{ "data": { "a": { "slug": "harnessrouter", "name": "HarnessRouter", "vendor": "HarnessRouter (Lumentree Corporation)", "vendorUrl": "https://harnessrouter.ai", "kind": "harness", "category": "agent-harnesses", "summary": "HarnessRouter runs complete agent harnesses such as Codex, Claude Code and Hermes behind one HTTP API, the Unified Harness Protocol, with sessions, streaming, files and artifacts. It comes as a hosted cloud or a self-hosted Community Edition.", "url": "https://www.anchorterminal.com/tools/harnessrouter", "markdownUrl": "https://www.anchorterminal.com/tools/harnessrouter.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/harnessrouter.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/harnessrouter.json", "dns": "harnessrouter.grade.anchorterminal.com", "repo": "https://github.com/HarnessRouter/harnessrouter", "license": "Apache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides.", "transports": [ "http" ], "remoteUrl": "https://api.harnessrouter.ai", "packages": [ { "registry": "oci", "name": "harnessrouter/harnessrouter" } ], "auth": "api-key", "authNotes": "A Workspace API key (sk-hr-) as a Bearer token from the product's server, never from a browser (https://harnessrouter.ai/docs/authentication). Keys are created in the console after a browser sign-up, can be held to one workspace or reach the whole organisation, and are revoked at once by DELETE /v1/orgs/{org}/keys/{id}. No OAuth or per-endpoint scopes found. The self-hosted Community Edition signs into its console with a username and password and needs no HarnessRouter key.", "pricing": "usage", "pricingNotes": "Free plan at $0 with no card, for the console and configuring agents, with 2 tasks at a time during its 7-day trial. Running tasks draws on top-up credit ($10 minimum, 5.5 per cent fee, minimum $0.80) or a plan, Developer $20, Production $200 or Scale $1,000 a month, each fully included as usage. Agent work is $0.020 an active minute on top-ups and $0.014 to $0.006 on plans, and model calls are at the provider's price or on your own keys (https://harnessrouter.ai/pricing.md, checked 2026-11-04). Self-serve payment is card-only.", "priceSummary": "$20 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in llms.txt, llms-full.txt, the pricing page or the UHP schema (checked 2026-10-17). Payment is by card for top-ups and plans.", "endpoints": [] }, "toolCount": 0, "popularity": { "githubStars": 4069, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-04" }, "docsUrl": "https://harnessrouter.ai/docs", "llmsTxt": "https://harnessrouter.ai/llms.txt", "openapi": "https://github.com/HarnessRouter/harnessrouter/blob/main/protocol/schema/uhp-2026-10-04.openapi.yaml", "capabilities": [ "agent.harness", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "hosted", "self-hosted", "open-source", "apache-2.0", "api-key", "usage", "openapi", "llms-txt", "docker", "python", "streaming", "cloud-agent", "agent-skill" ], "lastRelease": "2026-11-03", "graded": true, "anchor": { "graded": true, "score": 47.7, "grade": "D", "agentReady": false, "rank": 1028, "ranked": true, "rankOf": 1354, "categoryRank": 39, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 72, "payments": 25, "reliability": 35, "schema": 83, "security": 60, "transparency": 73 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -11, "negativeNotes": [ "2026-10-06, -5. Privately reported flaws fixed in public commits #416 to #429 on 6 and 7 October 2026. The gateway source names them GHSA-p6cq-54cg-8mpv (a bearer token that failed verification still reached internal routes, so anyone could rewrite any organisation's connections and routing; \"found live on the hosted service and closed there the same way, 2026-10-06\"), GHSA-qrr8-m92f-7vfp (identity headers trusted by default), GHSA-mw9j-m5jf-5r56 and GHSA-c5g7-c47h-f6c3 (server-side request forgery through git imports and upload addresses) and GHSA-rmh9-whjx-gfrc (secrets with quotes or non-ASCII characters left unredacted). A workspace key could also read, change and delete another workspace's harnesses, sessions and responses and mint an organisation-wide key (\"reported privately three times\"). All were fixed within days and described in the source. The advisory pages couldn't be read (GitHub answered 403), so whether they're published is unchecked, and the deduction is lower than an open cross-tenant flaw would get. Source https://github.com/HarnessRouter/harnessrouter/blob/main/gateway/app.py", "2026-10-10, -3. Since 10 October 2026 harness writes carrying a field the harness doesn't have, or a `default_model` its base doesn't run, are refused with 422 (`model_not_available` for the model), where they were accepted with 200 before. UHP's own versioning rules reserve such a tightening for a new version. The first notice was the known-compromises entry added to the versioning page in the same commit on 10 October, the day the hosted service made the change, and the changelog followed on 19 October (same-day term; it applies to the hosted service, so the 0.x reading doesn't reach it). Source https://github.com/HarnessRouter/harnessrouter/blob/main/protocol/VERSIONING.md", "2026-11-03, -3. Release v0.37.16 (3 November) fixes a flaw its commit describes with no advisory identifier. A relay route kept a connection's key usable after its turn ended, even