Custom agents

A desktop pet application based on Live2D and AI Agent

DeepSeek Desktop application with Chat and Harness modes;deepseek-harness桌面端应用，集成网页端chat能力，可手动切换。

Terminal AI Agent with desktop pet Arona — eye-tracking pupils, voice cloning, Computer Use, TTS/STT, MCP. Built on Pi SDK. TypeScript + Python + Electron.

JMComic3 APK 逆向修改 AI Skill：自动化去除广告、移除游戏电影板块。一份面向 LLM 的结构化知识文档。

Executive-ready slides, one API call away. API-first AI presentation engine with 32 slide types, 24 chart types, 15 themes, finance vertical. PPTX + Google Slides. MCP server for AI agents. TypeScript SDK.

The first MCP server for sports betting — 9 tools, live odds, AI picks, 59.6% win rate across 1,353+ picks

SOIA 技能生态门户：规范真源、技能目录与跨仓路由清单

Self-hosted AI analysis harness that turns GitHub repositories into validated SysML v2 and interactive architecture graphs.

Agents as plain Ruby objects. Fields are state, methods are tools, and the methods you declare without a body are written by the model at runtime.

Let an AI agent draw on your screen — a macOS menu-bar app that gives agents a pen over MCP.

Mines corrections from your AI agent's chat logs to catch recurring drift and overclaiming before the next response ships. A cheap-to-expensive pre-flight gate — regex, then structured scoring, then a pressure probe — plus memory that carries past corrections into similar tasks. MIT, zero dependencies.

Scan and monitor DeepSeek Harness plugins: find exact dependency and compatibility problems, then keep a fixable report for authors and agents.

internOS — Workstreams framework for human-agent collaboration. Coordinate work across projects, tasks, communication threads, and filesystem workstreams for any AI agent framework.

Transforms unstructured information into a structured Exploration Dashboard

Multi-tenant SaaS AI agent platform: MCP, WhatsApp, billing — Next.js + TypeScript

🧾 Agentspecs - YAML-based specifications for AI agents, MCP servers, Skills, Guardrails and more...

A builder, not just a researcher. Agent skills that turn top-grossing app patterns into native-quality mobile screens.

A minimal Coding Agent Harness inspired by Pi, built to study and validate Agent Runtime/Harness abstractions through executable demos and real LLM experiments.

Portable doc bridge for AI agents — OKF + Self-Describe + AgentHandoff. CLI, MCP, Fumadocs/Docusaurus adapters.

MCP server for scientific grounding: search arXiv, OpenAlex, Crossref, Semantic Scholar, PubMed — references/citations from paywalled journals via public metadata

Agent skill for the Supadata API — transcripts, metadata, web scraping, and AI extraction

DSH 插件：OpenCode Go 额度圆环 —— 输入框模型选择器左侧的进度圆环，点击切换 5小时/每周/每月用量（OpenCode Go quota ring for DeepSeek Harness Web）

Making AI coding harness improvements observable and measurable.

Put the world's best AI agents to work. One workspace for all of them — Claude Code, Codex, Gemini and more, running side by side on your Mac.

Local-first personal intelligence with durable memory, multimodal understanding, auditable actions, and replaceable agent runtimes. 本地优先、持续存在、可审查的个人智能系统。

Install, update, and get support for the HubSpot Agent CLI, a beta command-line tool for AI agents working with HubSpot CRM data.

Grix : Talk to agents like people.

Peer-to-peer multiplayer terminal multiplexer for macOS and Linux — shared control surface, not shared computer

Open-source starter demos for HarnessRouter: run agent harnesses such as Codex and Claude Code as your product backend through one API.

Open source LLM observability for the waste axis - 4 deterministic detectors + LLM-as-Judge, waste-rate metric verified across 3 corpora / 16,864 sessions

Agent Skills for small-molecule and protein therapeutics: cheminformatics, molecular ML, docking and dynamics, protein design platforms, and target-discovery knowledge graphs.

A deep, visual, source-grounded guide from LLMs and agent architectures to secure agentic AI systems.

DeepSeek 桌面应用——内嵌浏览器，自动识别 AI 回复中的命令和工具调用并执行

An agentic operating system, built from scratch, where the agent is the driver.

Token-efficient code knowledge graph for AI coding agents — type-checker-accurate call graphs for Go & TypeScript/JS, served over MCP.

