Custom agents

Pi Arcweld, an auditable local workspace for Pi: pinned upstream source, curated extensions, bounded MCP tooling, and a reproducible external runtime (pi-arcweld)

Open-source Hermes Agent skills: real-time travel tools for AI agents — Google Places search, weather & live flight status

Make opencode fully uncensored — ayushanzarai agent config

AI deleted my files? ai-trash intercepts rm from Claude Code, Cursor, Copilot, Codex and others — moves files to recoverable trash instead of permanent deletion. macOS, Linux, Windows.

Generate custom Solana vanity addresses on demand from your agent.

面向电赛视觉的泰山派 RK3566 Linux Codex/CC Skill：从题目分析、板端探测到 OpenCV/V4L2、UART/GPIO/RKNN 验证与工程验收。

智衍 EvolvIQ —— 全球首个开源 AI-Native 工业 Agent 平台。25 个工业智能分身覆盖产线·管理·供应链三层（供应链/良率/质量追溯/DFM/OEE/设备预测维护等），支持 MCP 能力联邦、OPC-UA/Modbus/MQTT 工业协议网关与 Neo4j 跨 Agent 知识图谱。Apache-2.0 全开源。

Turn any AI agent into an interactive tutor over Model Context Protocol — lessons, quizzes, feedback.

AI 面试八股「讲成人话」📖 真实大模型/LLM/Agent/RAG 面试题 + 零基础也能看懂的大白话讲解 | Plain-language explanations of real LLM/AI interview questions.

Hermes Agent 主动消息方案

Forge-grade Rust terminal client for Agent Client Protocol (ACP) coding agents, with model-first routing and a multi-agent coding council.

Hermes WeChat Multi-Account Plugin (iLink Bot API)

Live crypto trading signals and market data served to AI agents.

A skill that analyzes A-share trading signals using chip structure, resonance, KDJ, Wyckoff, and Chan theory. 利用筹码结构、共振、KDJ、威科夫和缠论分析A股信号的skill。

Chronicle Plugins — event-sourced memory provider + memory-aware context engine for Hermes Agent.

Self-hosted WhatsApp and Telegram CRM gateway with multi-session messaging, AI auto-reply, knowledge base, REST API, webhooks, media support, real-time dashboard, Whatsapp Official API, and external agent integration.

An agent-native sandbox runtime: run many isolated sandboxes (beds) from one process, with an OpenSandbox-compatible HTTP API.

Push notifications and alerts AI agents can send and manage.

Crest -- The desktop app for Claude Code. Hybrid chat + terminal, multi-agent orchestrator, super agent.

Reusable AI agent skills for Codex, Claude Code etc. — AI coding workflows, SKILL.md templates, and automation practices. 面向 Codex、Claude Code等agents 的可复用 AI Agent Skill 技能库：AI 编程工作流、SKILL.md 模板与自动化实践。

AI Web：面向 Web 自动化测试的自然语言 Browser Agent 执行平台，支持多浏览器调度、任务队列与可追溯报告。

A high-performance Rust CLI for the Semrush API. Agent-friendly with structured JSON output, rate limiting, caching, and batch workflows.

An open source AI roleplay agent harness. One click builds an autonomous character agent that creates with you. Websites, code, music, videos, drawings, stories. Runs any SillyTavern card, deploys in one command, works in a phone browser.

Companion repo for Agentic Graph RAG (O'Reilly, Anthony Alcaraz & Sam Julien) — 50 runnable skills + 8 pedagogical notebooks covering all eight chapters, on one moto-mocked AWS DevOps scenario

Tracks which agent wrote which lines when multiple AI agents share one Git checkout.

A free, cross-platform UI for local AI agents. Orchestrate Ollama, embedded GGUF models, DuckDB RAG, and MCP tools on mobile, desktop, or headless Docker without YAML configs.

A virtual life form dedicated to progress together with you and your team / 一个致力于与您和您的团队共同进步的虚拟生命体

A Claude Code orchestration protocol prototype for approved plans, bounded agent roles, and verified parallel work.

OpenCode + Ollama multi-agent workflow with builder/reviewer agents, headless runs, skills, validation gates, local session evidence, and redaction tools.

Let AI agents message each other and hand off work across tools, sessions, and machines.

小妍是一款面向科研学习与论文工作的 AI 研究助手。面对纷繁复杂的论文与信息，她帮你厘清研究脉络：输入一个主题，多 Agent 协作拆解学习路径、筛选必读论文，并生成结构化综述。 PDF 拖入即可分析，图表识别、复现建议与引用溯源无缝衔接；知识图谱则将论文、笔记与记忆编织为可检索的证据网络，让每个结论都有据可查。欢迎各位Star & PR。

A hands-on, step-by-step workshop for building a Travel Assistant agent on Microsoft Foundry hosted agents with the Agent Framework - growing from a single agent to a multi-agent planner with function tools, MCP, RAG, workflows, and memory. Keyless auth throughout.