after the operator removed the connection (\"200 on the turn's route after the turn had ended\"). The v0.37.15 fixes of 2 November (credentials and instance secrets readable by agent turns, the published default console password accepted) cite GHSA-m479 and GHSA-r37g in the source, and other v0.37.16 and v0.37.17 fixes cite GHSA-3vf8, GHSA-fx92, GHSA-gf7m-w8pf-6f68, GHSA-mm72-wr37-26pv and GHSA-mx6c-8c42-fw44, so they aren't counted here. None of those advisories could be read (GitHub answered 403). Source https://github.com/HarnessRouter/harnessrouter/commit/430358a" ], "verdict": "A product's server sends a task to a named harness and gets streamed progress, sessions and files back, under a published OpenAPI contract with idempotency keys and a closed set of error codes. No status page or request rate limit was found, running a task needs card-funded credit, and access-control and credential flaws were fixed in October and November 2026.", "bestFor": "A product team that wants to run Codex, Claude Code, Hermes or 27 other harnesses server-side behind one task, session and file contract, and switch between them by changing an ID.", "strengths": [ "UHP is published as OpenAPI 3.1 and JSON Schema 2020-12 under Apache-2.0, with a 101-check conformance suite in the repository", "Every task call takes an Idempotency-Key, and the error envelope has a closed code set, with a retry rule per code", "Per-turn budgets (400 steps, 7,200 seconds and $10 by default) cap what one task can spend", "30 harnesses listed as available, including Codex, Claude Code, Hermes, OpenCode, goose and Qoder, behind one task contract", "245 tagged releases between 15 August and 3 November 2026, and the self-hosted Community Edition runs with no HarnessRouter account" ], "weaknesses": [ "No status page found (status.harnessrouter.ai has no DNS record), and the terms give no service level without a signed Order Form", "No request rate limit is published. Only concurrency (2 tasks at a time in the Free trial) and task length (30 minutes, or 1 hour after a top-up) are stated", "Running a task on the hosted service draws on credit, and top-ups and plans are card-only, so an agent can't start without a person", "Access-control, SSRF and redaction flaws were fixed on 6 and 7 October 2026, and credential exposure to agent turns on 2 and 3 November, with no advisory readable", "Harness writes with unknown fields began failing with 422 on 10 October 2026, announced only that day in the versioning page and on 19 October in the changelog" ], "agentNotes": [ "Name the harness yourself. The task call is POST /{harness_id}/v1/responses, and HarnessRouter doesn't choose a harness for you", "Send a fresh Idempotency-Key with each new task, reuse it only for a retry of the same request, and recover from the session if a stream drops", "Call cancel to stop work. Closing the SSE connection leaves the agent running and billing", "Keep the Workspace API key on the server. The docs forbid calling the API from a browser with it", "Check each tool's enforcement in GET /v1/bases. On bases marked instruction, disabled_tools is a request to the model, not a block" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 47.7 } ], "editorialScores": { "ergonomics": 73, "maintenance": 72, "payments": 25, "reliability": 35, "schema": 83, "security": 60, "transparency": 79 }, "provenanceScore": 67, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "docker run -d --name harnessrouter -p 127.0.0.1:3000:3000 -v harnessrouter:/data harnessrouter/harnessrouter", "http": "curl -N https://api.harnessrouter.ai/$HARNESS_ID/v1/responses -H \"Authorization: Bearer $HR_API_KEY\" -H \"Idempotency-Key: $(uuidgen)\" -H \"Content-Type: application/json\" -d '{\"input\": \"Review this uploaded agreement and return a checklist.\", \"stream\": true}'" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/harnessrouter" }, "area": "frameworks", "unitPrices": [ { "item": "Developer plan, all $20 as usage", "unit": "month", "usd": 20, "note": "agent work $0.014 an active minute, one workspace" }, { "item": "Production plan, all $200 as usage", "unit": "month", "usd": 200, "note": "agent work $0.010 an active minute, five workspaces" }, { "item": "Scale plan, all $1,000 as usage", "unit": "month", "usd": 1000, "note": "agent work $0.006 an active minute, tracing included" }, { "item": "Agent work on top-up credit, per hour of active work", "unit": "session-hour", "usd": 1.2, "note": "$0.020 an active minute, billed by the second. Waiting on the model, the user or a queue isn't billed" }, { "item": "Tracing add-on", "unit": "month", "usd": 50, "note": "beta, included with Scale" } ], "provenance": { "legalEntity": "Lumentree Corporation", "domain": "harnessrouter.ai", "domainRegistered": "2026-06-18", "endpointOnVendorDomain": true, "terms": "https://harnessrouter.ai/legal/terms", "privacy": "https://harnessrouter.ai/legal/privacy", "statusPage": "", "changelog": "https://unifiedharnessprotocol.org/changelog", "securityTxt": "none", "checked": "2026-11-04", "notes": [ "The terms (v1.1, 31 July 2026) name Lumentree Corporation, a California corporation, as the contracting party, and the disclosure policy names the same company. The YC launch lists the company as Epsilla (Summer 2023), per the 17 October check.", "harnessrouter.ai was