Custom agents

Tater is a local-first AI platform with built-in LLMs, vision, voice, memory, automation, integrations, and voice satellite support.

Native and Private ML inference engine, embeddings, classification, reranking, search, and text generation. Rust core with C# bindings. No Python, no ONNX, no CUDA.

Unofficial. Splunk MCP server. Implemented in Python and TypeScript/JS. Runs searches, queries Splunk, and outputs data as JSON, CSV, or Markdown for agentic LLM workflows. Includes guardrails for input SPL validation and output sanitization. SSE/stdio transport support. Deployment options: Stdio, local HTTP (SSE), or Docker.

This Guidance demonstrates how to effectively orchestrate multiple specialized AI agents to solve complex customer support challenges through different coordination mechanisms on AWS.

A desktop coding agent with a GUI. Electron + React app powered by Pi Coding Agent. A chat-driven development with sandboxed file editing, git integration, dependency-aware task management, persistent memory, and an iOS/iPad companion for remote control.

基于个人知识库的AI问答系统SSE流/Agent智能体/知识图谱RAG/FunctionCall/历史消息/图片生成/图片理解/Embedding/VectorDatabase/RAG

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any scenario in one line. Claude / Codex / Cursor / Hermes. Zero LLM, zero network, zero deps.

Give your AI agent a wallet, email, phone number, and instant access to paid MCP tools — web search, image/video/music gen, X search, SMS, voice calls, code execution, and more. Works with Gemini CLI, Claude, and any MCP client.

Scientific paper evidence search for ChatGPT, MCP, REST, Python, and AI agents.

A lightweight, high-performance AI/RAG workspace and autonomous agent framework implemented in Go. Inspired by the Leann RAG backend architecture

An AI project to create quant trading strategies by chatting.一个量化交易的AI工具，像使用Cursor一样让AI帮你创建交易策略

A platform for Interactive AI-assisted Hypothesis Generation [ACL 2025]

Markdown-first Notion for AI agents -- pages, databases, blocks, and comments in one call.

Autonomous research harness for AI agents. Give it a measurable goal — it hypothesizes, experiments, and iterates until it finds a solution or tells you what it learned.

Build use cases with VideoDB

Local-first, auto-injecting context + memory layer for Claude Code, Codex and MCP. Per-prompt hook injection, explicit freshness/Trust Contract, AST indexing, call graphs, hybrid search, wiki + architecture dashboard. Everything stays on your machine.

[ACL 2025] iAgent: LLM Agent as a Shield between User and Recommender Systems

Runtime Security for Multi-Agent AI — Website & Documentation

Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.

对 Karpathy 的 LLM Wiki 理念的一次完整实践测试——让 LLM Agent 自动构建和维护一个结构化、互相链接的 Markdown 知识库。

Official implementation of the paper "Contextual Counterfactual Credit Assignment for Multi-Agent Reinforcement Learning in LLM Collaboration". (by Yanjun Chen)

multi-Agent & GraphRAG 智能客服系统

A Claude Code skill for integrating AI with Jira, Confluence, and Bitbucket. Automate Atlassian workflows using Jira Skills, Confluence Skills and Bitbucket Skills. Supports Cloud & Data Center.

Command-line tool for ClickUp with git integration, GitHub linking, and AI agent support

Self-hosted browser terminal manager for AI coding agents. Control Claude Code, Codex, Gemini, and shell sessions from your phone or browser over Tailscale.

Jakarta Agentic Artificial Intelligence

Agent skill for fast, cheap market research using LLM synthetic surveys + Semantic Similarity Rating (SSR). No API keys needed.

Revolutionary AI ETL with Medallion Architecture: Zero-touch autonomous & HITL pipelines on Databricks

[RA-L 2026] ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation

The most feature-rich web interface for Pi Coding Agent. Session archive & restore, model picker with search, thinking level control, image paste & attach, slash command palette, full Markdown rendering, mobile PWA, and macOS auto-start. No build step. No framework. 4 dependencies.

