{
  "schema": "tesign-radar/item/1",
  "generated_at": "2026-09-22T07:26:19.753Z",
  "lang": "en",
  "slug": "agentmeasure",
  "url": "https://tesign.com/en/item/agentmeasure/",
  "alternates": {
    "ko": {
      "html": "https://tesign.com/item/agentmeasure/",
      "json": "https://tesign.com/item/agentmeasure/index.json",
      "markdown": "https://tesign.com/item/agentmeasure/index.md"
    },
    "en": {
      "html": "https://tesign.com/en/item/agentmeasure/",
      "json": "https://tesign.com/en/item/agentmeasure/index.json",
      "markdown": "https://tesign.com/en/item/agentmeasure/index.md"
    }
  },
  "name": "AgentMeasure",
  "use_label": "Audit your Codex and Claude Code logs",
  "one_liner": "Reads your Codex and Claude Code session logs and surfaces repeated failures and retries, with the evidence attached.",
  "text": {
    "why": "An agent that edits the same file over and over, or hits one failed tool call after another, is easy to miss when it is buried in a log. AgentMeasure reads the session logs you already have and finds duplicate records, retry chains and consecutive tool failures — and when the evidence is not there it says UNPROVABLE rather than inventing a zero.",
    "take": "Marking what it cannot prove as UNPROVABLE instead of quietly writing zero is what makes the numbers worth trusting.",
    "build": [
      "Written in Python and published on PyPI, so pipx runs it with no repository checkout. There is a demo mode with no personal logs needed, a check command over the last seven days, and a flag to force the Claude Code adapter. All analysis runs locally with no network calls, and the result is a terminal summary plus a local HTML report."
    ],
    "who": [
      {
        "role": "Developers who use Codex or Claude Code daily, and anyone building or maintaining agent tooling.",
        "situation": null
      }
    ],
    "start": [
      {
        "command": false,
        "text": "Run pipx run agentmeasure demo first to see it on a synthetic example."
      }
    ],
    "caveat": [
      "It is built around the log formats Codex and Claude Code write, so sessions from other tools are not covered, and the repository marks its billing/settlement feature (settle) as still a concept."
    ]
  },
  "cta": {
    "type": "install",
    "label": "INSTALL",
    "url": "https://roy-tong.github.io/AgentMeasure"
  },
  "ready": "install",
  "categories": [
    "dev-tools",
    "ai"
  ],
  "categories_confirmed": true,
  "tags": [
    "에이전트 점검",
    "claude code",
    "codex",
    "로컬 분석"
  ],
  "platform": [
    "cli"
  ],
  "license": {
    "spdx": "MIT",
    "scope": "permissive",
    "scope_text": "Use, change and redistribute, commercially too. Keep the notice.",
    "url": "https://spdx.org/licenses/MIT.html",
    "note": null,
    "open_source": true
  },
  "language": "Python",
  "source_urls": {
    "canonical": "https://roy-tong.github.io/AgentMeasure",
    "github": "https://github.com/roy-tong/agentmeasure",
    "huggingface": null,
    "app_store": null,
    "sightings": [
      {
        "source": "showhn",
        "url": "https://github.com/roy-tong/AgentMeasure",
        "posted_at": "2026-09-19T09:16:41.000Z",
        "hn_url": "https://news.ycombinator.com/item?id=49764767"
      }
    ]
  },
  "numbers": {
    "as_of": "2026-09-22T03:00:00.000Z",
    "stars": 216,
    "stars_unit": "GitHub stars",
    "stars_checked_at": "2026-09-19T11:09:18.497Z",
    "stars_observed_since_check": 0,
    "star_delta_24h": null,
    "star_delta_7d": null,
    "star_delta_30d": 3,
    "star_delta_unit": "GitHub stars gained in the window, GH Archive events summed to as_of",
    "spark_14d": [
      null,
      null,
      null,
      null,
      null,
      null,
      null,
      null,
      null,
      null,
      null,
      null,
      null,
      null
    ],
    "hf_likes": null,
    "hf_likes_observed_at": null,
    "hn_points": 2,
    "hn_points_observed_at": "2026-09-22T01:35:29.180Z",
    "store": null,
    "method": "Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours."
  },
  "ranks": null,
  "activity": {
    "pushed_at": "2026-09-19T09:23:55.000Z",
    "owner_type": null,
    "open_issues": null,
    "contributors": null,
    "releases_count": null,
    "latest_release": null,
    "checked_at": null,
    "core_checked_at": "2026-09-19T11:09:18.497Z"
  },
  "signals": [
    {
      "kind": "new",
      "label": "NEW",
      "value": "0h OLD WHEN SEEN"
    }
  ],
  "images": {
    "og": "https://tesign.com/img/agentmeasure-50e9355166.png",
    "cover": "https://tesign.com/img/agentmeasure-50e9355166.png",
    "cover_width": 2400,
    "cover_height": 1260,
    "gallery": [
      "https://tesign.com/img/agentmeasure-50e9355166.png"
    ],
    "alt": "The AgentMeasure landing page: \"The open yardstick for agent metrics\" on the left, and a terminal panel on the right showing checks marked PASS, FAIL and UNPROVABLE.",
    "tier": 1
  },
  "dates": {
    "first_seen_at": "2026-09-19T10:09:19.071Z",
    "source_created_at": "2026-09-19T09:16:41.000Z",
    "discovery_hours": 0.8772419444444445,
    "launch_signal_at": "2026-09-19T09:16:41.000Z",
    "kept_at": "2026-09-22T05:53:16.093Z",
    "first_published_at": "2026-09-22T05:53:16.495Z",
    "updated_at": "2026-09-22T05:53:16.423Z",
    "ingestion_mode": "live"
  },
  "notes": [
    "This file was produced by the same build, from the same data, as the tesign.com item page. The text is editorial; the numbers are stored observations.",
    "null in the JSON means not observed — never zero. The Markdown writes [unconfirmed] for it.",
    "Star total = the value last checked on GitHub (stars_checked_at) + increases observed via GH Archive since. The 24h · 7d · 30d gains are GH Archive hourly events summed to the reference time (as_of). No score of ours.",
    "A summary, not legal advice."
  ]
}