Niches · Agent harnesses

Build or port a whole feature from a spec in an unattended loop

No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.

0companies, full fit
39companies, fit with a limit
77companies carry the tag
12share of the category's work
4first-hand accounts

What counts as done

Every 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.

Measured, for our own tests: every story in the spec has a passing test. No docs we read state these figures, so they don't count against a listing here.

How 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

Does the job, with a limit 41

It 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.

ListingWhy
Aider D
Aider AI LLC
A shell loop over --message works and each edit is a commit, but nothing caps turns or spend. source
Amp C
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. source
Antigravity CLI C
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. source
Auggie CLI D
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. source
AXLR BB
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. source
Claude Code C
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. source
Clawboo B
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. source
Cline C
Cline Bot Inc.
--worktree and --retries help a loop, but no turn or spend cap and no cost field were found. source
Crush D
Charmbracelet, Inc.
A loop can wrap crush run, but nothing caps turns or spend and no cost figure comes back per run. source
Cursor CLI E
Anysphere, Inc.
A loop can use agent -p --force, but no turn or spend cap exists and the result carries duration, not cost. source
DeepSeek Harness (dsh) D
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. source
Devin C
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. source
Droid CLI C
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. source
Pi B
Earendil Inc.
Sessions and --mode json support a loop wrapper, but nothing caps turns or spend. source
Gemini CLI B
Google LLC
maxSessionTurns and exit 53 bound a loop, but no spend cap exists and stats are tokens only. source
GitHub Copilot CLI C
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. source
goose BB
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. source
HarnessRouter D
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. source
Junie CLI D
JetBrains s.r.o.
--max-steps bounds each task, but no spend cap or cost output exists. source
Kilo Code CLI BB
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. source
Kimi Code CLI C
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. source
Kiro CLI B
Amazon Web Services, Inc.
No turn cap, spend cap, cost output or worktree flag; a loop wrapper gets exit codes only. source
Letta B
Letta
No turn cap, spend cap or worktree; token usage is reported but no cost. source
mini-swe-agent B
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. source
MiniMax Code B
Nanonoble Pte. Ltd.
Step and time caps exist, but no dollar budget, token usage only, and no worktree flag. source
Mistral Vibe CLI B
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. source
Muse Code C
Meta Platforms, Inc.
`--max-model-steps` caps work and isolated subagents get worktrees, but no dollar budget and no cost output. source
OpenAI Agents API BB
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. source
OpenAI Codex BB
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. source
OpenCode BB
Anomaly Innovations, Inc.
No turn or spend cap; worktree placement is configurable but there is no cost output to stay under a budget. source
OpenHands BB
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. source
OpenMausBot B
Supamaus Software Private Limited
`--timeout`, `--strict` and job trees bound a run, but there is no spend cap or cost output. source
Paperclip C
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. source
Paseo B
Mohamed Boudra
No turn or spend cap; usage limits are visible per account but not enforced. source
Prime Agent C
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. source
Qwen Code BB
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. source
Mirror CLI C
Reflection AI
`--max-iterations` and worktrees exist, but no budget, cost output or built-in loop. source
Rovo Dev CLI E
Atlassian Pty Ltd
Worktrees and permissions exist, but no turn or spend cap and no cost output. source
Traycer C
Traycer AI
Usage limits are read from providers and routed around, but nothing caps turns or spend. source
Verdent E
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. source
Warp (Warp Agent CLI and the Oz Agent API) C
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. source

Couldn't check 2

The docs were closed to us, or silent. These carry no mark either way.

ListingWhy
Orca C
Lovecast Inc.
No caps or cost reporting seen; docs not read.
Qoder CLI C
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.

Doesn't do this job 13

Listings in the category that do something else, with the reason.

ListingWhy
Agent Zero D
Agent Zero, s.r.o.
Not aimed at unattended repository builds; tasks and goals are chat-scoped. source
CLI Manager BB
solhun (Jeong Kyeonghun)
No loop, budget or completion handling; it starts and watches sessions. source
Conductor E
Conductor
No loop or budget functions; the app orchestrates sessions a person reviews. source
dsh-superagent (DeepSeek) E
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. source
Emdash C
General Action, Inc.
No loop, budget or completion handling. source
Harness B
Autonomous, Inc.
No loop, budget or completion handling. source
Harness² E
Google LLC
Refines a harness over benchmark tasks with --k steps; not a spec-to-build loop. source
Jules D
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. source
Parallax E
Conifer Solutions, Inc.
Not a build loop; it reviews sessions other harnesses ran. source
Sculptor C
Imbue, Inc.
Interactive only; no caps or unattended loop. source
T3 Code C
T3 Tools Inc.
No turn or spend caps and no built-in loop. source
Unstoppable E
Unstoppable Domains, Inc.
No caps or unattended loop documented. source
Vibe-Trading C
HKUDS
Not a build loop. source

What stops agents finishing

  • two Max 20x subscriptions exhausted in days (acc-28)
  • a day of Hermes cost $300 (acc-08)
  • no clear endpoint so the loop stops early or never (acc-28)
  • critic sub-agent misses invalid output the sandbox cannot render (acc-07)

Around it

Before: planning.write-spec. After: agent-harnesses.fix-failing-ci, code-hosting.open-pull-request.

Where this comes from

Weight 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

The same as data: /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. Other jobs in this category: /api/v1/niches?category=agent-harnesses.

Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.