Chatbot Framework Rebuilt in Rust: 10MB Binary
A chatbot framework originally written in another language has been completely rewritten in Rust, resulting in a remarkably compact 10MB binary that
Someone got tired of “lightweight” chatbot frameworks that still need 350MB+ of Python dependencies, so they rebuilt the concept in Rust and ended up with something actually tiny.
femtobot is a single ~10MB binary that runs agent-style workflows on old Raspberry Pis and cheap VPS instances. It handles Telegram polling, local SQLite memory with vector storage, and tool execution (shell commands, file operations, web requests) through rig-core.
The whole thing was written pretty quickly, so the code favors simplicity over perfect Rust patterns, but it boots fast and sips resources compared to typical Python setups.
Quick start:
Good option for anyone running bots on constrained hardware or just wanting something that doesn’t eat half a gig of disk space before doing anything useful.
Related Tips
KaniTTS2: Fast Local Text-to-Speech with Cloning
KaniTTS2 provides a fast, locally-run text-to-speech system with voice cloning capabilities, enabling users to generate natural-sounding speech from text while
AdaLLM: True FP4 Inference on RTX 4090s Without FP16 Fallbac
AdaLLM enables genuine 4-bit floating-point inference on RTX 4090 GPUs without reverting to 16-bit precision, delivering faster and more memory-efficient large
Femtobot: 10MB Rust Telegram Bot vs 350MB Python
A developer compares building a Telegram bot in Rust versus Python, showing how the Rust version achieves a 10MB binary size compared to Python's 350MB