Niches · Agent harnesses

Drive the harness from another program and gate on its result

Four or more companies' docs show a full fit.

8companies, full fit
35companies, fit with a limit
77companies carry the tag
14share of the category's work
8first-hand accounts

What counts as done

Each run exits on its own with a machine-readable result that says whether the task was done and what was denied, and a parent process can tell a failed run from a finished one without reading prose.

How agents ask for it: run the agent on each item in this queue, call the coding agent from my orchestrator, start a session over HTTP and read the result, let my agent hand a task to Codex

Does the job 8

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

ListingWhy
AXLR BB
Underpass AI
--exec --json ends with a result line, exit 3 means a call waits for --decide approve or deny, forbidden calls are marked in tool_calls, and the HTTP, gRPC and MCP service takes Idempotency-Key per turn. source
Droid CLI C
The San Francisco AI Factory, Inc.
-o json returns is_error, num_turns, session_id and usage, an action above the autonomy level stops the run with a stderr error and a non-zero exit, exit codes 0, 1 and 2 are documented, and stream-jsonrpc drives multi-turn sessions. source
MiniMax Code B
Nanonoble Pte. Ltd.
`ExecResult` JSON carries `status` (succeeded, failed, timeout, cancelled, limit_exceeded), exit codes distinguish input, config, task, timeout and limit failures, and a pending permission request fails the run instead of hanging. source
Mistral Vibe CLI B
Mistral AI (RCS Paris 952 418 325)
Exit 0 finished, 1 could not start, 2 model or runtime failure, 3 stopped by a limit or refusal; `--output json|streaming` and `export.json` give outcome, stop reason, tokens and cost. source
OpenAI Agents API BB
OpenAI OpCo, LLC
Sessions and turns carry `status` and `error` with named codes, `agent.session.turn.failed` and `requires_action` tell a parent what happened, and SDKs plus webhooks wrap it. source
OpenHands BB
All Hands AI
`conversation.run()` completes and exits, `set_confirmation_policy` and `reject_pending_actions` control approvals, and `conversation_stats` reports accumulated cost and tokens. source
OpenMausBot B
Supamaus Software Private Limited
`--json` prints one document with the job `state`, exit 3 means someone must answer, and the MCP server's `wait_for_conversation` returns settled, needs-user, failed, stalled or timed-out with a `send_id` for idempotent sends. source
Paperclip C
Paperclip Labs, Inc.
A REST API with `/api/openapi.json`, board and agent tokens, issue status fields, and a CLI whose `--json` prints the raw API payload. source

