Niches · Agent harnesses

Pair-program interactively in a terminal with approvals

Four or more companies' docs show a full fit.

13companies, full fit
25companies, fit with a limit
101companies carry the tag
15share of the category's work
8first-hand accounts

What counts as done

The requested change is applied and reviewable as a diff, each risky command was shown before it ran, and the session ends when the person says so.

How agents ask for it: add a priority field to tasks, refactor this module, find the bug in auth.py, explain this codebase

Does the job 14

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

ListingWhy
Antigravity CLI C
Google LLC
The Default preset asks before sensitive operations outside the terminal sandbox, which is on by default with no network, and Deny beats Ask beats Allow rules. source
Crush D
Charmbracelet, Inc.
By default Crush asks for permission before running tool calls, and permissions allow lists which tools may skip the prompt. source
Gemini CLI B
Google LLC
general.defaultApprovalMode defaults to default, which prompts for approval; YOLO can only be turned on from the command line and security.disableYoloMode can forbid it. source
GitHub Copilot CLI C
GitHub, Inc.
Tools prompt for permission unless listed with --allow-tool or --allow-all-tools, deny rules still apply, and the local sandbox can be turned on with /sandbox enable. source
Junie CLI D
JetBrains s.r.o.
The action allowlist runs matching commands automatically and asks for the rest, including each part of a chained or nested command, and Brave Mode is opt-in. source
Kimi Code CLI C
Moonshot AI (the global Kimi terms name NOVASCENT PRIVATE LIMITED, Singapore)
Default `manual` permission mode asks before tool calls, the dangerous-command guard covers risky shell, `.env` and git control paths, and `--yolo` or `--auto` relax it only when asked for. source
Kiro CLI B
Amazon Web Services, Inc.
Most tools default to `ask`, `permissions.yaml` rules use deny > ask > allow, and shell commands are parsed per sub-command before matching. source
mini-swe-agent B
No legal entity named. The MIT licence names Kilian A. Lieret and Carlos E. Jimenez
`confirm` mode is the default: the model proposes one bash action and the person confirms or rejects each one. source
MiniMax Code B
Nanonoble Pte. Ltd.
TUI modes Ask, Auto and Full access; Auto classifies routine actions and asks when risk is high, Ask confirms every tool action. source
Mistral Vibe CLI B
Mistral AI (RCS Paris 952 418 325)
Default `accept-edits` agent auto-approves edits and asks for shell and other sensitive tools; `ask` asks for everything, and calls outside the working directory prompt. source
Muse Code C
Meta Platforms, Inc.
Approval and an OS sandbox are on by default; the Auto-review profile lets a judge clear eligible requests and falls back to asking, and dangerous shell patterns always stop for review. source
Mirror CLI C
Reflection AI
Approval mode defaults to `approve` (manual), remembered approvals live in `tool_approvals.json`, and `/worktree` and `/sandbox` isolate work. source
Rovo Dev CLI E
Atlassian Pty Ltd
Most tools default to `ask` with Once, Session or Always choices, bash commands get per-command permissions, and worktree mode keeps edits out of the checkout. source
Warp (Warp Agent CLI and the Oz Agent API) C
Denver Technologies, Inc. (d/b/a Warp)
The CLI shows inline request cards for commands and edits, with profile allowlists and denylists, though `--auto-approve` bypasses the denylist unless a setting is changed. source

