Skip to content
Tech News
← Back to articles

Show HN: Ante, a coding agent in a single binary that runs offline

read original more articles
Why This Matters

Ante introduces a lightweight, offline-capable coding agent built in a single Rust binary, enabling developers and consumers to run high-performance AI models locally without dependencies or internet access. Its minimal footprint and open evaluation metrics make it a significant step toward accessible, verifiable AI tools that can operate independently of cloud services, fostering greater privacy and customization in the tech industry.

Key Takeaways

Ante

Alpha preview: expect breaking changes and incomplete functionality. macOS and Linux only; on Windows we suggest WSL.

A ghost in your shell. Ante is a self-contained coding agent that lives in your terminal and self-organizes. One ~15MB Rust binary from Antigma Labs, zero runtime dependencies, built to get the most out of any model.

It works like Claude Code or Codex, with none of their dependencies or model constraints. It can also be the optimized core for building your own harness and high-performing assistants.

curl -fsSL https://ante.run/install.sh | bash ante

Every agent claims to be good. Here are numbers you can check:

🥇 Continuously evaled and evolved, in public

Ante runs Terminal-Bench 2.1 continuously under official leaderboard constraints: 89 tasks, 5 trials each. Each result pins the exact build you can download and links the raw Harbor run for independent audit. Latest full run: 82.7% with open-weight DeepSeek V4 Flash 0731 (368/445 trials, Ante 0.preview.71, about $68 of inference). DeepSeek reports the same 82.7 for this model, measured with its unreleased DeepSeek Harness in minimal mode.

Live results → · Methodology →

🪶 A fraction of the footprint

... continue reading