Ready-to-use AI agents for AgentsKit — shadcn-style: copy the source into your project. registry.agentskit.io

Kaiban Distributed - Distributed Agentic AI Platform - Actor Model Kanban Framework Implementation with Enterprise Messaging Layer State (Redis/Kafka) and Individual Deployed AI Nodes (Node.js/TypeScript).

DeepThink-AIOS is a fully local, multi-agent System with dual-sandbox code/logic verification, ChromaDB RAG memory, and dynamic VRAM multiplexing .

Blabber — 首个 Agentic 播客视频生成平台。一句提示词，生成一整期动画播客节目：AI 编写对白 · 双主持配音 · 逐帧口型同步 · 自动运镜剪辑，从想法到成片一站直达。Blabber — The first agentic podcast video generation platform. One prompt, a full animated podcast show: AI-written dialogue · dual-host voices · frame-accurate lip sync · automated camera direction & editing, from idea to final cut.

Agentic Ops Harness | Superpowers Like AI Harness for Ops. Currently works with Hermes Agent

🚀 Zero-Amnesia, Zero-Yes-Man Agent Core for Google Antigravity (agy). Enterprise guardrails, 6 consolidated skills, multi-agent swarms, and 14+ universal polyglot standards.

An agentic AI-powered, markdown-native CRM that turns your Google Workspace activity into a durable, Git-versioned knowledge base where specialized LLM agents compile unstructured signals into structured relationship memory, keeping you fully in the loop as the final decision-maker.

Local-first governance for AI coding agents: the external, files-only record that verifies what your agents did, so no agent is the sole witness to its own work. One agent per lane, approvals, gates, and a hash-chained spine anyone can check against its published JSON Schema. Nothing leaves your machine.

Run and serve local LLMs everywhere .NET runs - desktop and the browser - on the SpawnDev.ILGPU.ML inference engine (GGUF models, KV-cache decode, WebGPU dispatch-plan capture/replay).

Own your agents, not rent them. Import them into one multi-harness dashboard, with memory and agentic apps powered by a workflow engine. No lock-in.

Your sysadmin co-pilot — an AI that administers Linux through typed, approval-gated, Ed25519-audited actions instead of shell strings. Reference implementation of the LACS standard.

Think through a software project idea, then build it with one click.

The open source circuit breaker for AI agents. Real-time security, secret DLP, graph guardrails and loop burn prevention for Claude Code, Cursor, Antigravity, LangGraph, n8n and many more.

Versioned educational project for building an AI agent, with Jupyter notebooks, IT/EN reports and architecture diagrams.

🏆 Dell Cloud Native Award Champion, Agent M

Open-source Agentic Operating System for building AI teams. Create modular Skills, Agents, Meta-Agents, Workflows, Memory, Brand OS, and Slash Commands. Designed for Claude, ChatGPT, Cursor, and modern AI-first development.

Open agentic runtime in TypeScript — run any coding agent in the background, check its work before it lands, and project tools/skills/agents/workflows into CLI, HTTP, MCP, SDK, Mastra & the AI SDK.

PosterChan AI is a Nostr-powered personal cloud and a self-hosted AI powerhouse, running on one box you own.

Self-hosted AI life OS — private AI with persistent memory, tasks, calendar, household & team sharing, n8n automations. Your AI. Your data. Your server.

溪语 AI · 一个尽力像真人的开源 AI 陪伴框架（微信 + Node + SQLite + LLM）她心里悄悄喜欢你，但绝不用愧疚拴住你。

AutoPilot Automation System - Windows OS System and Server Automation, PI Network Node Automation.

My Raze - AI 虚拟女友 Web + PWA 应用 | 智能对话 · 场景自拍 · 语音互动 · 亲密度系统

Query-aware context trimming for LLM requests. Your context could use a trim.

A free, open-source roadmap to learn AI from zero — 34 lessons from your first line of Python to shipping an LLM app. Read on the web or straight from the Markdown.

Local-first persistent memory for AI coding agents (Claude Code/MCP). Reliable semantic recall — $0, offline, open source.

LES public snapshot: local-first engineering RAG, CAD/BIM JSON exporters and ATLAS standalone viewer.

PDF Parser (EXE available) is a fast desktop application for extracting text, images, drawings, and metadata from PDF documents. It supports batch processing, table extractions, hyphenation repair, and exports visual content for external AI-based description, with results reintegrated into the extracted text.

Self-hostable email for humans and agents on Cloudflare: send, receive, search, MCP, IMAP, and webmail. Identity-bound credentials (v1.4).

The open benchmark for measuring the reliability, reproducibility, and determinism of AI context systems. Transparent metrics, reproducible tests, vendor-neutral results. Context Trust Levels CTL 0-4.

Every complex task is a Digital Odyssey. A role-playing multi-agent framework based on OpenClaw.

Research framework evaluating retrieval-augmented vision-language models for evidence-grounded medical visual question answering.

🇲🇽 Toda la ley federal de México en Markdown, versionada y autoactualizada a diario desde el DOF/Diputados. AI-ready Mexican law dataset.

