Custom agents

Curated agent skills for CesiumJS development.

Agentes e templates para criação de slides animados com D3.js em HTML

宠物自媒体一站式创作Agent

A lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.

Self-hosted Laravel monitoring agent. Drop-in Nightwatch alternative, open-source.

Agent skills for squirrelscan website audit tool

Continuous review for agents

Native macOS app for Pi coding-agent. Browse, resume sessions, and run Pi terminal tabs locally or over SSH.

Learning platform where a multi-agent builder turns a one-sentence goal into a private course and a course-scoped RAG tutor teaches it with lesson citations. Public evals.

The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.

Local AI multi-agent orchestration desktop app (Tauri · LangGraph)

Cross-platform office automation CLI -- WPS COM on Windows, LibreOffice headless on macOS/Linux. Same commands, any platform.

Local-first SSH/SFTP workspace for humans and coding agents: visible operations, shared sessions, integrated files and discoverable plugins.

二次元 / 动作游戏（ACT）战斗设计方法论 + 行业知识库，任意 AI agent（Claude、GPT、Cursor…）可用。设计玩家角色与 Boss → 审阅级 HTML + 落地资源表；招式集 / 视觉预警 / 配队等战斗约定由你的项目自定义，绝不强加。

A toolkit of Claude Code skills for doing economic theory with LLMs: math-proof (single-pass proving), codex-math (adversarial verification), and co-math (multi-agent proof projects). With a VCG-for-grade-inflation case study.

Public documentation and support hub for ECC Tools, the GitHub App that turns repo history into reusable workflows, skills, rules, hooks, audits, and rollout plans for AI coding agents.

Agent Harness (Loop Engineering) dev guide — complete architecture & core modules, based on production-grade agent source: Claude Code, DeepSeek Harness, OpenCode, Pi, Codex, OpenClaw & Hermes. English & 中文

Native terminal multiplexer for coding agents. Persistent sessions, Git worktrees, diffs, and an integrated editor. Built with Rust and GPUI.

A judgment-first coding agent runtime

Function Calling Benchmark & Testing

This repository is for active development of the Microsoft 365 Agent SDK components for JavaScript

Agent-native AI video factory: one brief → narrated, subtitled, scene-editable videos (shorts & long-form). Deterministic HTML rendering, free keyless stack, Korean-first.

Conversational-AI framework for Go.

humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, speculative abstractions. Test-gated, behavior-preserving.

Open, structured corpus of US primary law: 2M+ sections of state statutory codes, the US Code, and state constitutions, plus the ingestion pipeline that builds it. Data on Hugging Face (CC BY 4.0); scrapers Apache-2.0. Quarterly snapshots.

"AI 桌面管家 · 多 Agent 协作编排 · 一句话调动团队完成复杂任务

让任何 Agent 帮你学懂 Vibe Coding 术语

Open specification for cryptographic agent authorization in commerce

open source agent in vscodium

Agent-friendly InstSci workflow preview for legal paper acquisition, browser evidence, and Zotero handoff

Agent skill: turn any image into a postage-stamp style card with perforated edges and true transparent background

Build interactive 3D worlds with high-quality assets from Thrixel and your AI agent of choice.

会表情的 AI头像 — expressive, zero-dependency helmet avatar for AI agents (MIT)

产品宣传视频创作 Skills：从产品判断、分镜、素材、HyperFrames 剪辑到 BGM 设计的完整 Agent 工作流

OpenAssist is a voice-first personal AI assistant for macOS and iPhone. Built with Codex on the Codex app server: tasks, reminders, notes, projects and AI agent work in one place.

Agent skill: read STEM papers that answers Heilmeier's Catechism, so you get the big picture in one minute.

Aetheris 灵思 Agent — 全功能学术研究智能体（101 技能 / 60 科学数据库 / 论文管线 / 6 子智能体）

Hermes Agent conversation integration for Home Assistant

Multi-agent engineering framework: evidence packs, runtime validation, task decomposition, cross-window worker execution, and CI artifact verification for Codex.

A practical governance framework for organizations adopting the Model Context Protocol (MCP), the open standard that lets AI agents connect to external tools, data sources, and systems.

Toolmaker Agent is an Agentic AI SDLC platform — humans and agents collaborate on the same structured data model.

A WebMCP benchmark, measures WebMCP against other browser-agent interfaces.

This web browser has been designed to help your agent debug and develop complex web applications. (MCP Server)

A Consistent Data Visualizer for Agents and Humans

Desktop multicam recorder for macOS: records your screen and webcam in sync, then Claude Code or Codex edits the final video — shot selection, subtitles, graphics and SFX.

Task orchestration and engineering delivery for AI agents: definition, assignment, supervision, checks, verification, acceptance and rework. Knowledge/memory provide context. Reusable MCP/CLI capabilities; Claude Code/Codex adapters. Full supervision needs host adaptation and validation. Independently developed; noncommercial.

豆包办公模式、腾讯workbuddy、千问办公、ChatGPT agent内置的skills、专家团、连接器

The Open Source Voice Agent Platform - Build voice agents by connecting nodes in a canvas, deploy them to handle inbound and outbound phone calls, and monitor every call, latency and cost.

