Custom agents

Production-grade TypeScript AI runtime focused on reliability, governance, and reproducible LLM systems. Multi-provider gateway, agents, RAG, workflows, policy engine, audit trails, and deterministic testing — built for teams shipping AI in production.

Open-Source DLP for LLMs and Agents that provides Conversational Coherence

A fully autonomous asset manager. Returns may vary.

Spoox CLI - Terminal Agent - SPlit lOOp eXand agent

Morning Deck is an open-source, self-hostable AI-powered news intelligence platform.

A structured dialogue framework for Claude and ChatGPT. Four modes: analysis, action, lived experience, unformed intuition.

Learn to evaluate AI products for production — 21 hands-on lessons on evals, metrics, fairness, agents, red teaming, and release decisions for working PMs.

[2026 AAAI] Predicting the Future by Retrieving the Past

MCP server giving AI assistants verifiable access to PubMed, Europe PMC, US/UK drug labelling, and ClinicalTrials.gov. Built by PharmaTools.AI.

all tmux sessions, all agents, one interface

🦾 Bridge OpenClaw AI agents with physical servo robots — Python library for LOBOT LX bus servo control, motion teaching & playback

The finmap.org MCP server provides comprehensive historical data from the US, UK, Russian and Turkish stock exchanges. Access sectors, tickers, company profiles, market cap, volume, value, and trade counts, as well as treemap and histogram visualizations

Local-first CLI to read, compare, and hand off sessions across Claude Code, Codex, Gemini, and Cursor agents. Checkpoints, cross-agent messaging, zero npm deps.

BasaltCRM: A high-performance, enterprise-grade CRM and outreach engine. Built on Next.js 16, TypeScript, Shadcn/ui, and Prisma. Features AI-powered lead discovery, intelligent ICP scoring, multi-channel communication (Voice/SMS/Email), and real-time business analytics.

Impermanent: a live benchmark for forecasting that measures temporal generalization under real world data drift. The benchmark includes foundation models (from AWS, Google, NXAI, Salesforce), classical statistical methods, and simple baselines. Metrics such as MASE and scaled CRPS, along with championship style points, are published on the site.

A lightweight, extensible coding agent built in TypeScript that helps developers with coding tasks across TypeScript, React, JavaScript, Node.js, Bash, and markdown/JSON.

Resources and references on solved and unsolved problems in agentic AI.

LLM-wiki: drop in papers/articles/notes, get a structured, interlinked, searchable wiki knowledge base. LLM-wiki：扔论文、丢笔记，自动生成交互链接、可搜索的个人wiki知识库。

🔒 Automate cybersecurity tasks with n8n workflows for Red Team, Blue Team, and Application Security, enhancing efficiency and response times.

The open-source toolkit for building AI commerce agents using UCP and ACP protocols

Where AI discovery becomes science

Official implementation of ACL 2026 paper, "ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation"

Agent + Skill System for Controlling Figma and Automate Design Process

A opinionated collection of agent skills organized by domain: dev, writing, productivity, and knowledge management

TypeScript SDK and CLI for self-custodial MPC wallets. Built for AI agents. No seed phrase, 40+ chains.

Give AI eyes and hands on your desktop. Open-source MCP server for desktop automation — screenshots, UI control, browser automation, OCR. Works with Claude, Cursor, and any MCP client. macOS + Windows.

Fleet AI Security Posture Management (AI-SPM): client agents on each developer machine score their AI coding agents' guard surfaces (Claude Code, Cursor, Codex, Gemini CLI — permissions, hooks, sandboxes, mcp.json) and ship hash-anchored events to a central server + your SIEM. Fleet-wide posture; measures, doesn't block. Rust.

Web UI for opencode. Any device. Push notifications. Zero install.

The open-source skills library for Agentic Customer Success Operations. Hardened, multi-protocol playbooks designed for human CSMs and autonomous AI agents. Codifying technical API logic, expansion blueprints, and predictive churn-stop plays to close the Value Realization Gap. Licensed for internal business use. Please contribute & collaborate.

iKanban 是面向 OpenCode V2 的独立前端应用。iKanban is a standalone static frontend for OpenCode V2, based directly on the upstream shared desktop/web application.

Coordinate AI agents with human-in-the-loop control — YAML-based protocol, no server, any runtime

The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-demo

The first Minecraft AI that doesn't just talk—it lives in your world. High-performance Gemini-driven cognitive companion for Fabric 1.21.1.

Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval

Agent-Pilot · 飞书 AI 校园挑战赛 · 从 IM 对话到演示稿的一键智能闭环 | 6 Agent Multi-Agent Pipeline · MiniMax M2.7 Tool Calling · 飞书 Bot 全生态集成

Malaysian accounting skill for Claude Code. Process client documents into accrual-basis financial statements, working papers, and tax computations.

