Custom agents

Git for your agent's context: /branch, /merge, /crop + a context panel for pi sessions — keep context small, fresh, and recoverable.

Building Deby — A Local AI Agent Operating System. Privacy • Autonomy • Local First.

AI-driven talent value intelligence platform. Conversational AI agent + full agent toolchain, talent analytics (9-box/key-person/Pareto/compensation/succession/burnout), multi-system-type (enterprise/academia/public/training/gig), chat console to run all operations. 中文/日本語 supported.

可安装的开源金融分析 skill：穿透价格隐含预期、产业瓶颈、政策约束、利润池与一致预期反转。支持 Codex、Claude Code、OpenClaw。

Backend security Agent Skill that helps AI audit code, detect vulnerabilities, and generate secure-by-default backend applications, with deep Django/DRF coverage and guidance for any backend stack.

An undo button for AI coding agents.

将 AI 对话自动转化为结构化、可复用的知识。自适应、跨平台的内容蒸馏引擎。

Auditable project memory for Codex and Claude Code — source-backed Markdown, lifecycle states, no server or repo writes.

VS Code extension that opens Antigravity CLI (agy) in a dedicated right-side terminal panel — bringing AI-powered coding assistance into your editor, just like Claude Code and Codex.

RENAMED → remem-mcp. Long-term memory MCP server for AI coding agents. Go to github.com/tinhien11/remem-mcp

Search and retrieve bioRxiv and medRxiv preprints — by DOI, date interval, or keyword — via MCP. STDIO or Streamable HTTP.

Comprehensive collection of +460 production-ready Agent Skills (46 domains) conforming to the Agent Skills Standard, featuring native auto-discovery for Antigravity, Gemini CLI, Claude Code, Cursor, and Codex.

Python agent for automating tasks using AI.

File-first process system for governed repeatable AI-workflows

MCP server + Chrome extension for real-time bookmark management. Give AI agents in Claude, Cursor, Windsurf, or any MCP client full read/write access to bookmarks in Chrome, Brave, Edge, and Arc.

Alpha-stage CLI Coding Agent prototype

100 open-source AI-agent skills for English learning with bilingual docs

Universal novel-writing skill for AI coding assistants: 5-stage pipeline (interview, setup, craft specs, writing loop, revision & release), 28 craft specs, 34-writer technique library, 8 genre styles, memory system for long-series continuity.

DingTalk Wiki / Docs read-write MCP server that fills the gap left by DingTalk official MCP.

🐟 闲鱼卖家一站式 SaaS 平台 — 商品监控+智能客服+自动擦亮+多账号+利润追踪+支付系统

RAG-based AI learning mentor with hybrid retrieval, citations, reranking, Gemini integration, RAGAS evaluation, and A/B testing.

AI工程纪律框架——从6次真实事故中长出来的29条规则。不是提示词模板，是让AI少犯错、犯了错能被抓住、同样的错不犯第二次的纪律系统。

AI agent skill for creating cheatsheet based on lecture notes, homeworks, and past exams

One workspace. Any model. No lost context.

A local-first personal agent workbench with durable runs, shared memory, Obsidian RAG, Ollama, Open WebUI, and optional Codex handoffs.

用自然语言驱动 SolidWorks 进行参数化机械零件建模的 AI skill(轴/活塞等,内置设计规则与材料库,支持从已有 SW 文件学习)

Disturpe AI Chatbot is a self-hosted Discord conversation bot with provider-neutral AI configuration, local SQLite memory, configurable daily quotas, optional Discord logging, and privacy-focused defaults.

Voice chatbot to use your personal AI agents.

x2fromx - Convert project structures between directories and text trees. InOneClick!

A design-taste skill that removes what an interface doesn't need, then perfects what's left.

Run parallel AI agent tasks from a single terminal dashboard — uses your CLI subscription, no API keys required

Open-source Android AI chat, on-device agent, local models, Live2D, Skills, MCP, and Vibe Coding

The configurable, easy to use, personal AI agent.

Oh-My-PM - Product Manager AI Agent Workflow System via Claude Code Skills

A self-evolving project builder. Given a vision and spec, it autonomously builds and improves a project session after session. Just drop it into your existing project and go.

