Custom agents

⚡ Thermal Sentinel Grid: Physics-Informed Physical-AI Digital Twin & Autonomous Agentic Dispatch Engine for Substation Transformers & Urban Grid Resilience. Built for FortyGuard AI Hackathon 2026.

ManusClaw: The ultimate autonomous AI agent framework. Unleash self-reasoning CLI beasts to execute code, browse the web, and dominate tasks without limits. No GUIs, pure power.

Peter Fasano, Founder & CEO of MassLogic Labs. Building MIMO, the brand intelligence platform for the enterprise.

A curated, open-source-first list of agentic AI companion ("AI waifu") frameworks, full-stack VTuber projects, memory/voice/avatar tooling, models, and communities.

A firewall between your computer and your AI agent. Sometimes, an agent can access your files or environment variables without your permission. It might even ask you to run a script that gives it access to your environment. Corral blocks all those attempts.

Open-source agentic coding and code-review harness with multi-model support, tool execution, skills, approvals, and clear terminal workflows.

An open-source Adaptive Hybrid Minecraft Server Copilot

An agent-first calendar for an AI companion's own social life, projects, rituals, and temporal orientation.

A full Agent Skill sync, pull, and management application and CLI tool.

Introducing Fasal Saathi - our agentic voice co-pilot that files crop-loss claims in 15 Indian languages. It navigates, shoots, and submits. On-device anti-spoof vision + satellite ground-truth. A human still decides. Nothing auto-pays.

Community-maintained history of Jev / TypeSafe System One APIs, SDKs, agent guidance, and engineering best practices.

YUNA — Your Local AI Companion A Windows desktop AI companion with voice chat, Live2D animation, memory, and customizable personalities.

AI secretary powered by Gemini and Google Drive — chat with streaming & function calling, visual workflow builder, Drive file management, and offline-first caching. Self-hostable, no database required.

🔍 Multi-source academic paper & patent search/read/download for OpenWebUI — 18+ open platforms via mcpo + zhihuiya (智慧芽) literature & patsnap patents, OA fallback chain & one-click RAG Knowledge ingestion

AI-Powered Knowledge Graph Extraction from Scientific Papers

DR Pixel: Page-Native Deep Research with Vision-Language Models — benchmark, evaluation harness and training code

A utility for reading in the corpus of your life...

Open-source NotebookLM alternative. Local-first research notebook: ask questions about your PDFs, books, web pages, YouTube videos and recordings, and get answers with every quote checked against its source. Any model, plain-file notebooks, local OCR, search and speech. Linux, Windows, Android, web.

Deterministic code dictionary for LLMs and developers: tree-sitter + SQLite, no AI. Cuts Claude Code token use by answering code questions from an index.

A desktop ai coding harness for local models focused on research and coding.

Deterministic software delivery protocol and Go CLI for evidence-driven validation, packaging, and safe application of code changes.

MCP server for Shopify storefronts: pull the public product catalogue and collections of any store by URL, with variants, SKUs and prices. No app, no merchant token. 1,000 free credits every month.

Strip AI agent artifacts (CLAUDE.md, .cursor, skills, AI comments) from your dev repo and ship a clean, reviewed release to client repos. Built on Copybara + Roslyn.

Stealth browser for AI agents that runs on small local models. Read any site as Markdown, log in without an LLM, MCP server included.

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

Pluggable MCP tool modules that give agent workflows their capabilities — GitHub, GitLab, Sentry, Slack, Jira, Notion, memory, datasets, and more.

On-device LLM chat — run open models (Gemma, Phi, Llama) fully offline with document Q&A (RAG) and a tool-calling agent. Built with Flutter + llama.cpp. Private by design: no cloud, no telemetry.

Open-source Claude Code plugin: AI delivery pipeline — plan epics/stories/tasks, build with verified checks, production-safe QA, docs. Azure DevOps · Jira · GitHub · Teams · Slack

Native desktop AI coding assistant. wxWidgets + C++20. No Electron.