registered on 18 June 2026 and unifiedharnessprotocol.org on 12 August 2026, from the registry RDAP readings of 17 October 2026 (not re-read; RDAP is a JSON service).", "No status page. status.harnessrouter.ai has no DNS record (4 November 2026) and no other status page was found.", "harnessrouter.ai/.well-known/security.txt answered 404 on 17 October 2026 (not re-read). A disclosure policy is at /legal/security, and SECURITY.md in the repository names GitHub private reporting and contact@harnessrouter.ai.", "The changelog is the UHP specification's (protocol/CHANGELOG.md in the repository). HarnessRouter itself has 245 tags in the repository and no product changelog page was found.", "The terms (§4.4(c)) forbid scraping or crawling except as allowed by the documentation, an API endpoint, robots.txt or written permission. robots.txt on harnessrouter.ai names ClaudeBot, Claude-User and Claude-SearchBot and allows all paths, and unifiedharnessprotocol.org allows all paths (4 November 2026)." ], "score": 67 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/harnessrouter.json", "live": { "slug": "harnessrouter", "probe": { "target": "https://api.harnessrouter.ai", "method": "get", "lastAt": "2026-11-06T09:47:31.11594914Z", "lastOk": true, "lastStatus": 404, "lastMs": 281, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 276, "p95ms24h": 361, "samples24h": 221, "samples30d": 4819, "days": [ { "date": "2026-10-17", "probes": 21, "ok": 21 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 102, "ok": 102 } ] }, "versions": [ { "registry": "github", "name": "HarnessRouter/harnessrouter", "version": "v0.38.2", "released": "2026-11-04", "seenAt": "2026-11-05T21:36:22.821590841Z" } ], "githubStars": 4222, "securityTxt": { "url": "https://harnessrouter.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-05T15:55:30.844244682Z" }, "llmsTxt": { "url": "https://harnessrouter.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-05T15:26:14.404319285Z" }, "domain": { "domain": "harnessrouter.ai", "registered": "2026-06-18", "source": "https://rdap.identitydigital.services/rdap/domain/harnessrouter.ai", "checkedAt": "2026-11-01T14:17:32.25734582Z" }, "pages": [ { "url": "https://unifiedharnessprotocol.org/changelog", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-05T13:07:17.1144076Z", "changedAt": "2026-11-04T08:35:29.196603298Z", "fingerprint": "df248ace8f95" }, { "url": "https://harnessrouter.ai/pricing.md", "kind": "pricing", "status": 200, "checkedAt": "2026-11-05T12:56:19.003867087Z", "changedAt": "2026-10-18T23:31:33.798956939Z", "fingerprint": "b31b753df12b" }, { "url": "https://harnessrouter.ai/legal/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-05T12:56:14.976756246Z", "changedAt": "2026-11-03T07:51:05.619736871Z", "fingerprint": "3de312eb4d16" }, { "url": "https://harnessrouter.ai/legal/terms", "kind": "terms", "status": 304, "checkedAt": "2026-11-05T12:56:17.016927682Z", "changedAt": "2026-11-03T07:51:07.897150705Z", "fingerprint": "d25dce7ee92b" } ], "github": { "repo": "harnessrouter/harnessrouter", "checkedAt": "2026-11-02T08:53:53.843359717Z", "stars": 3860, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T02:10:02Z", "openIssues": 16, "openPRs": 5, "issuesOpened90d": 85, "issuesClosed90d": 69, "prsMerged90d": 479, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-11-01T10:11:08Z" }, "advisories": [ { "ghsa": "GHSA-59mq-hx4p-fw48", "severity": "medium", "published": "2026-10-08T04:42:01Z" }, { "ghsa": "GHSA-c5g7-c47h-f6c3", "severity": "medium", "published": "2026-10-08T01:58:14Z" }, { "ghsa": "GHSA-qrr8-m92f-7vfp", "severity": "high", "published": "2026-10-07T19:55:26Z" }, { "ghsa": "GHSA-mw9j-m5jf-5r56", "severity": "high", "published": "2026-10-07T19:24:34Z" }, { "ghsa": "GHSA-7pwj-vv9r-rh2m", "severity": "medium", "published": "2026-10-07T07:13:59Z" }, { "ghsa": "GHSA-rmh9-whjx-gfrc", "severity": "medium", "published": "2026-10-07T07:13:58Z" }, { "ghsa": "GHSA-4386-3vpq-3xhx", "severity": "high", "published": "2026-10-06T21:59:22Z" }, { "ghsa": "GHSA-p6cq-54cg-8mpv", "severity": "critical", "published": "2026-10-06T21:59:21Z" }, { "ghsa": "GHSA-cgf4-38c9-39vr", "severity": "high", "published": "2026-10-06T21:32:58Z" }, { "ghsa": "GHSA-9pjr-97x3-c4wv", "severity": "high", "published": "2026-10-06T21:32:57Z" }, { "ghsa": "GHSA-5hfm-crcm-5vh7", "severity": "high", "published": "2026-10-06T20:00:17Z" } ], "replies": { "sampled": 25, "unanswered": 6, "medianDays": 0.9 } }, "updatedAt": "2026-11-06T09:47:31.11594914Z" } }, "answer": "OpenAI Agents API scores 73.3 (BB) on agent readiness against HarnessRouter's 47.7 (D), and leads in every scored category.", "b": { "slug": "openai-agents-api", "name": "OpenAI Agents API", "vendor": "OpenAI", "vendorUrl": "https://openai.com/index/introducing-the-agents-api/", "kind": "http-api", "category": "agent-harnesses", "summary": "The OpenAI Agents API runs OpenAI's managed Codex harness as a hosted service. One call creates a session with a model, tools, MCP servers, subagents and an OpenAI-hosted or self-hosted sandbox, and OpenAI runs the loop.", "url": "https://www.anchorterminal.com/tools/openai-agents-api", "markdownUrl": "https://www.anchorterminal.com/tools/openai-agents-api.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/openai-agents-api.