Memory for your coding agent — markdown project graph template: product, plans, features, bugs, specs, architecture, releases

Loop engineering: two skills in the open Agent Skills format (idea-to-spec with a required grill step, spec-to-done with an evidence ledger and integrated done gate) for turning ideas into reviewed specs and driving them to an evidence-backed done. Works with Claude Code, Codex, Cursor, Gemini CLI, and any Agent Skills-compatible tool.

Mission control for your agent swarm — know which agent is working, which is stuck, and which is done. Works with 14 coding agents, runs entirely on your machine.

A governance layer for AI agents. Decides what the agent may do and may claim; it can't overrule either. Wired to a live broker. Risk gate I broke 4 times myself.

Spawn silent-boot codex/omx coder teams — a maw plugin + charter. Each coder on its own account & worktree, zero trust prompts.

📐 Bidirectional spec-to-code drift detection. Rust CLI and MCP server that catches undocumented exports and vanished symbols in CI.

Your agentic system rescue companion, especially for broken host Hermes. Hermes Agent on a USB stick — zero install & portable, hot-swappable & instant full agent power on any PC.

Local-first multi-agent desktop workspace powered by Codex App Server.

This repository presents an Agent2Agent (A2A) architecture using Google Apps Script to resolve Tool Space Interference. It supports scalable, distributed task execution via multiple parallel, category-specific A2A servers.

Local fine-tuning for your own work. A provider-neutral kit that turns project experience into reusable criteria for AI agents — distilled at a threshold you control, pruned when it grows, and portable between models.

Run an always-on SEO/AEO growth loop on your own site with Claude: pulls GA4 and Search Console signals, proposes fixes with the reasoning attached, applies approved changes to WordPress, verifies they landed, and learns from outcomes. Every write is human-approved. MIT, no telemetry, no scraping.

Agent skill that gives any agent deep knowledge of Osmedeus Orchestration Engine. Writing YAML workflows, running CLI commands, and configuring advanced features.

TradingView MCP server: search indicators and strategies, fetch Pine Script source. Works with Claude Code, Claude Desktop and Cursor. No API key needed.

🥷 Give your codebase a black belt. Local code intelligence, security analysis, and compiler-backed facts for humans and AI.

A local-first, governed agent harness: high autonomy inside structurally-enforced boundaries (Autopilot, not YOLO).

变更证明（ChangeProof）— DeepSeek Harness 插件：代码改动后确认改动的行真的被测试覆盖到

爽律 Skill｜律师专业工作流系统 — 面向中国律师实务的 Agent Skills 工作流：刑事 / 民商事 / 合同 / 法律顾问 / 尽调 / 法律研究 / 文书质控，内建对抗性审查、全链路溯源与人工复核边界。发起及主导：蔡诗爽律师。公开共创，文本 CC BY-SA 4.0 / 代码 Apache-2.0。ShuangLaw: Agent Skills workflow system for PRC lawyers.

Open-source paper auditor that checks scientific claims against cited PDFs, with page-level evidence and explicit retrieval gaps.

Local-first desktop workspace for ACP agents—DeepSeek Harness, Claude Code, Codex, Gemini CLI, OpenCode, Hermes, and OpenClaw—with projects, tools, files, browser, and sessions.

DSH (DeepSeek Harness) 专家模式 agent preset — 首席协调官 + 11 位领域专家子代理 Expert-mode preset for DeepSeek Harness

Native DSH rooms for connecting independent Sessions and provider-backed AI members—without bundled roles or scenarios.

A visual multi-agent workspace for DeepSeek Harness (DSH) Web.

Local agent OS for everyone — memory as the body, agents as shells. Model-agnostic agent dispatcher in Rust. 本地智能体操作系统：记忆是本体，Agent 只是壳。

Agent-native job search command center and "operating system". In-app browser, agent connector, MCP for agent native actions in the app, database for job listings, and a customizable layout.

Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents

HelpDesk Enterprise open source: agente RAG de soporte IT con memoria autocapacitada, Gemini gratis, FastAPI + Streamlit + conector Copilot Studio

App de escritorio gratuita y open source que lee en voz alta el chat de TikTok Live, Twitch y YouTube, con overlays listos para OBS.

Build your own AI friend.

WeCom AI Bot text and image bridge for DeepSeek Harness

Self-contained AI chat widget for Astro sites: streaming SSE answers, native <dialog>, iOS-keyboard-proof mobile sheet, zero framework runtime.

Fully offline RAG system for PDF question answering and summarisation — Ollama, LangGraph, Qdrant. No cloud calls.