Does the job, with a limit 37

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
Agent Zero D
Agent Zero, s.r.o.
POST /api_message with X-API-KEY sends a message and api_log_get reads the log, but the docs defer request and response shapes to the source and no done-or-denied field is described. source
Amp C
Amp Frontier Corporation
The final result message has subtype, is_error and num_turns, --stream-json-input drives several turns, and SDKs exist, but nothing is ever denied so there is no denial field, and exit codes are undocumented. source
Antigravity CLI C
Google LLC
json and stream-json end with a result whose status is SUCCESS, ERROR, CANCELED or WAITING and a failed run exits 1, but a denied tool leaves status SUCCESS and exit 0 with only a stderr notice. source
Auggie CLI D
Augment Computing, Inc.
--mode json emits structured events and a TypeScript SDK exists, but exit codes are undocumented and the docs do not say how a denied ask-user call appears in the output. source
Claude Code C
Anthropic, PBC
json and stream-json end with a result carrying is_error, permission_denials and total_cost_usd, and --permission-prompts none denies instead of waiting, but exit 0 and is_error false when the edit was denied (acc-12); .claude writes denied silently (acc-13). source
Clawboo B
Sanreds
A REST API behind an access token starts runs, answers approval cards and lists budgets, but no machine-readable done-or-denied result per run was found in the docs read. source
CLI Manager BB
solhun (Jeong Kyeonghun)
REST and MCP on 127.0.0.1 with a bearer token, HTTP statuses for awaiting_input, disconnected and timedOut, but the outcome is screen text and session state, not a done-or-denied field. source
Cline C
Cline Bot Inc.
--json emits messages as JSON and -P picks a provider, but exit codes are undocumented, nothing is denied in the default yolo mode, and CLI 3.0.70 removed options without notice. source
Cursor CLI E
Anysphere, Inc.
json and stream-json end with a result event, but a rejected action leaves no field in the output, exit codes are undocumented, and print mode hung with no output for over 90 seconds (acc-03). source
DeepSeek Harness (dsh) D
DeepSeek (the LICENSE names DeepSeek, and no legal entity is named in the repository or the docs)
--json opens with a session event and closes with final, exit 0 means completed and 1 aborted or errored, and AUTO_REVIEW_DENIED marks a policy denial, but it is a developer preview whose README warns of breaking changes. 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 Management API with revisions and a status script exist, but tasks arrive through GitHub conversations rather than a program call, and the result is a pull request, not a per-run record. source
Devin C
Cognition AI, Inc.
Sessions have states, devin_session_gather waits for finished, errored, sleeping or waiting, and max_acu_limit bounds each, but creation is not idempotent so a retried timeout doubles the work. source
Pi B
Earendil Inc.
--mode json streams JSONL to agent_settled and RPC mode takes commands on stdin, but a failed response does not set a non-zero exit in JSON mode and nothing is ever denied. source
Gemini CLI B
Google LLC
Exit codes 0, 1, 42 and 53 and a JSON envelope with response, stats and error are documented, but how a tool denied in headless mode appears in the output is not; the TUI, not -p, hung on bare Ubuntu (acc-06). source
GitHub Copilot CLI C
GitHub, Inc.
-p with --output-format json ends in a result record with an exit status even on early failure, but exit codes are not documented as a table and patch releases have removed flags. source
goose BB
Agentic AI Foundation (Linux Foundation)
json and stream-json output and exit codes to check are documented, but no code table exists, a run that ends with a question has not completed, and MCP transports closed under Ollama (acc-18). source
Harness B
Autonomous, Inc.
harness new, wait and show take --json and wait exits 0 idle, 3 needs the person, 4 stopped, 124 timed out and 5 refused, but the person must sign in and turn on Agents can start other agents first, and the result is screen text. source
HarnessRouter D
Lumentree Corporation
POST /{harness_id}/v1/responses with an Idempotency-Key streams SSE events with response and session ids, cancel stops work and budgets are per turn, but closing the stream leaves the agent running and billing, and a person must top up credit first. source
Junie CLI D
JetBrains s.r.o.
json and json-stream output exist, but exit codes are undocumented and what a headless run does when an action needs approval is not stated. 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.)
--format json streams events, exit 0, 1 and 124 are documented, and an auto-rejected request without --auto exits 1 with a stderr cause, but 7.8.13 and 7.8.18 changed permission and MCP behaviour in patch releases. source
Kimi Code CLI C
Moonshot AI (the global Kimi terms name NOVASCENT PRIVATE LIMITED, Singapore)
`-p --output-format stream-json` emits one JSON object a line, plus ACP and a local REST server with OpenAPI, but no final result event with status or cost and no exit code table are documented, and denials cannot occur because print mode auto-approves. source
Kiro CLI B
Amazon Web Services, Inc.
stream-json events and exit codes 0, 1, 3 and 4 are documented, but a denied tool is reported as a `[denied]` text line, not a field, and acc-15 and acc-19 show flags that opened interactive prompts under an orchestrator until 2.0.1. source
Letta B
Letta
JSON result with `usage` and a bidirectional stream-json mode with `can_use_tool` control requests, but no documented exit codes or denial field for non-interactive runs. source
mini-swe-agent B
No legal entity named. The MIT licence names Kilian A. Lieret and Carlos E. Jimenez
It is a Python library with a `-o` trajectory file, so a parent can parse the trajectory, but process exit codes and a denial field are not documented. source
Muse Code C
Meta Platforms, Inc.
`--json` JSONL and exit codes 0, 1, 2, 130 and 143 exist, but a held approval in a headless run stays unresolved rather than failing, and the events carry no cost. source
OpenAI Codex BB
OpenAI OpCo, LLC
`--json` emits `turn.completed` and `turn.failed` with usage, `--output-schema` fixes the final shape, and TypeScript and Python SDKs exist, but exit codes and the `error` payload are undocumented. source
OpenCode BB
Anomaly Innovations, Inc.
`run --format json` gives NDJSON and the server has an OpenAPI spec, but the final event and exit codes are undocumented, and acc-09 and acc-10 are programs failing on the non-interactive and server paths. source
Parallax E
Conifer Solutions, Inc.
`GET $PARALLAX_URL/v1/sweeps` and `/v1/calibration` answer a bearer capture token with JSON, but the base URL is unpublished and there is no OpenAPI or endpoint reference. source
Paseo B
Mohamed Boudra
The `@getpaseo/client` SDK creates agents over WebSocket and the CLI has `--json` and `--output-schema`, but only the usage commands document exit statuses. source
Prime Agent C
Prime Intellect, Inc.
The json mode streams session events and `--mode rpc` and `acp` exist, but exit codes beyond 1 for a failed command and a denial field are not documented. source
Qwen Code BB
Qwen team, Alibaba Group (no legal entity is named in the repository or the docs)
JSON and stream-json output with usage, exit 53 for the turn cap, 55 for a budget, 52 for bad config and 130 for SIGINT, but no documented field says what was denied. source
Mirror CLI C
Reflection AI
`mirror exec` prints plain text with undocumented exit codes; `mirror acp` has a structured protocol, but both need the interactive notice step first. source
Rovo Dev CLI E
Atlassian Pty Ltd
`acli rovodev serve <port>` streams `/v3/stream_chat` as server-sent events and `pause_on_call_tools_start=true` lets a program approve or deny each tool call, but the one-shot `run` has no JSON or exit codes. source
T3 Code C
T3 Tools Inc.
The MCP server lets outside agents start, message, wait on and read threads with a sign-in approval flow, but no result status, denial field or exit code is documented. source
Traycer C
Traycer AI
`--json` writes NDJSON for every CLI command and `host capabilities --has` exits non-zero, but the agent automation commands were not read in detail. source
Vibe-Trading C
HKUDS
`vibe-trading run -p ... --json`, a REST API behind `API_AUTH_KEY` and a stdio MCP server exist, but no exit code table or denial field is documented. source
Warp (Warp Agent CLI and the Oz Agent API) C
Denver Technologies, Inc. (d/b/a Warp)
The platform API returns `run_id` and `state`, error bodies carry `code` and `retryable`, and a TypeScript SDK exists, but what was denied is not reported and a Warp account is required. source