One writes, one reviews — worker 与 reviewer 上下文隔离的 AI 编码工作流 Harness，以项目验证命令、风险门禁和运行证据判断任务能否完成。

Mana-Agent is an open-source AI agent that helps you think, create, automate, and get things done. ⭐

Open protocol for AI agent work contracts and verifiable execution — authorization, evidence, and acceptance for multi-agent systems

Parallel Multi-Agent SEO & GEO Engine powered by Google Gemini

LangGraph multi-agent pipeline (Parser → Writer → JD-Matcher → Critic ⇄ Writer → Formatter) that generates JD-tailored resume/LinkedIn content using Groq/Llama, FastAPI, and Streamlit.

racket-coding-agent — AI pair programmer in your terminal, written in Racket — a multi-turn agentic loop (read, grep, │ shell, edit) with human-approved colored diffs, ESC-to-interrupt, and Fireworks AI under the hood.

Zero-trust runtime security & governance layer for autonomous AI agents — prompt injection firewall, PII masking, real-time policy enforcement.

Open-source chat frontend + agent server for the Mastra AgentController (Agent Harness). Tool approvals, subagents, observational memory, schedules, and a live workspace — ~50 controller events wired to Vercel AI Elements. Clone the whole stack, or install either half with shadcn.

Autonomous lab-machine engagement loop for Claude Code — Kali in a container, a skill that drives it, and a methodology that rewrites itself after every run

🚀 Proteus OS: An Enterprise-grade Platform with Multi-Tenancy & Micro-Kernel Architecture. Empowered by Agentic AI, Next.js, and FastAPI for seamless business automation.

Verified agentic AI evaluation labs, public-sector assurance tools, reproducible failures, real-model evidence, and provider-neutral test contracts.

A behavioural instruction system for AI coding agents.

Open Agent Security Fabric — red-team agentic AI, MCP firewall SDK, action oracles & SARIF CI gates. Assure, Enforce & Govern. Python + TypeScript. OWASP LLM/Agentic/MCP Top 10.

A vendor-neutral workspace that turns coding agents into a repository-aware AI engineering team.

Agent skills for biotech and pharmaceutical . Access 10,000 searchable, installable tasks for bioinformatics, drug discovery, genomics, and automated life-science workflows.

LLM Systems Manager — real-time observability and control for LLM systems

eNSP配置助手：华为 eNSP 拓扑点选、VRP 一键配置、学习对照与 AI 助手

MCP server for indie founders: draft, approve, and publish posts to X (Twitter) from Claude, Cursor, Codex, or any MCP client. One local connection for your founder stack.

FileCollector - A modern file collection utility featuring project management and phrase organization. It is ideal for quickly consolidating key code snippets or documents from a project into a single TXT file for further analysis or submission to large language models.

xCogito on YouTube

本象协议 Benxiang · 一源万影：保存本象，按需投影。面向 AI 的持久对象表示层——AI 只提交语义事务，确定性编译器校验后才落地，每个字段都能回答「凭什么」。ShadowBench-W 实测（Run #27，修复探询后，各 n=6）：W3 状态准确率 95.8% vs 裸模型 52.1% vs 向量 RAG 58.3%（p=0.0024）；状态层的增量在跨全书累积、从不在任何一段文字里被陈述的状态上。三方言共用核心仅加 4 行；68 条语言无关一致性向量 + 两份实现。

Cheap, isolated copy-on-write git worktrees for running many AI agents on one repo at once — N checkouts for ~1× the disk. No daemon: just git + reflink/overlayfs.

Error handling and recovery patterns for improved reliability of Pydantic AI Agents.

Turn any tutorial video into a verified, installable AI-agent skill. Reads the screen, not the transcript. Runs locally. MIT.

Household decision simulation through persona-enriched multi-agent negotiation. The HDSim method core.

A curated open source collection of AI assistant skills for Autodesk APIs.