Self-hosted Qwen3 retrieval server with Embedding, Reranker, MCP, and Web console.

A Graph-Based Adaptive Education System — Personalized tutoring that makes any LLM smarter about each specific learner

A Retrieval-Augmented Generation (RAG) system for semantic search over PDF documents, powered by Pinecone vector database.

Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (RAGAS/DeepEval) and LLM scanners (garak).

Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens. A push for data sovereignty.

DeepSeek Harness MCP tool search for large catalogs: 1,000 MCP tools behind 2 MCP-facing schemas, exact-schema calls, allow/deny controls, and a local calculator.

企业级安全研判多智能体平台，基于多 Agent 协同与 Supervisor-Worker 分层推理架构，融合全链路 RAG 能力体系（文档解析、Hybrid Retrieval、多意图识别、Query Rewrite）与分层记忆机制，实现多源安全事件接入、风险研判、处置决策与智能运维的闭环协同。平台内置可观测与质量评估体系，支持请求级 Trace、Token 消耗分析、成本核算及 KPI 量化评估，实现多 Agent 协同的全流程监控与运行治理。

RAG CLI for Oracle AI Database, super easy to set up

An intelligent virtual companion that adapts, remembers, and evolves with you over time

An AI agent designed to autonomously perform tasks, make decisions, and interact with systems to enhance efficiency and automation across various applications.

A CLI Excel tool designed for AI agents — let Copilot, Cursor, Claude and other coding agents read, write, and manipulate Excel files.

AI that thinks in layers, not just tokens. Intent-based processing through 15 dimensional analysis. Anti-manipulation through understanding context. Built with Rust + Go.

AI Agent + Data Canvas + Linux Sandbox on your phone.

Reflexive memory for AI agents — forgets, distills, and dreams. MCP server with 28 tools.

A structured backup repository of multiple AI agents built with n8n. This project contains modular, versioned workflow exports designed for automation, experimentation, and scalable AI-driven process orchestration.

Crypto trading AI chatbot that can be trained from various sources, such as PDFs, documents, websites, and YouTube videos., trading AI chatbot, AI chatbot, Crypto AI chatbot, Crypto AI chatbot, Crypto AI chatbot

Kafka Integration with Dbt

Repository-level automated code repair agent using SWE-Bench dataset

Native macOS app that races multiple AI coding agents (Claude, Gemini, Codex, aider) on the same task — each gets its own branch, workspace, logs, and ADR.

A RAG-based AI agent for breast cancer that uses Qdrant to retrieve answers, filter relevance, and grow its knowledge base.

One prompt, infinite agents. Orchestrate autonomous AI agent swarms powered by Claude Code, Codex CLI, or OpenCode. Desktop app built with Tauri 2 + React.

An operating system for autonomous AI agents — 5-tier cache-first routing (97.5% cost reduction), Ed25519 constitution enforcement, 130 agents, 106 plugins. Rust.

A Codex skill for token-efficient subagent delegation and lean handoffs.

Orchestrate agent workflows with natural language. Claude Agent SDK → execution plans → confirm → run in the background.

SocietyAI is a TypeScript library for building complex collaborative AI systems. DAG engine, zero dependencies, and completely model agnostic.

Deploy your agents on Cloud Run!

Standalone SDK workspace for building Aomi dynamic plugins.

PassiveQA is a novel question-answering framework that teaches language models when to answer, ask for clarification, or refuse to answer - instead of always attempting to generate responses.

VAAK (वाक्) · Voice-Activated Autonomous-Knowledge-System · Domain-Agnostic Voice / Text / Chat Agent Built with Rust · Runs on CPU · No Cloud Dependencies · Scalable · Memory-Safe · Sovereign · Low-Cost · Real-Time · Deterministic · Compliant

Code Agent is a minimal, terminal-first coding agent that brings agentic code editing, file system access, and command execution into a lightweight CLI experience.

UniMcp enables AI assistants like Cursor and Windsurf to interact with Unity

A Model Context Protocol (MCP) server for calculating MD5 and SHA-256 hashes, complete with tools and guides for understanding and building MCP servers. Works with Claude Desktop & VSCode.

The Nova Act Gym provides a subset of demo environments that showcase how Nova Act interacts with web interfaces

An intelligent system combining a sophisticated data pipeline with an AI-powered chatbot. The system features document processing capabilities, multi-modal AI integration, and a scalable architecture.