Zero-cost AI Chinese novel writing. 900K+ chars. 3 OpenClaw skills. ¥0 API spend.

Glossary of key concepts in Large Language Models (LLMs), Artificial Intelligence (AI), Natural Language Processing (NLP), and Machine Learning (ML). Clear definitions and resources for developers, researchers, and AI enthusiasts exploring generative language technologies.

Community MiroFish guide and AI-agent skill with operator workflow, troubleshooting, evaluation rubric, prompt engineering, model and proxy compatibility, runtime forensics, and report audit.

AI agent skills library built by OpenSite AI. A single git repo that keeps Claude, Codex, Cursor, Copilot, and Perplexity Computer in perfect skill sync, with persistent cross-session memory and automated cloud upload via Playwright.

Open-source agent orchestration platform with stigmergic coordination, AOA heartbeats, dynamic model routing, and custom agent personas. Fork of Paperclip, used to build Ancilis.

阿洛娜AI是一个以游戏《蔚蓝档案》（Blue Archive）中角色"阿洛娜"为原型打造的桌面AI助手。

Offline RAG-powered technical support agent for gas field engineers using Foundry Local, Phi-3.5 Mini, and SQLite vector store

Extensible AI agent framework in Go — multi-channel (Feishu/Slack/CLI), sandboxed tool execution, MCP integration, multi-tenant sessions

Minimal Coding Agent for use on iPad/iOS in a-Shell Terminal

SparkLabs - The First AI-Native Game Engine. Ignite Your Infinite Play! 💥 🎮

Sample application for Enterprise MCP server architecture. Built with Workato Enterprise MCP. Hospitality use case, with customer- and employee-facing agentic experiences.

Full Mistral AI MCP server — OCR, Voxtral audio, Codestral FIM, durable workflows, document extraction — for Claude Code, Cursor, Windsurf, Zed, Mistral Connectors

Hermes Windows Native Guide — Agent + WebUI, no Docker, no WSL2

AI-powered content generation and auto-posting engine built for Claude Code and Codex. Generate viral videos, carousels, and reels for TikTok, Instagram, and X using Grok. No API keys needed — uses browser cookies for both generation and posting. Template-first, agent-driven, free and open source.

In this article, I will show you how to build your first AI agent from scratch using Google’s ADK (Agent Development Kit). This is an open-source framework that makes it easier to create agents, test them, add tools, and even build multi-agent systems.

Debugging-first MCP server for n8n. Tools for workflow generation, linting, per-node execution diagnosis, and driving live n8n instances. Built for AI agents.

Control your local Claude Code (and other CLI coding agents) from your phone over Tailscale. Self-hosted, peer-to-peer, no cloud relay — your code, sessions, and API keys never leave your machine.

AAAR (Auto- Abaqus-Agent-Research)

agent-replay is a 100% local, SQLite-powered CLI tool for time-travel debugging AI agents that lets you replay execution traces, diff behavioral changes, fork runs to test fixes, and run AI-powered evaluations or safety guardrails to eliminate hallucinations and production failures.

Agentic knowledge retrieval redefined with an AI agent system that combines traditional RAG (vector search) with knowledge graph capabilities to analyze and provide insights about big tech companies and their AI initiatives. The system uses PostgreSQL with pgvector for semantic search and Neo4j with Graphiti for temporal knowledge graphs.

AI Fitness Coach — A full-stack AI fitness and nutrition assistant built with Next.js and Gemini AI. Generates personalized workout plans and diet guidance with chat sessions, profile memory, streaming AI responses, and a modern UI. Deployed on Vercel.

A terminal Tamagotchi — raise a virtual pet in your CLI. Phase 2: AI agent awareness. Phase 3: peer-to-peer pet visits.

The canonical open-source monorepo for production-ready MCP servers.

An AI agent for professional business analysis compliant with BABOK v3 (International Institute of Business Analysis) standard. Guides the analyst step-by-step through 8 stages - from project initialization to business case with ROI calculation.

MCP server exposing the free SportScore sports-data API as tool calls for Claude, Cursor, and Zed. Live scores, fixtures, standings for football, basketball, cricket, tennis.

A curated list of principles and technologies related to Agentic AI systems.

A tool for students to use, calling an agent to operate your Moodle.

DaVinci Resolve CLI, Python library, and MCP server. Automate editing, color, and rendering with LLM-friendly tools for AI agents (Claude, Cursor), declarative specs, and structured JSON output. No more silent None returns.

