Codync: open-source Rust tool turns AI agents into chatbots
Codync is a free Rust project that wraps more than 40 local AI agents into chatbots, enabling control from iPhone, Mac, Windows, Linux, or the terminal.
Codync is a free, open-source alternative to Grok Bot written in Rust. The program turns more than 40 AI agents installed on a computer, including Claude Code, Codex, Gemini CLI, and Cursor, into bots that users can chat with.
Users can send messages and assign tasks from iPhone, Mac, Windows, Linux, or the terminal. When a bot finishes work or needs action confirmation, the user receives a notification.
There are no paid tiers. Bots use the limits of the accounts under which the corresponding agents are authorized. Through the ACP registry, the program can automatically discover or load agents. It supports group chats with replies via and allows bots to ask each other for help.
Remote access runs through a free Cloudflare relay with end-to-end encryption. Devices on the same local network connect directly. The mobile app also provides remote screen viewing and voice calls over WebRTC.
More details: Codync on GitHub.
Why it matters
AnalysisIt reduces the friction of managing multiple AI coding agents across devices without paid plans, while preserving each agent's existing account limits.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Cloudflare Open-Sources Kitesurf, a Browser Built for AI Agents
Cloudflare released the source code of Kitesurf, a headless browser written in Rust and WebAssembly for AI agents and Cloudflare Workers.
DeepSeek open-sources part of its chat interface
DeepSeek has released the source code for a portion of its chat UI, including web search, deep thinking, and conversation history features.
Jev and System One AI: A Complete Practical Guide to the Decision Model from TypeSafe
A deep engineering breakdown of the flagship Jev model: System One architecture versus LLMs, Choice/Score/Noul primitives, request parallelism, confidence mathematics, video use cases, code, and an overview of local open-weight alternatives (Laya, GLiNER2.5, CLM-8B).
Open Weights vs Truly Open Source AI
A legal and engineering analysis of the fundamental difference between accessible numerical weights of models (Llama, DeepSeek) and fully open projects with source data, code, and architecture (OSI Standard).