An agent harness written in rust, 100 % self-contained, and topped terminal bench
Summary
Ante is a lightweight, self-contained terminal agent harness written in Rust, designed to be fast and dependency-free. It topped Terminal Bench 2.0 and remains highly responsive to user feedback despite being in preview and not yet open-sourced.
Similar Articles
Show HN: Ante, a coding agent in a single binary that runs offline
Ante is a self-contained coding agent in a single ~15MB Rust binary from Antigma Labs, designed to run entirely offline with built-in inference. It boasts strong Terminal-Bench 2.1 results, low resource usage compared to Claude Code, and supports GGUF models.
Your agent is only as good as its harness. I open-sourced one with 40 capabilities behind a single function call
An open-source agent harness with 40 capabilities behind a single function call, including persistent memory, Docker sandbox, auto-summarization, stuck-loop detection, budget caps, and live run forking for branching agent execution. Built on Pydantic AI and designed to replace the 2000 lines of glue code every production agent needs.
I built agentwerk, a tiny Rust crate for scaling agent collaboration focusing on getting work done
The author introduces agentwerk, a lightweight Rust crate designed for scaling agent collaboration through a ticket system, aiming to provide a simpler alternative to bloated frameworks like LangChain or AutoGen for human-in-the-loop-free pipelines.
hip-agent: a harness that fits in the prompt (5 minute read)
hip-agent is a minimal agent harness that fits within the prompt, allowing AI models to read and adapt their own harness using simple tools like shell commands and existing protocols. It is designed to be repairable and suitable for subagent tasks.
Built an agent harness with cost control and native MCP support
Agentic Harness is a new open-source Python infrastructure that turns YAML files into executable agent workflows, featuring markdown audit logs, pre-built specialists, cost guardrails, native MCP support, and local model integration.