Niches · Agent harnesses

Hand a whole task to a hosted agent and collect a pull request

One company's docs show a full fit.

1companies, full fit
10companies, fit with a limit
48companies carry the tag
3share of the category's work
2first-hand accounts

What counts as done

A branch or pull request appears, the plan was shown before execution when asked, and the task count or credit spend is visible afterwards.

Measured, for our own tests: the branch or pull request's checks pass. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: open a PR that bumps these dependencies, fix this issue while I'm away, queue these five tasks

Does the job 1

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Warp (Warp Agent CLI and the Oz Agent API) C
Denver Technologies, Inc. (d/b/a Warp)
Factories route an issue through triage, planning, implementation and review with human decision points and return a pull request to the thread; runs expose `state` and usage is billed to credits. source

Does the job, with a limit 11

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
Amp C
Amp Frontier Corporation
amp -ox runs the prompt in an orb on Amp's servers and returns the thread URL at once, but no plan approval step or pull request output is documented on the pages read. source
Claude Code C
Anthropic, PBC
Cloud routines run without the machine on and start in auto mode, and a label-driven pipeline merged a one-line change, but the cloud sandbox had no database so a UI change shipped unrendered (acc-07). source
Devin C
Cognition AI, Inc.
Sessions clone the repository, work in a VM and open pull requests with a max_acu_limit, but no idempotency key exists on creation and the 24 September 2026 outage took the web app down for two hours. source
GitHub Copilot CLI C
GitHub, Inc.
Cloud sandboxing runs a whole session in a GitHub-hosted ephemeral Linux environment billed by usage, and --connect joins a remote session, but the cloud agent's pull request flow was not read here. source
HarnessRouter D
Lumentree Corporation
A hosted agent runs the task and spend shows per task, but no pull request output or plan approval step is documented. source
Kiro CLI B
Amazon Web Services, Inc.
`--cloud --repo owner/repository` starts a managed cloud session from the headless page, but the cloud sessions page, plan approval and credit visibility were not read. source
Mistral Vibe CLI B
Mistral AI (RCS Paris 952 418 325)
An `&` prefix sends a prompt to a Vibe Code Web cloud session that works on a GitHub repository, but the Web pages were not read and this listing covers the CLI. source
OpenAI Agents API BB
OpenAI OpCo, LLC
OpenAI hosts the agent and sandbox, but no GitHub clone or pull request flow is documented, so an agent would push with its own token; billing is tokens plus container minutes, not task credits. source
OpenAI Codex BB
OpenAI OpCo, LLC
`codex cloud exec` submits a task and `codex cloud list --json` returns `status` per task, but cloud needs a ChatGPT plan rather than an API key and acc-31 found its automatic PR creation less reliable than Jules. source
OpenHands BB
All Hands AI
OpenHands Cloud automations clone with your git login and can open issues or PRs, but the Cloud task pages, plan approval and credit display were not read. source
Parallax E
Conifer Solutions, Inc.
The hosted service opens one fix PR per review with proven patches on GitHub and spends episode credits (5 free, then one per episode), but it reviews work rather than taking a task, and the hosted door has no spend cap. source

Couldn't check 3

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

ListingWhy
Cursor CLI E
Anysphere, Inc.
The listing's bestFor names a hand-off to Cloud Agents, but the cloud agents docs were not opened in this 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.
Unstoppable E
Unstoppable Domains, Inc.
Cloud tasks and MCP tools to wait on them appear in the 1.15.0 changelog with no documentation or pricing.

