturing AI agent work as structured traces.

a skill for lovart agent