Couldn't check 2

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

ListingWhy
Orca C
Lovecast Inc.
An Orca CLI exists per the README; its output format and exit codes were 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 9

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

ListingWhy
Aider D
Aider AI LLC
The scripting page has --message and a Python API that print text; there is no JSON result, denial field or documented exit code, so a parent must read prose or git. source
Conductor E
Conductor
The beta API at api.conductor.build/v0 creates cloud workspaces and polls session status, and the cloud goes read-only on 13 November 2026 and is deleted on 20 November. source
Crush D
Charmbracelet, Inc.
crush run prints text to stdout with --quiet to hide the spinner; there is no JSON mode, no denial field and no documented exit code, so a parent cannot tell done from failed without reading prose. source
Emdash C
General Action, Inc.
No API or CLI for another program; it is a GUI. source
Harness² E
Google LLC
The CLI accepts only the three benchmarks; a program cannot hand it its own task. 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
Sculptor C
Imbue, Inc.
No API, CLI or MCP server. source
Unstoppable E
Unstoppable Domains, Inc.
No API, MCP server or CLI is documented for outside callers. source
Verdent E
Verdent AI, Inc.
No API, SDK or CLI; the only outside entry is a paired Telegram, Slack or Feishu bot. source

What stops agents finishing

  • print mode hangs with no output and no timeout (acc-03)
  • a consent dialog appears on first run and cannot be answered (acc-15, acc-19)
  • exit 0 and is_error false when the edit was denied (acc-12)
  • patch release breaks the non-interactive path (acc-09)
  • no batch mode for a headless server (acc-10)

Around it

Before: agent-frameworks.plan-task, queues.dequeue. After: agent-harnesses.fix-failing-ci, code-hosting.open-pull-request.

Where this comes from

Weight 14 of 100 in Agent harnesses: 8 of 33 accounts (acc-03, acc-06, acc-09, acc-10, acc-12, acc-13, acc-15, acc-19) are programs calling a harness and failing on its interface

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