Doesn't do this job 41

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

ListingWhy
Agent Zero D
Agent Zero, s.r.o.
Self-hosted in Docker; no vendor runner. source
Aider D
Aider AI LLC
Runs locally; no hosted runner. source
Antigravity CLI C
Google LLC
agy runs on the user's machine; no hosted runner that clones a repository and opens a pull request is documented. source
Auggie CLI D
Augment Computing, Inc.
Auggie runs in your CI or terminal; the GitHub Actions wrapper runs on your runners, not a vendor-hosted agent that returns a pull request. source
AXLR BB
Underpass AI
No hosted AXLR exists; the service runs on a machine the operator controls. source
Clawboo B
Sanreds
Self-hosted only; no hosted option is offered. source
CLI Manager BB
solhun (Jeong Kyeonghun)
Local macOS app only. source
Cline C
Cline Bot Inc.
The CLI, extension and hub run on your machines; no vendor-hosted runner returns a pull request. source
Conductor E
Conductor
Conductor Cloud goes read-only on 13 November 2026 and shuts down on 20 November 2026. source
Crush D
Charmbracelet, Inc.
Crush runs locally; no hosted runner. source
DeepSeek Harness (dsh) D
DeepSeek (the LICENSE names DeepSeek, and no legal entity is named in the repository or the docs)
Runs locally; no hosted runner. source
dsh-superagent (DeepSeek) E
DeepSeek (the LICENSE names the DeepSeek Harness Team; DeepSeek Harness's terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)
Self-hosted on the operator's machine; no vendor runner. source
Droid CLI C
The San Francisco AI Factory, Inc.
The CLI runs on your machine; no hosted runner that returns a pull request was found in the pages read. source
Pi B
Earendil Inc.
Runs locally; Radius is a model gateway, not a runner. source
Emdash C
General Action, Inc.
Local and SSH machines only; no vendor runner. source
Gemini CLI B
Google LLC
Runs locally; no hosted runner. source
goose BB
Agentic AI Foundation (Linux Foundation)
Runs locally or on your own server; no vendor runner. source
Harness B
Autonomous, Inc.
Runs on the person's own computers. source
Harness² E
Google LLC
No hosted service. source
Jules D
Google LLC
Jules showed a plan, published a branch and left the PR to the author with five tasks a day (acc-31), but sessions are read-only after 11 November 2026 and the service ends on 31 December. source
Junie CLI D
JetBrains s.r.o.
Runs locally; no hosted runner. 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.)
Runs locally; the Kilo Gateway routes models, not tasks. source
Kimi Code CLI C
Moonshot AI (the global Kimi terms name NOVASCENT PRIVATE LIMITED, Singapore)
No hosted runner; the CLI runs on the user's machine or a declared remote environment. source
Letta B
Letta
`--computer cloud` runs a prompt in a Letta sandbox, but no repository or pull request flow is documented. source
mini-swe-agent B
No legal entity named. The MIT licence names Kilian A. Lieret and Carlos E. Jimenez
No hosted runner; Modal and Docker environments are for batch evaluation, not a pull request service. source
MiniMax Code B
Nanonoble Pte. Ltd.
No hosted runner for the CLI. source
Muse Code C
Meta Platforms, Inc.
No hosted runner. source
OpenCode BB
Anomaly Innovations, Inc.
No hosted runner; Zen and Go are model subscriptions. source
OpenMausBot B
Supamaus Software Private Limited
MausBot Cloud hosts a workspace, but no pull request flow is documented. source
Orca C
Lovecast Inc.
Cloud VMs host worktrees you control; no pull request service is described. source
Paperclip C
Paperclip Labs, Inc.
Paperclip Cloud is a waitlist with no published service. source
Paseo B
Mohamed Boudra
Agents run on your own machines; no hosted service. source
Prime Agent C
Prime Intellect, Inc.
No hosted runner. source
Qwen Code BB
Qwen team, Alibaba Group (no legal entity is named in the repository or the docs)
No hosted runner. source
Mirror CLI C
Reflection AI
No hosted runner. source
Rovo Dev CLI E
Atlassian Pty Ltd
No hosted task runner; Bitbucket Pipelines integration runs in your CI. source
Sculptor C
Imbue, Inc.
The container backend is experimental and self-managed; no hosted PR service. source
T3 Code C
T3 Tools Inc.
Agents run on your machines. source
Traycer C
Traycer AI
Agents run on your hosts; Traycer inference is only the model. source
Verdent E
Verdent AI, Inc.
Verdent Cloud builds web apps in the browser; no repository task delegate is documented. source
Vibe-Trading C
HKUDS
Self-hosted only. source

What stops agents finishing

  • Jules turns read-only after 11 November 2026
  • no idempotency on session creation so a retry doubles the work
  • daily task caps on free tiers (acc-31)
  • no database in the sandbox so UI changes cannot be rendered (acc-07)

Around it

Before: issue-tracking.read-issue. After: code-hosting.review-pr.

Where this comes from

Weight 3 of 100 in Agent harnesses: 2 of 33 accounts (acc-07, acc-31); Devin and Codex cloud produced only vendor numbers

The same as data: /api/v1/use-cases/agent-harnesses.cloud-delegate.json, or the MCP tool get_use_case with id agent-harnesses.cloud-delegate. 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.