Harness²

Better Harness is an open-source Harness Engineering platform for coding agents. It analyzes project and, where supported, session evidence around an agent's work rather than only its final code diff, evaluating the Agent Work Loop for issues such as task understanding, validation, delivery control, and retained lessons. It turns supported gaps into prioritized findings linked to their evidence, expected outcomes, repair boundaries, and acceptance checks, and produces host-specific reports in formats including HTML, paired Markdown, or native Canvas reports. The platform also supports defining harnesses as code, running controlled experiments, inspecting evidence, and comparing outcomes across coding-agent hosts such as Claude Code, Codex, Qoder, Cursor, and GitHub Copilot CLI.

Harness Engineering is Ryan Lopopolo’s anthology, field guide, and agent-context repository for improving coding-agent output without changing the underlying model or coding agent. It shapes the surrounding environment through context and tools so an agent can recover intent, operate the real system, respect authority, prove its outcome, and incorporate lessons from accepted work, corrections, failures, and user responses. The repository uses AGENTS.md to route agents to relevant arguments, cases, and proof, and provides a thesis index, playbooks, source material, and executable constraints for encoding organizational requirements and decisions. Repository-authored material is licensed under CC BY 4.0.

FrontierHarness Eval is an open evaluation benchmark and repository for measuring how coding-agent harness configurations affect software-engineering task results when the underlying model and runtime are held constant. It publishes benchmark definitions, task instructions and metadata, harness-version metadata, normalized aggregate and task-level results, and an agent-neutral workflow for evaluating additional harnesses. The benchmark runs the same model through multiple harness configurations on 30 tasks, using a frozen golden checkpoint and a fresh restore for each task. Its scripts provision the environment, run trials, record verifier-based pass/fail outcomes, measure cost, cache behavior, and speed, then normalize results and generate charts and reports. The repository also provides a CLI and skill-based workflow for evaluating a third-party harness, with infrastructure failures marked separately from task failures. The project focuses on terminal-based software-engineering tasks and states that its results may not generalize to other knowledge-work domains. The repository is published under the frontier-harness-eval organization, with isolated runtimes and checkpoint restores provided by Runta.

OpenVLHarness is an open-source framework for turning multimodal language models into visual agents without fine-tuning their backbone weights. The model selects tools and reads their evidence through nine task-level capabilities: visual grounding, OCR, depth estimation, camera-trajectory estimation, image zoom, text search, reverse image search, webpage visits, and a Python coding agent. Its multimodal memory keeps images, boxes, masks, depth maps, numerical data, and web references addressable across a question, allowing later tools or generated Python code to combine earlier results—for example, locating objects, estimating their spatial relationship, or searching for and verifying an unfamiliar object. The harness includes model presets, a configurable tool router, evaluation utilities, and support for local or API-served models; the main code is released under the MIT License, while some evaluation, visualization, model, service, and dataset components have separate licenses. The local Python coding executor runs with the agent host's permissions and network and filesystem access, so it should be isolated when handling untrusted workloads.

HarnessRouter Community Edition is the open-source edition of HarnessRouter, an agent-harness infrastructure that provides a unified Agent API to integrate language models and agent runtimes. It is maintained by HarnessRouter and is intended for deployment on users' own infrastructure to connect models such as Codex, Claude Code, and Hermes.