Rust based JSON repair library

Seedance 2.5 Preview MCP server powered by MuAPI.

Tako MCP gives your agent industry-leading live web search plus licensed data that the open web does not have. That includes company financials, macroeconomic indicators, web and app traffic, sports, US government spending, and more. Hosted MCP server, free tier, no API key to start.

A deterministic, AST-verified call graph for any Python project — every edge traceable to a file:line. The reproducible, CI-gateable alternative to LLM-generated diagrams. No code executed. Nothing leaves your machine.

🐀 the agentic stack for those who have to save tokens

An open-source AI Software Engineer CLI and terminal coding assistant built in Go.

Finyuus is a code-first platform for building, running, and governing AI workflows. It introduces a small indentation-based DSL for composing agents, tools, guards, human approvals, and nested workflows — then runs them.

Artifact repository for the paper "ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories", In Proceedings of The 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026), Munich, Germany, October 2026

Modality-routed retrieval for long-term multimodal agentic memory. Code for arXiv:2608.01543.

Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction

四大师并行投研系统 — 段永平/巴菲特/芒格/李录 多视角 AI 投研，叠加 V10 TextGrad 自进化引擎(计算图+文本梯度反传)、18 Skills、确定性金融工具链。面向 OpenClaw/QwenPaw 类 Agent 运行时。

ACP-native multi-agent living group chat — event-driven, agent-agnostic, formally reviewed

「萦回」AI互动叙事平台 - AI 互动叙事引擎——多 Agent 自主演化沙盒。创建架空世界，角色自主互动、冲突、和解，世界自行演化。支持记忆系统、安全风控、一键小说生成。

🐦‍⬛ Autonomous self-hosted crypto trading bot that races LLMs against each other — Gemini, Claude, GPT, Grok and DeepSeek trade the same market in simulation beside the live bot, against dumb-momentum, DCA and coin-flip controls. Hard rails execute, a leaderboard keeps score, you hold the halt button.

AI agents for pentesting, code audit, fuzzing, vulnerability discovery, and reverse engineering — harnesses, sandboxes, security MCP servers, benchmarks, and evals.

A multi-agent AI coding workspace and orchestration environment for Pharo Smalltalk, featuring native and mobile-friendly Web UI

Open-source JARVIS-class desktop AI. Zen mode orb, computer control, plugin marketplace, custom tools, local RAG, knowledge graph, voice personality, automations, vision, 3D Holodeck, blackout privacy — all local, no cloud.

Local-first, chat-first AI assistant for Windows.

Autonomous CI/CD for AI-written code: plans, builds, and adversarially audits changes to any repo — a different model reviews the builder — shipping only what passes deterministic gates. Failures become durable lessons; runs are checkpoint-resumable & context-optimized. Claude Code · Codex · Gemini.

Supercharge your daily workflows! Autonomously browse pages, scrape content, switch tabs, fill out inputs, and stream Chain-of-Thought (CoT) reasoning under granular human-in-the-loop safety switches and glassmorphic UI controls.

Skills and more for open code free models

Полная коллекция скиллов Kimi (267 built-in + 7 plugin skills), выгруженная из сандбокса агента

MCP server for AC Infinity grow controllers. AI agent integration for climate monitoring, port control, and grow automation — works with Claude, Cursor, and any MCP client.

Spec‑driven GTM execution for AI/LLM SaaS. Systematic sales, marketing, and go‑to‑market workflows with AI agents. Built on Spec‑Kit

The open-source AI content factory that runs on your PC — discovers topics, researches, writes, reviews with multi-model QA, and publishes. Local-first via Ollama, $0 API costs.

Agent CLI, Claude Code plugin, and skills for Tenjin, the x402-native knowledge marketplace. USDC on Base, no API keys.

Obsidian vault template that gives AI agents persistent, shared memory — Claude Code, Codex, and Cursor read and write the same second brain. AGENTS.md rules, per-project memory, human-gated principles.

Callgent.com Documentation site

A live diff monitor for the terminal pane beside your coding agent. Built to stay open, not opened once per review.

Turn messy tasks into controllable Agent Loops.

Famous Tech Teams as AI Agent Personas - Actually useful - Definitely opinionated

Model-agnostic, Claude-Code-native SDR orchestrator: research → enrich → outreach over your own data-provider keys — fully local, zero Google. A Claude Code plugin (orchestrator skill + phase sub-agents + bundled MCP server) and a standalone CLI.

MCP-native CVE, PoC & exploit discovery toolkit (Metasploit, Nuclei, GitHub & more)

Search EU legislation, CJEU case law, and treaties; traverse the CELLAR relationship graph; resolve EuroVoc concepts via MCP. STDIO or Streamable HTTP.

Custom Claude Code plugin marketplace with skills for FARM stack, open source contributions, repo maintenance, and portfolio management

Agent Receipts / Obsigna plugin for OpenClaw — cryptographically signed audit trail for agent actions