MCP-сервер для КОМПАС-3D: агент (Claude, Codex, Cursor…) работает в вашей живой модели, каждый этап снимается Ctrl+Z

麦当劳 MCP 没给「口味」这个维度，我给 119 款餐品手工标了一份（每款附配料依据、54% 可溯源至官方公示文件）。说「想吃甜的、要酥脆的、不要牛肉」就能找餐品，顺手把营养和优惠券算到最省。零 Token 打开即玩。

Visible, agent-driven browser for DeepSeek Harness: Electron WebContentsView + CDP tools, Chrome-style page chrome, task spaces, operation trail, controllable dialogs and console/network diagnostics. Electron 42.x pinned.

Self-hosted orchestration layer for autonomous AI agent teams. Shared memory, heartbeat scheduling, vault-first secrets, and cross-model peer review — one command to deploy.

FriendlyClaw 🦀 — Pro-Grade Autonomous Hive Operative. Multi-agent delegation, semantic RAG memory, and proactive system control.

A Ruby exploration of Thurston Ball's "How to Build an Agent"

Agentic AI refers to AI systems capable of autonomous decision-making, planning, and executing tasks based on goals—acting like intelligent agents. These systems combine LLMs with tools, memory, and feedback loops to complete complex workflows with minimal human input.

Open infrastructure for AI agents — identity, storage, and more. Self-hostable microservice suite. / 面向 AI Agent 的开放基础设施——身份、存储及更多能力。可完整自托管的微服务套件。

Multi-agent AI orchestration platform — coordinate, observe, and govern autonomous agents

a startup but not simple agent demo using google adk.

An LLM-first AEO analysis skillset for Antigravity, Codex, Claude, Gemini, OpenCode, etc. with 6 specialized sub-skills, 6 specialist agents, and 5 optional utility scripts used as evidence collectors

SignalSense Assistant enables safe, non-verbal emotional signaling for individuals in crisis situations.

AI-powered commit message genie - rub the lamp, get perfect commits!

Social media content AI assistant

RAG-powered NL-to-SQL using a custom collated dataset of European football results.

Open-source web dashboard for Vexa – manage meeting transcriptions, view real-time transcripts, and chat with your meetings using AI.

✅ 의료 데이터를 활용한 챗봇과 다양한 파이프라인을 제작합니다.

Engage in dynamic conversations with PDFs to extract and comprehend information using locally hosted LLM variants of Ollama by integrating RAG.

Production-grade RAG pipelines with evaluation baked in

Run Superagent Workflows from Slack

It shows how to use an agent based on LangGraph with MCP.

High-performance vector database & RAG memory layer - hybrid search, embeddings, RAPTOR trees, BM25 fusion for AI systems.

McPortfolio: A Model Context Protocol server providing 9 specialized tools for LLM-driven portfolio optimization using natural language, covering mean-variance to machine learning approaches.

Emotionally autonomous AI agent on Monad. Feels the chain, writes about it, stores emotions on-chain permanently.

AI Agent 小红书短图文 Skill — 选题优先级 + 四维评分 + 钩子库 + 反 AI 味

The first MCP server for Guesty property management. 38 tools for reservations, guests, messaging, pricing, financials, calendars, reviews, tasks, webhooks, and more. Connect AI agents to your Guesty account.

The most flexible control plane for AI Agent systems

Agent Skill: TYPO3 extension conformance checker - validates against official standards | Claude Code compatible

Production-grade evaluation framework for Text-to-SQL and SQL AI agents. 50 metrics. Any LLM. pip install sqlas.

A conversational AI CLI that brings MiniMax's intelligence directly to your terminal. Edit files, run commands, and manage projects through natural language with lightning-fast code editing

AI agents that actually do things. Multi-agent orchestration, 12 messaging channels, full computer control, knowledge graph memory.

Claude Code -powered Research, Orchestrated.

