Ran
6acdd191c7
commit bcdb026ae43e4f95d0b2c4f9bd440a2df9d6b514 Author: Ran <16112591+chen-ran@users.noreply.github.com> Date: Thu Feb 12 17:10:32 2026 +0800 chore: update DEVELOPMENT.md commit30281742efMerge:ca5c6a15b05f13Author: BBQ <bbq@BBQdeMacBook-Air.local> Date: Thu Feb 12 15:49:17 2026 +0800 merge(github/main): integrate fx dependency injection framework Merge upstream fx refactor and adapt all services to use go.uber.org/fx for dependency injection. Resolve conflicts in main.go, server.go, and service constructors while preserving our domain model changes. - Fix telegram adapter panic on shutdown (double close channel) - Fix feishu adapter processing messages after stop - Increase directory lookup timeout from 2s to 5s commitca5c6a1866Author: BBQ <bbq@BBQdeMacBook-Air.local> Date: Thu Feb 12 15:33:09 2026 +0800 refactor(core): restructure conversation, channel and message domains - Rename chat module to conversation with flow-based architecture - Move channelidentities into channel/identities subpackage - Add channel/route for routing logic - Add message service with event hub - Add MCP providers: container, directory, schedule - Refactor Feishu/Telegram adapters with directory and stream support - Add platform management page and channel badges in web UI - Update database schema for conversations, messages and channel routes - Add @memoh/shared package for cross-package type definitions commit75e2ef0467Merge:d99ba3801cb6c8Author: BBQ <bbq@BBQdeMacBook-Air.local> Date: Thu Feb 12 14:45:49 2026 +0800 merge(github): merge github/main, resolve index.ts URL conflict Keep our defensive absolute-URL check in createAuthFetcher. commitd99ba38b7dMerge:860e20f35ce7d1Author: BBQ <bbq@BBQdeMacBook-Air.local> Date: Thu Feb 12 05:20:18 2026 +0800 merge(github): merge github/main, keep our code and docs/spec commit860e20fe70Author: BBQ <bbq@BBQdeMacBook-Air.local> Date: Wed Feb 11 22:13:27 2026 +0800 docs(docs): add concepts and style guides for VitePress site - Add concepts: identity-and-binding, index (en/zh) - Add style: terminology (en/zh) - Update index and zh/index - Update .vitepress/config.ts commita75fdb8040Author: BBQ <bbq@BBQdeMacBook-Air.local> Date: Wed Feb 11 17:37:16 2026 +0800 refactor(mcp): standardize unified tool gateway on go-sdk Split business executors from federation sources and migrate unified tool/federation transports to the official go-sdk for stricter MCP compliance and safer session lifecycle handling. Add targeted regression tests for accept compatibility, initialization retries, pending cleanup, and include updated swagger artifacts. commit02b33c8e85Author: BBQ <bbq@BBQdeMacBook-Air.local> Date: Wed Feb 11 15:42:21 2026 +0800 refactor(core): finalize user-centric identity and policy cleanup Unify auth and chat identity semantics around user_id, enforce personal-bot owner-only authorization, and remove legacy compatibility branches in integration tests. commit06e8619a37Author: BBQ <bbq@BBQdeMacBook-Air.local> Date: Wed Feb 11 14:47:03 2026 +0800 refactor(core): migrate channel identity and binding across app Align channel identity and bind flow across backend and app-facing layers, including generated swagger artifacts and package lock updates while excluding docs content changes.
Memoh
Multi-Member, Structured Long-Memory, Containerized AI Agent System.
Memoh is a AI agent system platform. Users can create their own AI bots and chat with them via Telegram, Discord, Lark(Feishu), etc. Every bot has independent container and memory system which allows them to edit files, execute commands and build themselves - Like OpenClaw, Memoh provides a more secure, flexible and scalable solution for multi-bot management.
Why Memoh?
OpenClaw, Clawdbot, and Moltbot are impressive, but they have notable drawbacks: stability issues, security concerns, cumbersome configuration, and high token costs. If you're looking for a stable, secure Bot SaaS solution, consider our open-source Memoh.
Memoh is a multi-bot agent service built with Golang. It offers full graphical configuration for bots, Channels, MCP, and Skills. We use Containerd to provide container-level isolation for each bot and draw heavily from OpenClaw's Agent design.
Memoh Bot features a deeply engineered memory layer inspired by Mem0. By storing knowledge from each conversation turn, it enables more precise memory retrieval.
Memoh Bot can distinguish and remember requests from multiple humans and bots, working seamlessly in any group chat. You can use Memoh to build bot teams, or set up accounts for family members to manage daily household tasks with bots.
Features
- Multi-bot Management: Create multiple bots; humans and bots, or bots with each other, can chat privately, in groups, or collaborate.
- Containerized: Each bot runs in its own isolated container. Bots can freely execute commands, edit files, and access the network within their containers—like having their own computer.
- Memory Engineering: Every chat is stored in the database, with the last 24 hours of context loaded by default. Each conversation turn is stored as memory and can be retrieved by bots through semantic search.
- Various Platforms: Supports Telegram, Lark (Feishu), and more.
- Simple and Easy to Use: Configure bots and settings for Provider, Model, Memory, Channel, MCP, and Skills through a graphical interface—no coding required to set up your own AI bot.
- Scheduled Tasks: Schedule tasks with cron expressions to run commands at specified times.
- More...
Roadmap
Please refer to the Roadmap Version 0.1 for more details.
Quick Start
Docker Deployment (Recommended)
The fastest way to deploy Memoh:
git clone https://github.com/memohai/Memoh.git
cd Memoh
./deploy.sh
Visit http://localhost after deployment. See Docker Deployment Guide for details.
Development
Refer to CONTRIBUTING.md for development setup.
Star History
Contributors
LICENSE: AGPLv3
Copyright (C) 2026 Memoh. All rights reserved.