Browse all 21,375 AI agents

📝 Manage and organize Obsidian vaults with CLI tools for notes, tasks, tags, templates, and knowledge graph analysis.

MCP server for Obsidian — access your vault from any AI agent, even when your machine is off. Powered by Self-hosted LiveSync.

The missing bridge between your 10+ TB cloud drive and your AI brain.

MCP tool allowing Open WebUI or Claude Desktop to retrieve files from your vault

Framework for AI agents to build and maintain an Obsidian wiki using Karpathy's LLM Wiki pattern

A Model Context Protocol (MCP) server that enables AI assistants to interact with your Obsidian vault

More than a writing assistant — ObsidiBot turns your Obsidian vault into a personal AI platform

Multi-backend observability CLI for metrics, logs, and traces — unified interface, AI-Agent friendly

MCP servers for coastal oceanography

an agentic harness system written in rust

Effortless AI email digests delivered to your inbox

Panduan lengkap memanfaatkan OCI Always Free Tier - provisioning ARM Ampere A1, Tailscale VPN, Docker, dan deployment AI Agent (OpenClaw) sebagai asisten pribadi 24/7. Termasuk setup terminal UX dan g

OCode is a sophisticated terminal-native AI coding assistant that provides deep codebase intelligence and autonomous task execution

Turn your Claude Pro/Max subscription into an OpenAI-compatible API. One proxy, multiple IDEs, LAN sharing for the whole family. $0 extra cost.

Who this is for

FastMCP server providing advanced OCR capabilities with current state-of-the-art models (DeepSeek-OCR, Florence-2, DOTS.OCR, PP-OCRv5, Qwen-Image-Layered decomposition), WIA scanner control, and multi

An autonomous AI agent

A free MCP server to analyze and extract insights from public filings, earnings transcripts, financial metrics, stock market data, private market transactions, and deep web-based research within Claud

An MCP server that runs AI-driven venture capitalist agents (Fred Wilson, Peter Thiel, etc.), whose thinking is continuously enriched by Octagon Private Markets' real-time deals, valuations, and deep

Third-party adapters for OCTO — bridge AI agents, IM platforms, and external services into the OCTO workplace via OpenClaw channels and WebSocket.

Private, self-hosted AI agent — your models and data stay on your machine. A feature-rich coding + assistant toolset across six interfaces (CLI, Web, desktop, IM, VS Code, Obsidian), all in one fast,

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

🛰 Local agent runtime reporter for the OCTO platform — detects installed AI agent CLIs (Claude Code, Codex, OpenClaw, Hermes), reports status & bindings, supports one-click remote upgrades.

VEC-ATP multi-agent system

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

The brain for your LLM

A platform that enables agents to securely, reliably, and controllably invoke internal enterprise capabilities, execute only authorized business actions, and fully record invocation activity.

Semantic code searcher and codebase utility

Create custom SVG icons with just plain text

🐙 A self-hosted AI Agent companion. Powered by persistent memory (GHOST) to remember, learn, and evolve as your digital partner.

Plug and play AI agents for any domain

A smarter, self-hosted AI assistant — multi-user, multi-agent.

Secure multi-agent runtime with isolated workers and powerful task execution under strict boundaries.

Official Octoparse MCP server for AI-powered web scraping workflows.

The open-source memory operating system for AI agents. Persistent memory, semantic search, loop detection, agent messaging, crash recovery, and real-time observability.

🐙Octopus: Desktop AI Agent Framework · Multi-tentacle Collaboration

Open-source AI agent operating system: one file-native brain (190+ skills, 180+ specialist agents) run across many sealed client arms, with per-client token attribution and opt-in budget caps. Organic

OctosArmy is a highly secure, multi-agent AI system for totally autonomous file management. Powered by an elite team of LLM drônes that scan, analyze, and organize strictly inside defined sandboxes.

Dead simple AI-loaded browser for geeks

ODAI - Multi Agentic AI Tool System (Text and Voice)

OpenAPI sports betting odds API for coding agents with REST examples, SDKs, MCP, mock mode, arbitrage, positive EV, and bookmaker comparison.

An advanced ChatGPT alternative with constant access to real-time factual information

Self-hosted MCP server connecting Claude to Odoo 15→19 — 197+ tools, multi-tenant, Bulgaria l10n

Your team uses Odoo — without logging in to Odoo. Free, self-hosted AI assistant on Telegram & WhatsApp: employees apply for leave, approve requests, update CRM, validate stock — by chat, in 15 langua

Webextension tool for Odoo

Odylith stops coding agents from confidently doing the wrong thing

Odyssey: Empowering Minecraft Agents with Open-World Skills

Gain visibility and insight into repairs that OEMs are completing and transfer this information into Nuvolo

Offer To Purchase Real Estate AI Agent streamlines real estate offers with dynamic conversations.

Offers 転職プラットフォームと AI エージェントを接続する Skill セット（Claude Code / Codex CLI 対応）

Vision-first AI agent for desktop automation. Fully offline. Powered by YOLO, OCR & ResNet — building towards local intelligence.

A web UI coding agent that handles the full development loop: understand your codebase, plan features collaboratively, spin up isolated branch agents, write the code, and ship PRs — all in parallel. W

Context-engineering-powered multi-agent team workflow pack for Antigravity CLI.

oh-my-codex (omx) — Orchestration layer for OpenAI Codex CLI. Async Claude Code delegation (no timeouts), structured workflows (autopilot, TDD, code review, planning), persistent state & memory. Like

multi-agent system built with Github Copilot SDK

Xihe · 羲和 — the system around the model. A model-agnostic multi-agent runtime: deterministic orchestration, a self-consolidating memory, a cross-model verifier, and engineered taste. Wright is its fir

oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed ever

Context-engineering-powered multi-agent team workflow pack for Gemini CLI.

Production-ready multi-agent orchestration harness for Kimi Code CLI (K2.6): worktree team runtime, DAG/ensemble planning, MCP skill-hooks, quality gates, and local graph memory. | Kimi Code CLI(K2.6)

Production-ready multi-agent orchestration harness for Kimi Code CLI (K2.6): worktree team runtime, DAG/ensemble planning, MCP skill-hooks, quality gates, and local graph memory. | Kimi Code CLI(K2.6)