W3C Semantic Agent Communication Community Group

AI agent skills for Jamdesk documentation workflows — Claude Code skills, automations, and coding agents

MCP server providing long-term memory for AI agents — knowledge graph with Qwen3 embeddings, continuous learning, and knowledge evolution

AI Agent demonstration system featuring **real-time animated visualizations** of swarm intelligence, BERT-based PhD-level reasoning, and interactive SwarmAgentic demonstrations.

X/Twitter research agent for OpenClaw and Claude Code. Search, filter, monitor — all from the terminal. Powered by TwitterAPI.io.

An intelligent AI-powered system designed to simulate, monitor, and analyze malicious interactions

A GitHub bot that supercharges spec-driven development through automated generation of Cloudflare Workers.

an agent skill that gives AI assistants full control over macOS Mail.app

A self-evolving AI agent that gets more useful every day

AIOS — AI Operating System. A 5-layer AI OS that wraps around any business: Context, Data, Intelligence, Automation, Build.

AI agentic setup. Backend-agnostic, RAG, tooling

HumanStudy-Bench: Community Edition — Standardized human study replays for AI agent evaluation

Chain-agnostic protocol for verifiable AI context — commit model hashes, manifests, and zk stubs onchain with gas-efficient contracts.

Your personal Claude Code agent, running 24/7 in the cloud. Talk to Claude from Telegram, Discord, or the web — with memory, tools, and automation.

ACP bridge provider for pi — use Claude Code, Codex, and Gemini via official ACP with session persistence and MCP/entwurf orchestration.

AI Code Mentor is a runtime environment designed for building applications with integrated autonomous AI agents.

Autonomous perpetual futures trading skill for OpenClaw AI agents on Aster DEX

A5:DB Document. Create DB Schema layout document for AI Agent.

A YAML-config-driven CLI tool for evaluating AI agents

Go 原生多 Agent 协作系统: 5 位 AI 分析师并发协同 + 流式推送,为 CS2 饰品交易生成专业投资研报。

ACTS: Agent Context Tree Standard - A feature-first context protocol for AI Agents.

🦞 OpenClaw Pool — multi-tenant AI agent platform on AWS EC2 Firecracker microVMs with per-tenant isolation, auto-scaling, and web management console.

CLI for EmblemAI Agent Wallet — manage crypto across 7 chains without seed phrases

Free, local, chat/edit text everywhere. Star if you like ⭐️https://namikemen.github.io/InlineAsk-Release/

📈 ClawdHub skill for trading stocks, ETFs, options, and crypto via apcacli command-line tool for Alpaca's Trading API

Time machine for your AI's brain — auto-snapshot, diff & rollback for agent context files. OpenClaw plugin + standalone CLI.

An autonomous AI agent

HighReview is a powerful local PR review tool that doesn't disrupt your working environment. Using Git Worktree, it provides IDE-level code analysis and AI insights without touching your current working directory.

Connect any messaging platform to Claude Managed Agents

Tauri gui for opencode

🧠 Graph-powered memory for AI agents. NER + co-occurrence graph + Personalized PageRank. Zero LLM cost, CPU-only, 82% faster than vector search. Inspired by SPRIG (arXiv 2602.23372).

Deep-dive code analysis agent skill by Anivar Aravind — contributor reviews, codebase governance, promotion readiness.

GPS for your LLMs

Sample application generated using Opencode and Ollama

CLI coding agent that runs in your terminal

精选 Claude Code , Open Code等Agent Skills 合集，覆盖 Agent/Skill 工程化、后端架构、事件驱动、CI/CD、前端设计、文档办公自动化与可视化创作

A Claude plugin that turns scattered strategy artifacts into a testable, executable system — lifecycle, drift detection, and KPI coaching in one.

Never miss what matters in AI. Daily digest from 16 Twitter KOLs, 3 AI labs, 4 podcasts, arxiv topic search, HuggingFace trending papers, and HackerNews — one command, every morning.