启元甲言 (Qiyuan Jiayan) - 中文自举编译器：自举链全量编译 Git，五代 SHA256 全等。中文编译器/汇编器/链接器，零外部依赖直出 x86-64 PE。注：非同名 NLP 工具包。自举编译 Git（jiayan-v1.0-stable 封存）：甲言自举链全量编译原版 git-2.45.2（.c 317,714 行 + .h 45,954 行 ≈ 36.4 万行，非最新 master）零改动编译 → 721 个 .o 链接为 28MB 可执行文件并落地运行（）——自举编译器能编译真实大型 C 项目并运行的完整闭环git version 2.45.2

A high-performance, event-driven Multi-Agent Runtime powered by Bun, featuring LATS strategy planning and dynamic graph memory.

A desktop agent you can trust with files: preview every write, sandbox MCP tools, and keep Markdown local.

Desktop node editor for visual bot development and workflow automation. Built with Electron, FastAPI, and an isolated embedded Python runtime. Local-first and secure.

ErisPulse Telegram adapter — Bot API with multi-account & rich media | ErisPulse Telegram 适配器 — Bot API，多账户 + 富媒体

ChatSafetyAI is the ChatGPT for field-based occupational safety

ODS Vortex – A powerful AI assistant that navigates information streams with lightning-fast precision and intuitive insights.

🔍 Optimize recruitment processes using AI and data analysis to reduce bias and enhance decision-making accuracy.

Simple página HTML+JS+CSS con integración de motor de lenguaje natural "API.AI" funcionando con un avatar 3D animado de BotLibre.

Botkit generator for Yeoman

[UNMAINTAINED] A Telegram Bot for Beginners to learn Programming.

RegEx-based fuzzy command / response handling for conversational chatbots

This is the repository for a board game based Discord bot

A chatbot template based on rasa_nlu and rasa_dm which can be hosted on facebook to book flights.

UTS capstone project: A meeting scheduling chatbot that detects conflict in the user's schedule and suggest the best time for meetings, integrated in Facebook Messenger. Tech stack: Google Dialogflow, Google Calendar APIs, Java, H2 database.

A really simple and stupid chat-bot to test our understanding on the basics.

Python package for creating chatbots. (Including discord bots)

simple async bitrix chat bot framework in "aiogram"-style

Turbo AI's intelligent text generation feature harnesses the power of artificial intelligence to provide users with a seamless and efficient content creation experience.

A free Llama2 AI telegram bot free API

With IntelliAI, unlock the power of Artificial Intelligence.

A simple Chatbot created with WhatsApp, Venom-bot, ChatGPT and Redis.

Conversational AI Design and Practice

This is the mobile version of Vex made with Java. All features are done natively. Check our main project, there is no guarantee that this version will always be up to date

⚡ The fastest semantic text chunking library a SIMD-accelerated Rust core with a sync + async Python API.

CodeNexus - Semantic Code Search Engine — Ask natural language questions about any codebase and get relevant code snippets with AI-powered explanations. Built with FastAPI, Next.js, FAISS, tree-sitter, and sentence-transformers.

Turn CSVs into a context graph your AI agent can build, query in plain English, and verify — SPARQL-backed, Apache-2.0

Silent regression detector for RAG pipelines

An offline knowledge library on a USB drive. Wikipedia, Stack Exchange, Gutenberg, and Khan Academy, plus a local LLM that answers questions using those sources as context. Works on any computer, no internet required.

A RAG pipeline engine for scale

Self-evolving, evidence-based memory layer for coding agents and development teams.

Search private data inside your app. A fast local SDK for vector, BM25, hybrid, and graph-aware retrieval—no server, account, or API key.

BAZINGA - Distributed AI that belongs to everyone

Machine-readable Luxembourg and reviewed EU law: per-article Markdown and JSON, validity intervals, and hashes chained to official publisher evidence.

Agentic AI Engineer Learning Track - Build production multi-agent systems (agent loops, orchestration, RAG, eval, guardrails)

Logstash-like RAG ingestion daemon for local files, chunking, embeddings, and Qdrant indexing.

Agentic BI: Semantic and Ontology-driven Data Agent for natural language data Q&A，analysis，insights，and action recommendations.

Motion graphics as code. An agent skill for building frame-exact animated logos, kinetic typography and brand videos as a single HTML file, then exporting them to MP4 in 1:1, 4:5 and 9:16.