AnyModelBot: Local-First Open-Source AI Agents for Desktop and Chat Apps
GitHub Open Source
Deploy a local-first AI agent to WeChat, Feishu, and Telegram that runs commands with a single Modelflare key.
Repository snapshot
- Repository: modelflare-ai/AnyModelBot
- Language: Python
- License: MIT
- Stars: 2 737
- Forks: 44
Daily open-source picks: GitHub Open Source on Telegram
What it is
AnyModelBot is a local-first desktop application built for Windows, macOS, and Linux that lets you run autonomous AI agents right on your own machine. Each bot acts as a distinct persona equipped with its own default model, isolated workspace directory, and persistent memory. Instead of forcing you into a single proprietary ecosystem, the project bridges your local file system and external chat networks like WeChat, Feishu, Telegram, Slack, and Discord into a unified operational hub.
Why it matters
Many developer workflows involve juggling multiple chat web apps while manually copy-pasting code, executing shell scripts, and tracking context across disparate systems. AnyModelBot addresses this fragmentation by keeping your conversations, memory fragments, and API keys stored locally on your device. By routing requests through Modelflare or your own direct vendor keys, it gives you the flexibility to swap between GPT, Claude, Gemini, Grok, and DeepSeek without changing your interface.
Key features
- Connect 70+ models across 13 providers using a single Modelflare billing key.
- Deploy multi-channel bots to WeChat, Feishu, Slack, and Discord alongside desktop chat.
- Enforce granular workspace permissions with read-only, workspace-bound, and full access tiers.
- Run background tasks and scheduled routines that ping you only when human decisions are needed.
- Import custom agent skills via packaged ZIP archives containing SKILL.md definitions.
Quick start
To run the project locally from source, ensure you have Node.js 22.13+ and Go 1.26.8+ installed, then execute the following commands:
git clone https://github.com/modelflare-ai/AnyModelBot.git
cd AnyModelBot
npm install
npm run setup
npm startWho should try it
This tool fits developers who want a self-hosted alternative to proprietary AI assistants and need deep integration with local files and everyday messaging platforms. If you prefer managing your own prompts, workspaces, and model choices without giving up desktop automation, it is worth exploring.
Verdict
AnyModelBot offers a mature, open-source approach to local agent execution with transparent permission boundaries. While it requires trusting external gateways for multi-model routing unless you supply direct API keys, its flexibility makes it a strong choice for local-first developer automation.
Continue exploring
Get the next pick in Telegram: Follow GitHub Open Source
Curated from the repository README and metadata. No hands-on test is claimed; evaluate it in a sandbox before production use.