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/openai-agents-api.json", "dns": "openai-agents-api.grade.anchorterminal.com", "license": "Proprietary hosted API under OpenAI's Services Agreement. The SDKs are Apache 2.0", "transports": [ "https" ], "remoteUrl": "https://api.openai.com/v1/agents/sessions", "packages": [ { "registry": "pypi", "name": "openai" }, { "registry": "npm", "name": "openai" } ], "auth": "api-key", "authNotes": "An OpenAI project API key as a Bearer token, with the header `OpenAI-Beta: agents=v1`. Project keys can be restricted per endpoint or read-only, and service accounts and workload identity federation are available, per the openai-api listing. Signing up and creating a key need a person in a browser.", "pricing": "usage", "pricingNotes": "No fee for the API itself. Model tokens are billed at the chosen model's API rates, OpenAI tools at their built-in rates (web search $10.00 per 1,000 calls plus content tokens), and OpenAI-hosted sandboxes at container rates, $0.03 for 1 GB, $0.12 for 4 GB, $0.48 for 16 GB and $1.92 for 64 GB per 20-minute session, billed by the minute with a 5-minute minimum. Since 9 October sandbox compute is billed only during active turns (checked 2026-11-06).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Agents API guides or on OpenAI's pricing page; billing is to an OpenAI account (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://developers.openai.com/api/docs/guides/agents-api/overview", "llmsTxt": "https://developers.openai.com/api/docs/llms.txt", "capabilities": [ "agent.harness" ], "tags": [ "official", "hosted", "beta", "usage-priced", "llms-txt", "status-page", "mcp-client", "sandbox", "subagents", "webhooks", "soc2", "iso27001", "bug-bounty" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 73.3, "grade": "BB", "agentReady": true, "rank": 99, "ranked": true, "rankOf": 1354, "categoryRank": 2, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 87, "payments": 30, "reliability": 60, "schema": 88, "security": 87, "transparency": 85 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "OpenAI's hosted agent runtime, the Codex harness behind one session call, with MCP, functions, web search, computer use, subagents and sandboxes on OpenAI or your own infrastructure. Documentation, errors and SDKs are thorough. It's still public beta, can't use Zero Data Retention and keeps data in the United States only.", "bestFor": "Teams that want OpenAI to run the agent loop, with sandboxes, MCP tools and subagents, and are fine with a beta API, US-only data residency and no Zero Data Retention.", "strengths": [ "One session call configures the model, tools, MCP servers, subagents and the sandbox, and OpenAI runs and recovers the loop", "Sandboxes on OpenAI or self-hosted, with guides for ten providers including E2B, Daytona, Modal, Cloudflare and Vercel", "An errors guide with codes per status and turn, Retry-After and a check-before-retry procedure", "Webhooks, streamed events, tracing and usage views for each session", "SDK examples in Python, JavaScript, Go, Java and Ruby", "Status page with its own Agents component" ], "weaknesses": [ "Public beta since 10 September 2026 behind the agents=v1 beta header, with no GA date", "Not eligible for Zero Data Retention, and data residency is United States only", "No idempotency key for session or turn requests; retries depend on checking state first", "One API-wide major outage on 29 September included it, plus several smaller incidents since release", "No retention period stated for published artifacts after a sandbox expires" ], "agentNotes": [ "POST https://api.openai.com/v1/agents/sessions with a project key and the header OpenAI-Beta: agents=v1, or use client.beta.agents in the SDKs", "Before retrying, retrieve the session and turn and check which actions completed, since there's no idempotency key", "Set the sandbox network to restricted with an allowlist of up to 100 hosts when the agent doesn't need the open web", "Save files from /workspace/outputs before deleting a session; no retention period is stated for artifacts", "Don't send data that needs Zero Data Retention or non-US residency; the Agents API supports neither" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 73.3 } ], "editorialScores": { "ergonomics": 80, "maintenance": 87, "payments": 30, "reliability": 60, "schema": 88, "security": 87, "transparency": 75 }, "provenanceScore": 95, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl https://api.openai.com/v1/agents/sessions \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -H \"OpenAI-Beta: agents=v1\" \\\n -H \"Content-Type: application/json\" \\\n -d @session.json # model, tools, environment and input, per the quickstart" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/openai-agents-api" }, "sameCompany": [ "openai-api", "openai-embeddings", "openai-guardrails", "openai-moderation", "openai-image-api", "openai-sora", "openai-speech-to-text", "gpt-live", "openai-realtime", "openai-agents-sdk", "openai-decisions-api", "openai-codex", "gpt-oss-120b", "gpt-oss-20b" ], "area": "frameworks", "provenance": { "legalEntity": "OpenAI OpCo, LLC", "domain": "openai.com", "domainRegistered": "2007-01-19", "domainNote": "openai.com was registered in 2007, before OpenAI existed, per the openai-api