{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/agent-harnesses.spec-to-build-loop/",
    "json": "https://www.anchorterminal.com/niches/agent-harnesses.spec-to-build-loop/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/agent-harnesses.spec-to-build-loop/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/agent-harnesses.spec-to-build-loop/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 39 | 77 | 12 | 4 |\n\n## What counts as done\n\nEvery story in the spec has a commit, the loop stopped on its own at the completion marker or iteration cap, and total spend stayed under the stated budget.\n\nMeasured, for our own tests: every story in the spec has a passing test.\n\nHow agents ask for it: work through prd.json until every story passes; port this Python tool to Go; build the app from the spec overnight; keep going until the tests pass\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Aider (Aider AI LLC)**: A shell loop over --message works and each edit is a commit, but nothing caps turns or spend.\n- **Amp (Amp Frontier Corporation)**: A loop can wrap amp -x and read is_error, but no turn, time or cost cap exists and usage is reported in tokens only; background subagents keep running after the process exits.\n- **Antigravity CLI (Google LLC)**: A loop can drive agy -p and read status, but no turn cap or spend cap exists, only --print-timeout, and usage is tokens without cost.\n- **Auggie CLI (Augment Computing, Inc.)**: Print mode and --show-cost give a scriptable loop with cost in logs, but no turn or spend cap exists in the 1.x reference.\n- **AXLR (Underpass AI)**: Per-execution budgets in usd, seconds and tool_calls and max_session_usd bound spend, but no built-in loop or completion marker exists and the project is pre-1.0.\n- **Claude Code (Anthropic, PBC)**: A bash loop over claude -p built two apps in a weekend (acc-28) and --max-turns and --max-budget-usd bound each run, but the budget counts estimated spend (acc-16) and the loop exhausted two Max 20x subscriptions.\n- **Clawboo (Sanreds)**: Per-task worktrees, verification and hard-cap USD budgets fit a long build, but there is no completion-marker loop and the runtimes run unattended with permissions bypassed.\n- **Cline (Cline Bot Inc.)**: --worktree and --retries help a loop, but no turn or spend cap and no cost field were found.\n- **Crush (Charmbracelet, Inc.)**: A loop can wrap crush run, but nothing caps turns or spend and no cost figure comes back per run.\n- **Cursor CLI (Anysphere, Inc.)**: A loop can use agent -p --force, but no turn or spend cap exists and the result carries duration, not cost.\n- **DeepSeek Harness (dsh) (DeepSeek (the LICENSE names DeepSeek, and no legal entity is named in the repository or the docs))**: Resume with --session-id and a documented supervisor workflow exist, but no turn or spend cap and no cost field were found.\n- **Devin (Cognition AI, Inc.)**: Playbooks and max_acu_limit per session bound a long task, but there is no loop with a completion marker and spend is in ACUs without a published rate.\n- **Droid CLI (The San Francisco AI Factory, Inc.)**: --worktree and --fork help a loop, but no flag caps turns or spend, and rolling rate limits are unstated.\n- **Pi (Earendil Inc.)**: Sessions and --mode json support a loop wrapper, but nothing caps turns or spend.\n- **Gemini CLI (Google LLC)**: maxSessionTurns and exit 53 bound a loop, but no spend cap exists and stats are tokens only.\n- **GitHub Copilot CLI (GitHub, Inc.)**: --autopilot keeps working until task_complete and /goal --max-ai-credits caps credits, but the credit cap is interactive only and -p has no turn cap.\n- **goose (Agentic AI Foundation (Linux Foundation))**: GOOSE_MAX_TURNS and GOOSE_SUBAGENT_MAX_TURNS cap turns including subagents, but no spend cap or cost output exists.\n- **HarnessRouter (Lumentree Corporation)**: Per-turn defaults of 400 steps, 7200 seconds and 10 USD bound each turn and sessions continue, but no loop or completion marker exists and disabled_tools is only an instruction on some bases.\n- **Junie CLI (JetBrains s.r.o.)**: --max-steps bounds each task, but no spend cap or cost output exists.\n- **Kilo Code CLI (Kilo Code Inc. (the terms are a contract with Anaconda, Inc. on behalf of itself and its affiliates, including Kilo Code Inc.))**: --worktree and sessions help, but no turn, time or cost cap exists for kilo run.\n- **Kimi Code CLI (Moonshot AI (the global Kimi terms name NOVASCENT PRIVATE LIMITED, Singapore))**: A step cap exists per turn, but no dollar budget, no cost output and no worktree support; the loop itself needs an outside wrapper.\n- **Kiro CLI (Amazon Web Services, Inc.)**: No turn cap, spend cap, cost output or worktree flag; a loop wrapper gets exit codes only.\n- **Letta (Letta)**: No turn cap, spend cap or worktree; token usage is reported but no cost.\n- **mini-swe-agent (No legal entity named. The MIT licence names Kilian A. Lieret and Carlos E. Jimenez)**: Cost and step limits exist, but no worktree, no built-in loop, and the limits are LiteLLM estimates.\n- **MiniMax Code (Nanonoble Pte. Ltd.)**: Step and time caps exist, but no dollar budget, token usage only, and no worktree flag.\n- **Mistral Vibe CLI (Mistral AI (RCS Paris 952 418 325))**: `--max-turns`, `--max-tokens`, `--time-limit` and `--worktree` are there, but the docs say not to rely on `--max-price` for hard budget enforcement.\n- **Muse Code (Meta Platforms, Inc.)**: `--max-model-steps` caps work and isolated subagents get worktrees, but no dollar budget and no cost output.\n- **OpenAI Agents API (OpenAI OpCo, LLC)**: OpenAI runs the loop with subagents and a session budget code, but hosted sandboxes expire after an hour idle and no per-turn cost is shown.