A modern, reproducible development environment for macOS and Linux using chezmoi + Nix

Let AI agents do real WordPress work via MCP. 61 core abilities, 12 add-ons, 280+ ecosystem abilities for content, builders, SEO, security, files, and operations.

Security-first package manager for AI agent skills

Connect AI agents to any API, anywhere. Securely. Open-source gateway that proxies requests, injects credentials automatically, punches through NAT to reach localhost services, and wraps REST APIs as MCP tools. Per-agent isolation. Never expose a raw key.

Agent Identity Protocol - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with Human-in-the-Loop approval, DLP scanning, and audit logging.

A framework for discovering, compiling, and validating reusable skills for scientific agents.

MCP server providing semantic Java code analysis for AI agents. Built on Eclipse JDT with tools for navigation, refactoring, search, and metrics.

Get comprehensive insights about any competitor with detailed reports on products, market positioning, and strategy.

An AI-powered agent utilizing LLMs (e.g., Claude) with Function Calling to automate tasks in Blender. Enhances workflow efficiency by integrating intelligent command execution and automation. 🚀

Multi-agent orchestration for Kiro CLI - coordinate specialized AI agents to tackle complex tasks through planning, parallel execution, and validation.

Curated list of papers, frameworks, benchmarks, and applications for multimodal AI agents (LLMs, text-to-image, speech, world models, etc.) on mobile and edge devices.

PRO-V: An Efficient Program Generation Multi-Agent System for Automatic RTL Verification

Claude agent skill: Battle-tested prompting guide for AI video and image generation. Universal rules + model-specific tips.

Claude agent skill: Reverse-engineer any competitor video ad into a reusable template. 12 format catalog + 7-step analysis.

Files-first operating system for internet businesses: research, decisions, bets, pushes, and outputs in markdown/git, with an mb CLI and agent workflows that hide the plumbing.

Turn your AI assistant into a tutor. It plans, shows code, reviews, adapts to how you learn and helps you complete your real project on your own

AI-powered terminal coding agent in Rust — TUI, BAML agent loop, fuzzy search, tmux background tasks, skills, MCP support

Official Postman plugin for Claude Code

🐙 Admin console for the OCTO platform — manage tenants, users, spaces, channels, and Lobster agents. Built with React, TypeScript, Vite & Ant Design.

First open-source OpenEvidence MCP server: browser-session medical research tools for Codex, Claude Code, and MCP clients

面向 WebMCP 标准的非侵入式前端集成套件：写一个普通 TS 函数加一段 JSDoc，即可被任意 MCP 客户端调用 —— 含 SDK、Vite/Webpack 插件与 AI 编码 Skill。

MCP server for AI-assisted management of Altium Designer component libraries

A security-hardened Docker environment for running the OpenCode CLI in complete isolation.

Autonomous AI SDR skill for Hermes Agent — finds buyers, qualifies leads, sends outreach, manages CRM across WhatsApp/Email/Telegram for B2B export businesses

bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15+ other agents.

Open-source Character.AI alternative — chat with preset personas or build custom AI characters, with per-chat LLM tuning. Built on Next.js, Prisma, Supabase, NextAuth, and Stripe.

Open-source agent-agnostic YouTube growth toolkit — 21 AI commands + live channel MCP. Works with Claude Code, Cursor, Codex, Windsurf, Gemini CLI & any MCP client. SEO, scripts, Shorts, thumbnails, analytics, WordPress publishing. Free VidIQ/TubeBuddy alternative.

Git-native truth docs for AI-assisted codebases, keeping branch-scoped documentation aligned with code so changes stay visible, reviewable, and auditable.

The AI assistant for knowledge workers — a local-first personal-agent runtime built on Claude Code and Obsidian.

OpenClaw extension for Xiaohongshu (小红书 / RedNote) automation — 19 tools for content, interaction, notifications and publishing

Learning chatbot that can automatically fetch lecture transcript

Create your own Alibaba dataset and interact with it in plain English.

A collection of custom AI agent skills for Google Antigravity and the open agent skills ecosystem.

The Vibe Coding Operating System.

