Ante - Self-contained offline coding agent in a single binary
Show HN: Ante, a coding agent in a single binary that runs offline
Ante is a coding agent that runs entirely from a single ~15MB Rust binary, with zero runtime dependencies. It works like Claude Code or Codex but without vendor lock-in or model constraints, supporting 12+ providers and fully offline local inference via GGUF models. Ante is optimized for efficiency, using ~7x less memory and ~9x less CPU than Claude Code, and is continuously benchmarked on Terminal-Bench 2.1, achieving 82.7% with DeepSeek V4 Flash. It offers interactive TUI, headless, server, and gateway modes, making it a versatile tool for developers seeking a lightweight, verifiable, and affordable agent for terminal-based coding tasks.
A ghost in your shell. Ante is a self-contained coding agent that lives in your terminal and self-organizes.
- NitpickLawyer
Linking to a github repo for a binary release (no source code related to the agent that I could see) is a bit iffy IMO. You should clarify your intentions or link to something else. Might confuse folks.
- messh
I understand that claude-code takes a lot of memory and that's bad. However, harneses are simple loops, in theory should take very little memory even if written in python or typescript. See for e.g. pi agent
- gumby
> “while taking the time to figure out how open source should work in the agentic era”
I can’t even guess what this means
- thih9
> We care about the harness, not the model or the prompts.
I wonder if this is a viable approach; after all frontier model providers are betting on the opposite.
Then again, they bundle their harness and offer subsidiary pricing - so maybe they themselves aren’t sure if models are as important.
- swrrt
How good is it to work on building games, compared to existing agents? I am building my own game?