\n- **OpenAI Codex (OpenAI OpCo, LLC)**: `--worktree` and `exec resume` support a loop, but there is no turn or spend cap and acc-26 needed about six interventions and hit quota over a month of porting work.\n- **OpenCode (Anomaly Innovations, Inc.)**: No turn or spend cap; worktree placement is configurable but there is no cost output to stay under a budget.\n- **OpenHands (All Hands AI)**: Iterative refinement and a stuck detector are guides, and costs are tracked, but no per-run spend cap exists in the SDK pages read.\n- **OpenMausBot (Supamaus Software Private Limited)**: `--timeout`, `--strict` and job trees bound a run, but there is no spend cap or cost output.\n- **Paperclip (Paperclip Labs, Inc.)**: Heartbeats, `maxTurnsPerRun` and budget hard stops bound the work, but the docs say enforcement uses recorded spend so in-flight work can delay a stop.\n- **Paseo (Mohamed Boudra)**: No turn or spend cap; usage limits are visible per account but not enforced.\n- **Prime Agent (Prime Intellect, Inc.)**: `/autonomous` continues within turn, token and time budgets with quality gates, but the README says reaching a limit does not imply success and there is no spend cap in dollars.\n- **Qwen Code (Qwen team, Alibaba Group (no legal entity is named in the repository or the docs))**: Three run budgets exist, but `--max-tool-calls` does not count a subagent's inner calls and there is no dollar budget or cost output.\n- **Mirror CLI (Reflection AI)**: `--max-iterations` and worktrees exist, but no budget, cost output or built-in loop.\n- **Rovo Dev CLI (Atlassian Pty Ltd)**: Worktrees and permissions exist, but no turn or spend cap and no cost output.\n- **Traycer (Traycer AI)**: Usage limits are read from providers and routed around, but nothing caps turns or spend.\n- **Verdent (Verdent AI, Inc.)**: Manager plans and dispatches Worker tasks, including to Claude Code or Codex through BYOA, but no caps, cost output or completion marker are documented.\n- **Warp (Warp Agent CLI and the Oz Agent API) (Denver Technologies, Inc. (d/b/a Warp))**: Cloud runs and budgets bound spend at the platform level, but no turn cap or per-run cost was found.\n\n## Couldn't check\n\nThe docs were closed to us, or silent. These carry no mark either way.\n\n- **Orca (Lovecast Inc.)**: No caps or cost reporting seen; docs not read.\n- **Qoder CLI (BRIGHT ZENITH PRIVATE LIMITED)**: docs.qoder.com answered 502 from the fetch proxy on three attempts and a DNS failure through WebFetch, so no page was read.\n\n- not this job: Agent Zero (Agent Zero, s.r.o.): Not aimed at unattended repository builds; tasks and goals are chat-scoped.\n- not this job: CLI Manager (solhun (Jeong Kyeonghun)): No loop, budget or completion handling; it starts and watches sessions.\n- not this job: Conductor (Conductor): No loop or budget functions; the app orchestrates sessions a person reviews.\n- not this job: dsh-superagent (DeepSeek) (DeepSeek (the LICENSE names the DeepSeek Harness Team; DeepSeek Harness's terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)): One Ticket per request with a 30-minute background limit; not built to work through a spec until done.\n- not this job: Emdash (General Action, Inc.): No loop, budget or completion handling.\n- not this job: Harness (Autonomous, Inc.): No loop, budget or completion handling.\n- not this job: Harness² (Google LLC): Refines a harness over benchmark tasks with --k steps; not a spec-to-build loop.\n- not this job: Jules (Google LLC): Sessions turned read-only after 11 November 2026 and the service ends on 31 December 2026, per the changelog, so no new work can finish.\n- not this job: Parallax (Conifer Solutions, Inc.): Not a build loop; it reviews sessions other harnesses ran.\n- not this job: Sculptor (Imbue, Inc.): Interactive only; no caps or unattended loop.\n- not this job: T3 Code (T3 Tools Inc.): No turn or spend caps and no built-in loop.\n- not this job: Unstoppable (Unstoppable Domains, Inc.): No caps or unattended loop documented.\n- not this job: Vibe-Trading (HKUDS): Not a build loop.\n\n## What stops agents finishing\n\n- two Max 20x subscriptions exhausted in days (acc-28)\n- a day of Hermes cost $300 (acc-08)\n- no clear endpoint so the loop stops early or never (acc-28)\n- critic sub-agent misses invalid output the sandbox cannot render (acc-07)\n\n## Around it\n\nBefore: planning.write-spec. After: agent-harnesses.fix-failing-ci, code-hosting.open-pull-request.\n\n## Where this comes from\n\nWeight 12 of 100 in Agent harnesses: 4 of 33 accounts (acc-07, acc-08, acc-26, acc-28); the Ralph loop is the most written-about pattern of early 2026 but most posts are guides, not runs\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/agent-harnesses.spec-to-build-loop.json, or the MCP tool get_use_case with id agent-harnesses.spec-to-build-loop. Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Build or port a whole feature from a spec in an unattended loop",
        "url": ""
      }
    ],
    "description": "Build or port a whole feature from a spec in an unattended loop: 0 companies fully do it, 39 with a limit, 77 carry the tag. Every listing in Agent harnesses with the reason and a source.",
    "facts": null,
    "h1": "Build or port a whole feature from a spec in an unattended loop",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/agent-harnesses.spec-to-build-loop/",
    "published": "",
    "section": "agents",
    "title": "Build or port a whole feature from a spec in an unattended loop |…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/agent-harnesses.spec-to-build-loop/"
  },
  "tokens": {
    "markdown": 2800,
    "slim": 730
  },
  "version": 1
}
