Logo
Deploy Now

SaaS Alternative

Claude

Categories

Self-Hosted Automation Chatbot AI Agent Containers Multi Agent Memory

Stars

2,074

Forks

201

Watchers

11

Developer links

Last Updated: 08-22-2026 04:52 PM (UTC)

Memoh

Memoh delivers an open-source multi-agent platform where every AI agent gets its own computer — not a chat window but a fully isolated container with dedicated filesystem, desktop environment, browser, network stack, and persistent long-term memory that survives across sessions, days, and platforms. The containerd-based runtime ensures each bot operates in complete isolation with snapshot and data import/export capabilities. The memory engine uses LLM-driven fact extraction with hybrid retrieval combining dense embeddings via Qdrant, sparse vectors, and BM25, plus 24-hour context loading and automatic compaction — with Mem0 and OpenViking as drop-in alternatives. Ten communication channels connect agents to users through Telegram, Discord, Lark, QQ, Matrix, WeCom, WeChat, Email, Web UI, and group chats with cross-platform identity binding. MCP tool calling enables agents to interact with external services, while browser automation drives GUI workflows for web research and data extraction. Agent hosting supports running external coding agents like Codex and Claude Code inside Memoh workspaces via ACP with per-bot configuration. Scheduled tasks run without human triggers, and agents proactively reach out when needed. The web dashboard built with Vue 3 and Tailwind CSS provides streaming chat, tool call visualization, file management, model and provider configuration, and bot lifecycle management. Deploy via Docker Compose with PostgreSQL, Qdrant, sparse service, and the Go backend server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Memoh

Benefits

  • Containerized Agent Computers
  • Each agent runs in its own isolated containerd container with dedicated filesystem, desktop, browser, and network — real computing environments that persist independently with snapshots.
  • Built In Long Term Memory
  • LLM-driven fact extraction with hybrid dense and sparse vector retrieval via Qdrant enables agents to remember context across sessions, days, and platforms without manual configuration.
  • 10 Plus Communication Channels
  • Connect agents to Telegram, Discord, Lark, QQ, Matrix, WeCom, WeChat, Email, and Web UI with cross-platform identity binding and multi-bot group chat capabilities.
  • Always On Agent Hosting
  • Agents run in the cloud 24/7 independent of your laptop, executing scheduled tasks, proactively reaching out, and hosting coding agents like Codex and Claude Code via ACP.

Features

  • MCP Tool Integration
  • Model Context Protocol enables agents to call external tools and services with structured schemas, extending capabilities beyond conversation into actionable automation.
  • Browser Automation
  • Each agent's dedicated browser drives GUI workflows for web research, data extraction, and form filling with isolated profiles and network access.
  • Memory Provider System
  • Built-in hybrid retrieval engine with dense embeddings, sparse vectors, and BM25 scoring, plus drop-in alternatives via Mem0 and OpenViking providers.
  • Vue 3 Web Dashboard
  • Modern management interface with streaming chat, tool call visualization, file management, model configuration, provider management, and bot lifecycle controls.
  • Multi User Multi Bot
  • Deploy one agent per person, run a fleet for team operations, or create specialized bots that chat privately, in groups, or autonomously with each other.