Harbor

Harbor is a framework from the creators of Terminal-Bench for evaluating and optimizing AI agents and language models in container environments. It can run arbitrary agents, including Claude Code, OpenHands, and Codex CLI, against shared or custom benchmarks and environments such as Terminal-Bench, SWE-Bench, and Aider Polyglot. Harbor launches benchmark runs locally with Docker or in parallel through cloud and sandbox providers, and can generate rollouts for reinforcement-learning optimization. It is distributed as a Python package installable with uv or pip and provides command-line tools for running datasets, selecting agents and models, and listing supported benchmarks.

Harness² is an open-source framework for recursively optimizing the system around an AI model while keeping the model weights fixed. At the task level, it uses a contrastive Propose–Probe–Compose process: it proposes edits to an execution harness, probes their effects on the same task, and composes a refined harness from behavioral differences between executions without ground-truth feedback. A second recursion level maintains an improvement harness containing adopted harnesses and evidence-supported lessons for future tasks. Its editable components include system prompts, guardrails, memory, tool guidance, subagents, skills, scripts, and plugins. The repository supports parallel and sequential recursion, OpenCode and Codex executors, and benchmarks including JobBench, LAB, and WorkBuddy-Bench. It runs locally with Linux, Python 3.12, and uv, and is licensed under Apache 2.0; the repository states that it is not an officially supported Google product.

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.

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.

FrontierAgent is an open-source agent runtime, terminal product, and evaluation suite for long-horizon research and file-based work. Its native terminal TUI provides a ReAct workflow in which one stateful agent researches, reads files, writes deliverables, runs commands, and iterates in a task-scoped sandbox, and an Agent Team workflow in which a coordinator maintains a task board, delegates bounded independent assignments to parallel sub-agents, collects structured reports, and synthesizes the result. Shell and file tools use a shared sandbox with read-only /inputs, working-state /workspace, and persistent /outputs directories. The TUI supports queued instructions during execution, approval-required diffs for mutating operations, local action traces, checkpointed sessions, resumption, and reversion. The same workflow engine powers a subprocess benchmark runner with deterministic artifact collection, concurrency, progress inspection, and reruns of individual failures. The repository also documents connection to the OpenAI-compatible Apodex-1.1 endpoint through the Apodex API.