Your Personal Super AI Assistant
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, autonomously grows with memory and knowledge. Multi-model, multi-channel, multi-agent. Lightweight, extensible, one-line install — runs 24/7 on your laptop or server.
Developer / Server Install
One command to install, configure, and launch — for developers and 24/7 servers
# Install and run CowAgent $ bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)
# Install and run CowAgent (PowerShell) > irm https://cdn.link-ai.tech/code/cow/run.ps1 | iex
# Install and run CowAgent (Docker) $ curl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml $ docker compose up -d
Core Capabilities
Not just chat — an AI assistant that actually gets things done
Task Planning
Decomposes complex tasks and executes them step by step, looping over tools and skills until the goal is reached.
Long-term Memory
Three-tier architecture (context → daily → core) with automatic Deep Dream distillation and hybrid keyword + vector retrieval.
Knowledge Base
Auto-curates structured knowledge into a Markdown wiki, building an evolving knowledge graph through cross-references.
Skills System
One-click install from Skill Hub, GitHub, and ClawHub, or create custom Skills through natural-language conversation.
Tool System
Built-in file I/O, terminal, browser, scheduler, memory retrieval, web search, and 10+ more tools — with native MCP integration.
Self-Evolution
Reviews conversations automatically to improve skills, follow up on unfinished tasks, and consolidate memory and knowledge.
Pluggable Models
Claude, GPT, Gemini, DeepSeek, Qwen, GLM, Kimi, MiniMax, Doubao, and more — swap providers with one click.
Multi-Channel
A single Agent integrates with Web, WeChat, Feishu, DingTalk, WeCom, QQ, and Official Accounts.
Multi-Agent Team
Create multiple Agents with distinct roles to form a team, with group-chat collaboration, task delegation, and sub-Agents — quickly build your own team of digital employees.
Models & Channels
Plug in any major LLM and deploy across multiple channels