listing.", "endpointOnVendorDomain": true, "terms": "https://openai.com/policies/services-agreement/", "privacy": "https://openai.com/policies/privacy-policy/", "statusPage": "https://status.openai.com", "changelog": "https://developers.openai.com/api/docs/changelog", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "The endpoint is on api.openai.com, the same host as the rest of the OpenAI API. Terms, privacy, security.txt and the domain are the openai-api listing's readings." ], "score": 95 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/openai-agents-api.json", "live": { "slug": "openai-agents-api", "probe": { "target": "https://api.openai.com/v1/agents/sessions", "method": "get", "lastAt": "2026-11-06T09:47:41.371658489Z", "lastOk": true, "lastStatus": 400, "lastMs": 162, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 148, "p95ms24h": 166, "samples24h": 47, "samples30d": 47, "days": [ { "date": "2026-11-06", "probes": 47, "ok": 47 } ] }, "vendorStatus": { "page": "https://status.openai.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-06T09:43:26.425829944Z" }, "updatedAt": "2026-11-06T09:47:41.371658489Z" } }, "edges": [ { "by": 27, "category": "security", "leads": "openai-agents-api", "name": "Security \u0026 auth", "reasons": { "a": "Hosted reading. Bearer Workspace API keys, revocable at once through the API, held to one workspace or reaching the organisation, with harness-bound calibration credentials. No OAuth, per-endpoint scopes or expiry found (20 of 30). Least privilege 10 of 20. disabled_tools per configured agent, enforced by the runtime only where GET /v1/bases says hard, and per-turn cost and step caps, with no approval step for actions a harness takes. Prompt injection 10 of 15. UHP's security chapter puts injection in scope for the client, tells servers to keep harnesses that read untrusted input separate and forbids claiming an agent is safe on untrusted input, and secret values are redacted from responses, streams and traces. Operator visibility 10 of 15. A cost breakdown per task on every plan, and the step-by-step trace is beta, included in Scale or $50 a month. Security programme 10 of 20 (was 8). A disclosure policy (v1.0, effective 30 July 2026) with safe harbour and no bounty, SECURITY.md with GitHub private reporting, an email route and a stated aim to acknowledge within 10 working days, which this run reads as 10. GHSA identifiers are cited in public fix commits; no security.txt and no SOC 2 or ISO 27001 found. 20 + 10 + 10 + 10 + 10 = 60.", "b": "Project keys with restricted per-endpoint permissions, service accounts and workload identity, per the openai-api listing; we didn't confirm a key can be limited to /v1/agents (27 of 30). Automatic review for approvals, a sandbox network restricted to a host allowlist, vaults for secrets and a sandbox security guide (17 of 20). The agent reads web pages, MCP results and browser content; the sandbox security guide and approval flow are the mitigations, with no prompt-injection guide of its own found (8 of 15). Tracing, observability and usage per session and admin audit logs (15). SOC 2 Type 2, ISO 27001 family, Bugcrowd bounty and a disclosure policy, per the openai-api listing (20). Not ZDR-eligible and US residency only, recorded under transparency. 27 + 17 + 8 + 15 + 20 = 87." }, "scores": { "a": 60, "b": 87 } }, { "by": 25, "category": "reliability", "leads": "openai-agents-api", "name": "Reliability", "reasons": { "a": "Hosted reading, for HarnessRouter Cloud at api.harnessrouter.ai, as on 17 October. No status page (status.harnessrouter.ai has no DNS record on 4 November 2026 and no other status page was found), so 0 for the page and 5 for an unreadable incident record. No request rate limit with numbers was found. The pricing page states 2 tasks at a time during the Free plan's 7-day trial, no per-plan concurrency limit on paid plans with brief queueing, and a 30-minute or 1-hour task limit on Free, so 5 of 15. 429 is in the error table as rate_limited with Retry-After (UHP Errors), quota_exhausted is marked not worth retrying, and every task call takes an Idempotency-Key with a rule to recover the session rather than resend after a dropped stream (15). Terms §5.4 still give no service level outside a signed Order Form (0). The task API isn't labelled beta, while tracing and agent memory are (10). 0 + 5 + 5 + 15 + 0 + 10 = 35.", "b": "Read as a hosted API. status.openai.com has an Agents component under APIs (20). Since release on 10 September (57 days, not 90), the feed names the Agents API in a degraded-performance incident on 14 September, the elevated errors across ChatGPT, Codex and the API on 29 September (the openai-api listing reads that one as a major, 17:52 to 23:14 UTC), computer use issues and degraded workspace agents on 6 and 7 October, degraded performance across the APIs for 22 minutes on 21 October, and overbilling for hosted containers on 19 September. One major, the rest minor (10). Rate limits come from the shared guide, published per tier and model with headers, and the errors page adds a Files API allowance on session creation (15). 429 and 503 guidance with Retry-After, capped backoff and a check-then-retry procedure for turns (15). The Scale Tier SLA in the openai-api listing isn't shown to cover a beta API (0). Public beta behind the agents=v1 header (0). 