Does the job, with a limit 25

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
Edits land as reviewable git commits and shell commands are suggested for confirmation, but users want tool calling and find it a poor fit without git knowledge (acc-33), and it is unmaintained. source
Auggie CLI D
Augment Computing, Inc.
Allow, deny, ask-user and webhook rules exist with deny winning, but what the CLI does with an unmatched tool is undefined and the MCP page says Auggie runs commands and tools automatically. source
AXLR BB
Underpass AI
The console shows approval cards, but after setup approvals.autonomous is on and exec_sandbox off, so commands run with the person's rights unless the settings are changed first. source
Claude Code C
Anthropic, PBC
Since 2.1.283 interactive sessions start in auto mode, where a classifier rather than the person reviews most actions; the Bash sandbox is off by default, and skip-permissions mode deleted a home directory (acc-14). source
CLI Manager BB
solhun (Jeong Kyeonghun)
It hosts Claude Code, Codex and Gemini CLI terminals side by side with worktree workspaces, but approvals and diffs belong to the child harness. source
Cline C
Cline Bot Inc.
A prompt runs in yolo mode by default; pass --auto-approve false or --act to get act mode, which asks before tools; in ACP mode the default is already false. source
Conductor E
Conductor
Each task gets a workspace, branch, terminal and diff for Claude Code, Codex, Cursor or OpenCode, but no new downloads since 4 November 2026 and the local app winds down in early 2027. source
Cursor CLI E
Anysphere, Inc.
Shell(...), Read and Write permission tokens in cli.json allow or deny actions and --sandbox toggles a sandbox, but the docs do not state what runs without approval by default in an interactive session. source
Droid CLI C
The San Francisco AI Factory, Inc.
Autonomy Off, Low, Medium and High gate what runs without asking and command rules can block, but the sandbox is off until sandbox.enabled is set and included usage is stated only as rolling limits without numbers. source
Emdash C
General Action, Inc.
Each task runs a CLI agent in its own worktree with a diff to review and a pull request button, but approvals and sandboxes are the child agent's. source
goose BB
Agentic AI Foundation (Linux Foundation)
Manual and Smart Approval modes exist, but Autonomous mode, which approves everything, is the default. source
Harness B
Autonomous, Inc.
Every agent runs in a real tmux pane the person can read and type into, across machines, but approvals and diffs are the child harness's. 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.)
Allow, ask and deny rules per tool exist and unmatched checks default to ask, but most tools ship with "*": "allow", so only exceptions such as .env reads prompt out of the box. source
Letta B
Letta
The interactive CLI starts in `unrestricted`, auto-allowing tools; the person must switch to `standard` or `strict` before risky commands are shown. source
OpenAI Codex BB
OpenAI OpCo, LLC
The Auto preset edits and runs in the workspace and asks outside it, with `/permissions` and worktrees, but acc-22 found Codex edits through scripts unreviewable as they happen and acc-26 ran out of Plus quota mid-task. source
OpenCode BB
Anomaly Innovations, Inc.
The default policy is `allow` for every action except `.env` reads, so nothing is shown before it runs until the user adds `ask` rules. source
Orca C
Lovecast Inc.
Orca hosts Claude Code, Codex and any CLI agent in chat or raw terminal; approvals belong to the agent below, and the README is the only source read. source
Paseo B
Mohamed Boudra
The app and `paseo attach` stream an agent and plugins answer permissions, but approval behaviour is the harness's and was not documented in the pages read. source
Prime Agent C
Prime Intellect, Inc.
The TUI executes model-written Python and shell with the user's rights and asks nothing first, so risky commands are not shown before they run. source
Qwen Code BB
Qwen team, Alibaba Group (no legal entity is named in the repository or the docs)
The default is Auto, where an LLM classifier approves safe actions, so a person sees only what the classifier escalates; acc-25 ran it on a local model successfully. source
Sculptor C
Imbue, Inc.
The person prompts in the app and reviews diffs, but Claude Code runs sandboxed with tool permissions auto-approved, so commands are not shown before they run. source
T3 Code C
T3 Tools Inc.
Pairing happens in the desktop, web or phone app with Supervised, Auto-accept edits, Auto and Full access modes, but the initial default is Full access. source
Traycer C
Traycer AI
A desktop app, not a terminal; new conversations default to Full access and Auto mode's judge is experimental. source
Unstoppable E
Unstoppable Domains, Inc.
A desktop IDE rather than a terminal; every chat starts in Full access until the person picks Ask or Accept edits, though deny rules still apply. source
Verdent E
Verdent AI, Inc.
A desktop app, not a terminal; Agent Mode is the default and some actions prompt for approval, but which ones is not listed. source

Couldn't check 2

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

ListingWhy
Parallax E
Conifer Solutions, Inc.
The macOS app that runs Claude Code and Codex side by side has no documentation; only the review service pages were 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 15

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

ListingWhy
Agent Zero D
Agent Zero, s.r.o.
A web UI, not a terminal, and Tool Access defaults to allow with no approval before shell commands. source
Amp C
Amp Frontier Corporation
The tools page says Amp does not ask for approval before running tools and that control needs a custom policy plugin, so risky commands are not shown before they run. source
Clawboo B
Sanreds
Clawboo is a web dashboard and board, not a terminal, and its coding runtimes start with their own permission prompts turned off. source
DeepSeek Harness (dsh) D
DeepSeek (the LICENSE names DeepSeek, and no legal entity is named in the repository or the docs)
dsh's interactive surface is a local web app or an ACP editor session, not a terminal UI. source
dsh-superagent (DeepSeek) E
DeepSeek (the LICENSE names the DeepSeek Harness Team; DeepSeek Harness's terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)
A daemon that answers issues and pull requests; no terminal pairing. source
Devin C
Cognition AI, Inc.
Devin works in its own cloud VM; the terminal products are separate and not graded here. source
Pi B
Earendil Inc.
The security page says Pi does not ask for approval before every tool call and has no permission system, so a risky command is not shown before it runs. source
Harness² E
Google LLC
Not interactive; executors run with approvals and sandbox bypassed on benchmark tasks. source
HarnessRouter D
Lumentree Corporation
A server-side API; no terminal session. source
Jules D
Google LLC
A cloud agent with a CLI dashboard, not a terminal pair programmer, and read-only since 11 November 2026. source
OpenAI Agents API BB
OpenAI OpCo, LLC
It is a hosted API; there is no terminal client or interactive approval loop. source
OpenHands BB
All Hands AI
The CLI is no longer maintained; the interactive surface is a web UI, and acc-23 saw it edit README without asking in build mode. source
OpenMausBot B
Supamaus Software Private Limited
It is a chat app with approval cards, not a terminal pairing session. source
Paperclip C
Paperclip Labs, Inc.
It is a web control plane; the terminal belongs to the harness it drives. source
Vibe-Trading C
HKUDS
Not a coding harness; the bash tool and generated backtests run without per-action approval. source

What stops agents finishing

  • weekly subscription limits stop work mid-task (acc-26, acc-21)
  • skip-permissions mode plus a bad shell command deletes files outside the repository (acc-14)
  • edits made through scripts cannot be reviewed as they happen (acc-22)

Around it

Before: code-hosting.clone. After: code-hosting.commit, agent-harnesses.fix-failing-ci.

Where this comes from

Weight 15 of 100 in Agent harnesses: 8 of 33 accounts (acc-20, acc-21, acc-22, acc-26, acc-27, acc-32, acc-33, acc-14) are about daily interactive use or its failures

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