ArchestackBest of Open-Source AI: List on GitHub ↗ (opens in a new tab)

#2727th of 54 in Assistants

anymodelbot

Multi-bot desktop assistant with memory, file access and chat-app channels

Documentation ↗ (opens in a new tab)Website ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
3.1k
License
MIT
Last commit
Nov 2026
Last release
Nov 2026
Language
Python
Stars, last 2 weeks+3,085
27 Oct 2026: 58 stars3 Nov 2026: 2,379 stars10 Nov 2026: 3,143 stars

58 on 27 Oct 20263,143 on 10 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

AnyModelBot is an Electron/Node.js app for Windows, macOS and Linux that runs several bots, each with its own persona, default model, workspace and Markdown memory. Bots chat in-app or via WeChat, Feishu, Telegram, Slack and Discord, read and write files, run commands in a sandbox, and ask before writing outside the workspace. Models come from the Modelflare gateway (pay per use) or direct official API keys.

Who it is for: Users wanting a self-run multi-bot assistant reachable from chat apps

Strengths

  • Per-bot memory, persona and workspace, three permission levels, approval cards for outside writes
  • Connects to WeChat, Feishu, Telegram, Slack and Discord with shared account setup
  • Background tasks and scheduled rules with per-task budgets, quiet hours and daily message caps
  • Direct keys for OpenAI, Anthropic, Gemini, xAI, DeepSeek, Kimi, GLM, Qwen, MiniMax, Mistral

Weaknesses

  • Default model route goes through hosted Modelflare, which keeps request logs
  • Image and video generation only work through Modelflare, not direct API keys
  • Chat channels handle one-to-one chats only; group chat exists only inside the app
  • Rules do not run while the computer is off; macOS computer use is Beta

What it needs

  • no GPU
  • Docker
  • Needs Modelflare account or official provider API keys, Node.js 22.13+ and Go 1.26.8+ (source builds only), Python 3.10+ and FFmpeg (video studio bot only)
  • Models: Modelflare-hosted models, OpenAI, Anthropic, Google Gemini, xAI
  • port 3600

Quick answers

Is anymodelbot open source?

Yes. Its code is on GitHub under the MIT license.

Can you run anymodelbot with Docker?

Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.

Does anymodelbot need a GPU?

No, it runs without one.

Also in Assistants

See all 54
Also in Assistants
RankProjectScore
1ai-job-searchClaude Code workflow that searches job boards and drafts tailored CVs and cover letters71.2k starsMIT96 out of 100
2career-opsJob-search agent that scores listings, tailors CVs and drafts applications81.9k stars+8,035 (+11%) in 30 daysMIT95 out of 100
3OpenClawPersonal AI assistant reachable through Discord, Slack, Telegram, WhatsApp and more394.3k stars+4,398 (+1.1%) in 30 daysMIT93 out of 100
#4openhumanRust agent harness with desktop app, built-in memory and embeddable library42.7k stars+984 (+2.4%) in 30 daysGPL-3.093 out of 100
#5airiAI VTuber companion with VRM and Live2D avatars, voice, and game-playing Live demo ↗ (opens in a new tab)51.3k stars+1,184 (+2.4%) in 30 daysMIT91 out of 100