🏭 Production-grade multi-agent orchestration framework — 6 collaboration modes, 8 specialized tools, 4 execution paths. From simple chain-of-thought to LLM-driven deep clustering and dynamic workflows, one framework for every agent collaboration scenario.

A pure-skill, host-agnostic AI engineering harness: PRD → TRD → Plan → TDD → dual-agent review → archive. Works with Claude Code, Cursor & Codex. No MCP required.

論 — Ask multiple AI agents, get consensus. CLI tool for multi-agent design decisions. Currently supports Kiro, Claude Code, Copilot — more coming.

A launch-control room for your local AI agents — block minifig crew, NASA-style GO/NO-GO board, real-time events from Claude Code hooks and agent logs. No cloud, no simulation.

Any brain, any agent. Package an AI agent's brain — persona, MCP stack, skills, memory, config — into one open, signed bundle and install it into any framework (OpenClaw, Hermes, Claude Code) in one click.

Autonomous AI Agent built on tinyloom

Chatbot-GPT, powered by OpenIM’s webhooks, seamlessly integrates with various messaging platforms. This tool enables private and group chats with bots, enhancing interactive communication. It delivers quick, automated responses, ideal for optimizing customer service and dynamic discussions, meeting diverse communication needs.

Benchmarking RAG vs GraphRAG vs Compressed Knowledge Graphs on the McCreary Intelligent Textbook Corpus

Open, read-only MCP gateway over the Yochai knowledge graph of the Jewish textual tradition — for AI agents and developers.

Storage engine for AI agents to navigate, store, and retrieve structured data. PostgreSQL ltree, built-in versioning, scoped queries.

A multi-agent collaboration platform for CLI-based AI agents

New Update X69X BOT V3 ✔️

Copy and paste prompts for cursor agent. Free for anyone to use or add to. This repository provides a curated collection of advanced .mdc rules for Cursor IDE to optimize AI agent behavior, memory management, and development workflows.

An open-source companion repo for Agentique.io: a free community hub for discovering, sharing, and reusing trusted AI agent resources.

[ICML2026] The official code of "Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale"

Agentic scientific-computing platform: a reactive multi-agent team that orchestrates PINA physics-informed neural-network workflows via pydantic-graph, with MLflow tracing/provenance and a marimo chat UI (plus A2A & AG-UI servers).

A local memory and coordination layer for anything that can make an HTTP request — agents, devices, sensors, and humans on one network. Sovereign, local, no cloud.

A modern, framework-agnostic PHP package for adding customizable, AI-powered chat popups to any web application. Includes adapters for Laravel and Symfony, supports multiple AI providers, and is easy to extend.

Customize and enhance the UX/UI of ChatGPT and Gemini via user scripts. / ChatGPT・GeminiのUX/UIをカスタマイズするユーザースクリプト集

An Express and AI SDK agent that triages new GitHub issues on Vercel, applying labels and a maintainer reply.

Fast headless browser and native app automation CLI for AI coding agents — persistent Chromium via Playwright, camoufox stealth runtime, session multiplexing, MCP server, and Android/iOS/macOS app automation.

🤖 Self-Evolving Multi-Agent AI System | 116+ Skills | TrendRadar · Reviewer | Learn, Build & Evolve

MCP server that lets AI agents (Claude, Cursor) debug your .NET / ASP.NET Core app

Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.

Eliminates generic AI slop and enforces premium UI/UX design via 10 sequential gates, ratio-based layout/composition audits, and open-design craft integration.

Diagnosis-first Agent Skills that turn AI from answer machine into learning tutor.

Curated Orkas agents and skills for education, product development, content creation, data analysis, office automation, and e-commerce workflows.

The chunking benchmark

Advanced cognitive reasoning MCP server — DAG thought graph, 10 strategies, metacognition, self-critique, knowledge integration, and pruning

[ICML 2026] Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation

VELUNE CLI is an open-source AI engineering CLI that unifies local LLMs (Ollama), cloud AI providers, MCP servers, tools, memory, and project context into a single developer workflow. Build, code, automate, and orchestrate AI with one extensible, provider-agnostic command-line interface.

AI-assisted reverse engineering orchestration platform for IDA Pro and x64dbg with live synchronization and MCP agent workflows.

LifeOS — 会自我进化的个人第二大脑系统。五层架构、10个Agent、输入加工输出完整闭环。下载即用，把文章发给任意Agent软件一键搭建。

Open-source Human Design AI: BodyGraph charts, whole-chart talent and mission readings, DeepSeek consultation, FastAPI/React app, and Agent Skills. 开源人类图全盘解读。

Agent harness for general use. While Claude shits on you cutting corners all the time, Adame actually gets it's job done properly. Credit to @Nousresearch for heavily inspiring the framework draft