20 + 10 + 15 + 15 + 0 + 0 = 60." }, "scores": { "a": 35, "b": 60 } }, { "by": 15, "category": "maintenance", "leads": "openai-agents-api", "name": "Maintenance \u0026 community", "reasons": { "a": "Open-source reading of the repository behind the hosted service. Last tag v0.38.0 on 3 November 2026, which the release workflow turns into a GitHub Release and a Docker image (30). 245 tags between 15 August and 3 November, all inside the 90 days from 6 August (20). GitHub's issue pages and API refused this session, so open issues and reply times are unchecked. Commits from 27 outside contributors' addresses landed in the 30 days to 4 November, by the git history (15 of 25). No official SDK and no MCP server to register (0). A tests workflow runs every suite on each pull request and push to main, with a release workflow and a Docker image, but whether the default branch passes is unchecked (7 of 10). 30 + 20 + 15 + 0 + 7 = 72.", "b": "Closed API. Last dated change 16 October 2026, Ultrafast mode and document skills (30). Four dated changelog entries in the 57 days since release, 10 September, 29 September, 9 October and 16 October (20). Changelog and help centre, as the openai-api listing reads them (12 of 15). Official SDKs carry beta.agents (15). SDK CI, per the openai-api listing (10). 30 + 20 + 12 + 15 + 10 = 87." }, "scores": { "a": 72, "b": 87 } }, { "by": 12, "category": "transparency", "leads": "openai-agents-api", "name": "Transparency \u0026 trust", "reasons": { "a": "Editorial half. The server, specification, schema and conformance suite are Apache-2.0. The Cloud's own billing and deployment wasn't confirmed to match the open code, and the Agent Skill has a custom licence for some guides (25 of 30). The privacy policy, DPA, subprocessor list and a retention page agree. Customer content isn't used for training without an opt-in, and periods are stated (tasks deleted at once, agents and files after 30 days, backups within 14 days, credentials within 90, free-plan task records 7 days). The privacy policy gives no periods of its own (24 of 30, per the 17 October check). Deprecation 15 of 20 (was 14). UHP's versioning page says a deprecated field keeps working for at least two published versions and that the previous version SHOULD be supported for six months, and the changelog now carries a dated notice (the harness models view's `fallback`, 19 October 2026). The rule is counted in versions, not time, so dated notices give 15. Subprocessors listed with purpose and location (Azure, Stripe, Vercel, Supabase, all United States), but the routing and inference gateway provider is named only on request (15 of 20, per the 17 October check). 25 + 24 + 15 + 15 = 79. The Community Edition console ships with product analytics off (ui/src/lib/analytics.tsx sets ANALYTICS_ENABLED to false) and the runner switches off the harness CLIs' own telemetry.", "b": "Closed service with clear terms, Apache-2.0 SDKs (15). Session state retained until deleted, deletable sessions and artifacts, not ZDR-eligible, US residency only, and the data-controls guide agrees; no retention period for artifacts after a sandbox expires (25 of 30). Dated deprecation notices with minimum periods for GA models; a beta API can change faster (15 of 20). Subprocessors and processing countries listed, per the openai-api listing (20). 15 + 25 + 15 + 20 = 75." }, "scores": { "a": 73, "b": 85 } }, { "by": 7, "category": "ergonomics", "leads": "openai-agents-api", "name": "Agent ergonomics", "reasons": { "a": "API reading. Sessions, turns and files are separate reads, and list endpoints take limit and cursor, but there's no field selection on a response (15 of 25). Cursor paging on session and memory lists with a bounded limit, and few filters found (14 of 20). One error envelope with type, code, param and detail, a closed code set, a retry rule per code and a 422 that lists every failed field without echoing the body (18 of 20). Idempotency-Key on task creation, reuse only for the same request, recover from the session after a drop, and an explicit cancel because closing the stream doesn't stop work (18 of 20). Only input is required to run a task, and budgets default to 400 steps, 7,200 seconds and $10. No official SDK, only the OpenAI Responses shape, clients generated from the OpenAPI file and an Agent Skill (8 of 15). 73 in all.", "b": "Read as an API an agent drives. Context is compacted automatically, and session budgets and streamed events keep output sized (20 of 25). Sessions can be listed, continued and steered, events streamed or sent by webhook, artifacts fetched (15 of 20). Actionable error codes with recovery steps (20). No idempotency key; a documented check-then-retry procedure (10 of 20). One session call with defaults (medium sandbox, network enabled), SDKs in five languages (15). 