A product-validation system for AI agents: idea → logo → product → brand → launch video in two hours. Desktop app + skills for Claude Code and Codex.

MuseLite is an open-source AI workspace combining chat, Agent tools, browser automation, and scheduled tasks for users who enjoy Muse and Dots.

Best Practices for Claude Code Configuration

Claude Code-style plan mode for Hermes Agent: enforced read-only planning, then approval through Hermes' own approval prompt on every interactive surface.

Flopwire connects AI agents through messaging and shared history across harnesses, models, machines, and teammates.

touri: open-source desktop app for AI agent bots (Codex, Claude, OpenCode) with isolated VMs, browser and computer use.

《FDE：企业AI落地实战手册》前线部署工程师（Forward Deployed Engineer）开源手册 | The FDE Handbook — an open-source playbook for Forward Deployed Engineers

A zero-dependency TypeScript memory kernel that gives any agent long-term memory. No training or backpropagation: each output reads a few tag-compatible neighbors, updated by a manual Hebbian rule. Links used often are reinforced; idle ones evaporate by half-life. Based on the paper Local Pheromone Network (arXiv:2606.30669).

Auditable LLM multi-agent town simulation with AgentScope, Mesa, replay, policy experiments, and Streamlit

一个发文助手(多agent协作,包含复刻-模版-写文-配图-发布全流程的一个智能工作台)

MIT-licensed Rust framework for multi-agent systems: A2A 1.0, MCP 2026-07-28, three transports

A local-network remote control for coding agents running on your own computer.

Grader 的 agent 采用五阶段主循环：perceive→plan→act→observe→respond，由 harness 驱动。模型只决定意图与置信度，路由、工具集、风险等级由代码钉死。act 分只读 ReAct、RAG、人工提案、批量初批。四个写动作不在工具表，只能产提案。批改输出结构化 GradingDraft，逐条绑定 rubric 与段落 hash，保证可重放。

The stupid coordination tool - tasks and architecture decisions in your repo, behind one CLI any coding agent can call

An agent skill for launch and brand films that look directed, not AI-generated

Universal Research and Scientific Agent

Agentes e anotacoes da aula Dominando Claude Code - Bravy School

现代桌面 Agent / AI 应用的设计规范、交互物理学与深度工程实践指南

Moneyhelper ｜ 算清每一笔，攒稳每一步 —— 对话优先的个人理财智能体：一句话记账、持仓风控、股票投研、财报分析、策略回测、团队模拟盘。FastAPI + LangGraph + React，本地优先、数字可复核、MCP 开放。

A Soulseek client and lib built in Rust 🦀 for the terminal: TUI, CLI and daemon. Built for agents and people who live there.

Continuously updated catalogue of open-source OSINT tools, skills, plugins, MCP servers, and agentic integrations.

Ask your AI agent for a demo video. It clicks through your web app and hands back a polished MP4 that zooms in on each click. Works with any AI agent, or on its own as a CLI.

Mokusei (木犀): a native workspace for coordinating AI agents

Open-source, AI-assisted UI design review for coding agents. Inspect screenshots, scope code changes and compare results in a local workbench. Alpha.

CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements

Know when your DeepSeek Harness tasks need you. Local alerts, quiet notifications, and a task inbox.

AAI Gateway — Install MCP servers and skills once, share across all your AI agents. One-time setup, 90% less context overhead. The unified gateway for AI agent tooling.

AI RC Car Agent that using deep reinforcement learning on Jetson Nano

mcp server for slidev to make web ppt quickly and elegantly

Siwi (/ˈsɪwi/) is a PoC of Dialog System With Graph Database Backed Knowledge Graph.

document embedding and machine learning script for beginners

RAG(Retrieval-Augmented Generation) for Evolving Data

Java Based Arcus Platform and Agent Components

Enterprise-grade memory framework for LLMs featuring GPU-optimized inference, vector storage, and automated scaling. Enables hyper-personalized responses through efficient context retrieval and integration.

Bot API for Python

You can have a voice chat with AI Agent

Privacy-first desktop AI that runs agents, automations and MCP servers locally and in parallel, with your own model keys. Being rebuilt for Mac and Windows.

AI Agent Skill for Prompting Video Models

ai-agent-021：Build AI Agent from 0 to 1

Git-native issue tracker for AI agent workflows. Zero dependencies, JSONL storage, Bun runtime.

Agent Skills and plugins to help mobile devs ship better apps faster with AI assistance

Implementation of a reinforcement learning agent able to do autonomous changing lane using Sumo

Hierarchical multi-agent systems for multiple UAVs

Conflict-based search for multi-agent path finding (MAPF)

AgentSkills multi-IDE management extension: browse and install skill repositories for Antigravity, CodeBuddy, Cursor, Qoder, Trae, Windsurf (and VS Code), and search a cloud catalog (~58K skills) from https://claude-plugins.dev/.

Ansible role for installing New Relic Infrastructure agent

Rudder is an orchestration and control platform for agent work, and the operating layer for agent teams.

See what your user-agent detection library really thinks!

R1-like Computer-use Agent

A Chrome extension which duct tapes an SSH agent to the platformKey API