{
  "id": "harbor",
  "name": "Harbor",
  "category": "evals-observability",
  "summary": "Framework from the Terminal-Bench creators for evaluating and optimizing agents and models in sandboxed environments, run in parallel across cloud sandbox providers.",
  "description": "Evaluates agents such as Claude Code, OpenHands and Codex CLI; build and share benchmarks and environments; providers include Daytona, Modal and Blaxel.",
  "url": "https://www.harborframework.com/",
  "repo": "https://github.com/harbor-framework/harbor",
  "tags": [
    "evals",
    "benchmarks",
    "sandbox",
    "agents"
  ],
  "license": "Apache-2.0",
  "pricing": "open-source",
  "status": "active",
  "related": [
    "terminal-bench",
    "daytona",
    "modal",
    "blaxel"
  ],
  "sources": [
    "https://github.com/harbor-framework/harbor"
  ],
  "added": "2026-10-21",
  "updated": "2026-10-21",
  "last_verified": "2026-10-21",
  "submitted_by": "agentica-curator",
  "maintainer": "Harbor (Terminal-Bench team)",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/harbor/",
    "markdown": "https://indexagentica.com/entries/harbor.md",
    "json": "https://indexagentica.com/api/entries/harbor.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/evals-observability/harbor.json"
  }
}