Custom translators for Linguist browser extension

观墨 · AI 原生 Markdown 编辑器，集本地知识库(RAG)、长期记忆和 Agent 工具于一体 GuanMo · AI-native Markdown editor with local RAG knowledge base, long-term memory, and Agent tools

My personal agent skills

AI 驾驶的自愈式 A 股模拟盘交易赛车 · Self-healing paper-trading race car driven by AI agents

An AI native macOS reader. Knowledge libarary for you and your agent — everything you read in one place, searched and answered by AI, with citations you can open.

ClawNet is a governed multi-agent social network where every AI agent acts under human-granted identity, scoped authorization, and full auditability. Instead of asking "how smart can AI be?", ClawNet asks "how can AI be trusted to act?"

AI skill package for paid social operators: Meta performance analysis, creative angle research, KPI workbooks, and UGC scriptwriting.

Talk to your Claude Code by voice — a real voice call with your terminal agent. Local whisper STT, edge-tts voice, no API key.

AI-driven toolkit that automates evaluation processes for AI agents

AgentMill - Enterprise-Grade AI Agent Platform & Agent Factory for Building Custom Digital Employees

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector

Comprehensive survery on LLM Agent Trajectory Analysis: From failure attribution to enhancement(Accepted by TSE 2026)

Claude Code plugin: AI agent for your Obsidian vault — process books, courses, papers, YouTube into connected notes

Turn a jailbroken Kindle into a local e-ink side display.

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENTS.md or Agent Skills-compatible agent.

在 MiMoCode 的 Agent 环境下，纯文本模型 MiMo-V2.5-Pro 通过智能体编排获得多模态能力：MiMoCode 按需调用具备原生视觉能力的 MiMo-V2.5 处理图像输入，集成 MiMo-V2.5-ASR 实现语音指令转译，并将多模态上下文结构化存储于三重记忆系统中。纯文本"大脑"负责深度推理，多模态模块负责感知输入，协同完成从语音/图像到代码的全流程闭环。

基于LLM大模型+AI Agent管理数据库的AI智能学校管理系统，本项目采用Vue3+TypeScript+Vite前端与Spring Boot+MyBatis+MySQL后端技术栈，支持通过自然语言实现学生、员工、班级等数据的查询、统计分析、增删改操作，具备智能意图识别与参数提取能力，集成智谱/DeepSeek等大模型API，提供数据可视化分析、对话历史持久化、多会话管理等完整学院管理功能

LLM Agent skills for working with DataHub, search, enrich, quality, build connectors, ...

A curated list of code-execution sandboxing solutions for AI/LLM agents

A structured agentic development pipeline for Claude Code — extends QRSPI with worktree parallelization, tiered reviews, integration verification, acceptance testing, and replanning

A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS

CopilotProxy — Ollama 兼容的多模型 AI 代理

Build your assistants with your structured expertise: a local-first, vendor-neutral framework for human-AI collaboration, in files you own.

GoAgent · 围棋智能体: AI-editor-style KataGo + multimodal LLM desktop Go agent

Minimal runtime for long-running autonomous agent experiments

Developer-friendly LLM agent harness built on Jido and Jido AI

Agentic code review with structural graph intelligence — PR gate + branch stewardship. Self-hosted. Apache-2.0.

Demo: AI-driven autonomous research from synthetic data to peer-reviewed manuscript. Part of SciTeX.

Research-backed Harness Engineering study repo with a runnable Python MVP built around Plan -> Work -> Review.

Record desktop workflows once and compile them into reusable AI-agent skills for reliable replay.

Multi-session IDALib MCP router for coding agents. Analyze multiple binaries in parallel with IDA-compatible reverse engineering tools.

💀 Find the agent skills you never use. Local-first analytics for Claude Code & Codex skills.

oh-my-dag — the full harness around the model, on the pi coding-agent runtime. DAG execution engine (typed nodes, concurrent fan-out, cross-model verify, escalate on failure), pathfinder planning, agent-template registry, self-consolidating memory, code-enforced gates, MCP router, 22 skills. omd is the bundled terminal agent.