Ante: A Single-Binary Coding Agent That Runs Offline

Ante is a self-contained coding agent that lives in your terminal. It's a single ~15MB Rust binary from Antigma Labs with zero runtime dependencies. It works like Claude Code or Codex, but without their dependency chains or model constraints. You can run it fully offline with a local GGUF model.
Key Features
- Single binary: Hand-written Rust with Grep and git embedded — one process, no external tools.
- Natively offline: Uses a pinned, managed llama.cpp build. Point it at a GGUF file and the whole loop runs locally — no API key, no account, no internet.
- Low resource usage: Across 20 parallel Docker tasks, Ante uses ~7× less peak memory, ~9× less average CPU, and ~5× less disk I/O than Claude Code.
- Continuously benchmarked: Runs Terminal-Bench 2.1 under official leaderboard constraints. Latest full run: 82.7% with open-weight DeepSeek V4 Flash 0731 (368/445 trials, Ante 0.preview.71, ~$68 of inference).
Quick Install
Install with one command:
curl -fsSL https://ante.run/install.sh | bashInstall a specific release channel:
curl -fsSL https://ante.run/install.sh | bash -s -- nightlyInstall to a directory already on PATH:
curl -fsSL https://ante.run/install.sh | ANTE_INSTALL_DIR=/usr/local/bin bashUsage Modes
- Interactive TUI:
ante— day-to-day work in the terminal - Headless:
ante -p "..."— one-shot tasks, scripts, CI - Server:
ante serve— editor plugins and integrations via JSONL protocol - Gateway:
ante gateway— run as Slack or Discord bot
Offline Mode Example
ante --offline-model ~/.ante/models/Qwen3.5-9B-Q4_K_M.gguf \
-p "add error handling to src/main.rs"Telemetry and Source
Telemetry is opt-out via ANTE_TELEMETRY=off. Sends only an anonymous installation label that you can re-mint. The core harness currently ships as a prebuilt binary; the repo holds docs, protocol, SDK, and eval pipeline — but they plan to address source release.
📖 Read the full source: HN AI Agents
👀 See Also

Custom status line for Claude Code shows context usage, rate limits, and token counts at a glance
A custom script adds a persistent status line to Claude Code, displaying context %, 5-hour rate limit %, KV cache reads, cumulative input/output tokens, model name, and working directory — color-coded for dark terminals.

Quanta-SDK v0.9.2 adds MCP server for quantum circuit execution via AI agents
Quanta-SDK v0.9.2 now includes an MCP (Model Context Protocol) server that provides AI agents like Claude or GPT with tools to execute and interpret quantum circuits. The server offers over 20 tools including circuit execution on IBM hardware, result interpretation, noise analysis, and quantum financial pricing.

lazyclaude: A TUI for Managing Claude Code Configuration
lazyclaude is a terminal user interface tool inspired by lazygit that provides a single view for managing all Claude Code configuration stored on disk, including memory files, skills, agents, MCP servers, settings, permissions, hooks, keybindings, sessions, stats, plugins, and todos.

Claude's Code Dashboard Tracks 19M+ AI-Generated Commits on GitHub
A developer built a dashboard tracking over 19 million commits generated by Claude Code on GitHub public repositories, showing TypeScript (35.3%), Python (19.2%), and JavaScript (10.3%) as the top languages. The system uses Next.js with Recharts and PostgreSQL, with an ETL pipeline that works around GitHub's API rate limits.