20 + 15 + 20 + 10 + 15 = 80." }, "scores": { "a": 73, "b": 80 } }, { "by": 5, "category": "schema", "leads": "openai-agents-api", "name": "Schema \u0026 documentation", "reasons": { "a": "API reading. UHP's OpenAPI 3.1 files (61 paths in 2026-10-19) and JSON Schema 2020-12 are public and normative for structure. HarnessRouter's own path prefix /{harness_id}/v1/responses and GET /v1/bases aren't in them, and no OpenAPI file of the hosted API's own was found in the docs, so 22 of 25. llms.txt, llms-full.txt, agents.md, docs.md, pricing.md and harnesses.md (10). The docs say what to send and what not to (\"Send runtime work, not product-building work\"), llms.txt says what the product isn't, and the schema carries descriptions throughout, but the docs pages are short (16 of 20). Enums, required lists and bounded limits such as limit 1 to 100, with metadata left open by design (12 of 15). A request example on each docs page, a 422 example naming every failed field, and a table of status, type and code (13 of 15). Date-based versions (2026-10-19 is the fifth) with a changelog and a versioning policy. Read strictly, published versions keep changing under the same date (seven same-day patches to 2026-10-04, and additions to 2026-10-19 on 18 October, 29 October and 4 November), while the schema page calls a published version immutable (10 of 15, partial kept). The conformance page and the suite's README now agree on 101 checks. 22 + 10 + 16 + 12 + 13 + 10 = 83.", "b": "The reference is linked from the overview and the SDKs carry beta.agents types; we didn't confirm /agents/sessions in OpenAI's public OpenAPI file, so 15 of 25. llms.txt with every Agents API page and Markdown twins (10). The overview, architecture page and the agents guide that compares the Agents API, Agents SDK and Responses API say when to use it (20). Typed configuration with enumerated container sizes, network modes and environment types (13 of 15). Examples in six languages and an errors page with codes per HTTP status, turn and session (15). Dated changelog entries and a versioned beta header (15). 15 + 10 + 20 + 13 + 15 + 15 = 88." }, "scores": { "a": 83, "b": 88 } } ], "facts": [ { "a": "Agent harness", "b": "HTTP API", "name": "Kind" }, { "a": "HarnessRouter (Lumentree Corporation)", "b": "OpenAI", "name": "Vendor" }, { "a": "https://api.harnessrouter.ai", "b": "https://api.openai.com/v1/agents/sessions", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "https", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides.", "b": "Proprietary hosted API under OpenAI's Services Agreement. The SDKs are Apache 2.0", "name": "Licence" }, { "a": "0", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-03", "b": "2026-10-16", "name": "Last release" }, { "a": "no date given", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "2026-07-30", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "yes", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "4.1k stars", "b": "none", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "OpenAI Agents API scores 73.3 (BB) on agent readiness against HarnessRouter's 47.7 (D), and leads in every scored category.", "question": "Which is better for AI agents, HarnessRouter or OpenAI Agents API?" }, { "answer": "Yes. HarnessRouter has a hosted endpoint at https://api.harnessrouter.ai and OpenAI Agents API at https://api.openai.com/v1/agents/sessions.", "question": "Can an agent call HarnessRouter and OpenAI Agents API without installing anything?" }, { "answer": "HarnessRouter is open source (Apache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides.). No open-source release is listed for OpenAI Agents API.", "question": "Are HarnessRouter and OpenAI Agents API open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "Open source" ], "goodFor": "A product team that wants to run Codex, Claude Code, Hermes or 27 other harnesses server-side behind one task, session and file contract, and switch between them by changing an ID.", "slug": "harnessrouter", "watchFor": "No status page found (status.harnessrouter.ai has no DNS record), and the terms give no service level without a signed Order Form" }, { "aheadOn": [ "Reliability, 60 against 35", "Schema \u0026 documentation, 88 against 83", "Agent ergonomics, 80 against 73", "Security \u0026 auth, 87 against 60", "Payments \u0026 pricing, 30 against 25", "Maintenance \u0026 community, 87 against 72", "Transparency \u0026 trust, 85 against 73" ], "also": [ "Agent-ready, a grade of BB or better", "No incidents deducted, where HarnessRouter loses 11 points for them" ], "goodFor": "Teams that want OpenAI to run the agent loop, with sandboxes, MCP tools and subagents, and are fine with a beta API, US-only data residency and no Zero Data Retention.", "slug": "openai-agents-api", "watchFor": "Public beta since 10 September 2026 behind the agents=v1 beta header, with no GA date" } ], "history": { "harnessrouter": [ { "causes": [ "correction", "event" ], "date": "2026-11-04", "delta": -5.6, "from": 53.3, "fromGrade": "D", "to": 47.7, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.1, "from": 53.4, "fromGrade": "D", "to": 53.3, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 53.2, "fromGrade": "D", "to": 53.4, "toGrade": "D" } ], "openai-agents-api": null }, "job": { "capability": "agent.harness", "name": "Agent harnesses" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-harnessrouter.json", "title": "Agent Zero vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/agent-zero-vs-openai-agents-api.json", "title": "Agent Zero vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-harnessrouter.json", "title": "Aider vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/aider-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/aider-vs-openai-agents-api.json", "title": "Aider vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/aider-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-harnessrouter.json", "title": "Amp vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/amp-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/amp-vs-openai-agents-api.json", "title": "Amp vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/amp-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harnessrouter.json", "title": "Antigravity CLI vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openai-agents-api.json", "title": "Antigravity CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-harnessrouter.json", "title": "Auggie CLI vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/auggie-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/auggie-vs-openai-agents-api.json", "title": "Auggie CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/auggie-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-harnessrouter.json", "title": "AXLR vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/axlr-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/axlr-vs-openai-agents-api.json", "title": "AXLR vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/axlr-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-harnessrouter.json", "title": "Claude Code vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/claude-code-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/claude-code-vs-openai-agents-api.json", "title": "Claude Code vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/claude-code-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-harnessrouter.json", "title": "Cline vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/cline-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/cline-vs-openai-agents-api.json", "title": "Cline vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/cline-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-harnessrouter.json", "title": "Crush vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/crush-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/crush-vs-openai-agents-api.json", "title": "Crush vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/crush-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-harnessrouter.json", "title": "Cursor CLI vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/cursor-cli-vs-openai-agents-api.json", "title": "Cursor CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harnessrouter.json", "title": "DeepSeek Harness (dsh) vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-agents-api.json", "title": "DeepSeek Harness (dsh) vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harnessrouter.json", "title": "dsh-superagent (DeepSeek) vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openai-agents-api.json", "title": "dsh-superagent (DeepSeek) vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-harnessrouter.json", "title": "Devin vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/devin-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/devin-vs-openai-agents-api.json", "title": "Devin vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/devin-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-harnessrouter.json", "title": "Droid CLI vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/droid-cli-vs-openai-agents-api.json", "title": "Droid CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-harnessrouter.json", "title": "Pi vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-agents-api.json", "title": "Pi vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-harnessrouter.json", "title": "Gemini CLI vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-agents-api.json", "title": "Gemini CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harnessrouter.json", "title": "GitHub Copilot CLI vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-openai-agents-api.json", "title": "GitHub Copilot CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-harnessrouter.json", "title": "goose vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/goose-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/goose-vs-openai-agents-api.json", "title": "goose vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/goose-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.json", "title": "Harness² vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/harness2-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api.json", "title": "Harness² vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-jules.json", "title": "HarnessRouter vs Jules", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-jules" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-junie.json", "title": "HarnessRouter vs Junie CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-junie" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-kilo-code-cli.json", "title": "HarnessRouter vs Kilo Code CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-kilo-code-cli" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-kimi-code-cli.json", "title": "HarnessRouter vs Kimi Code CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-kimi-code-cli" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-kiro-cli.json", "title": "HarnessRouter vs Kiro CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-kiro-cli" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-mini-swe-agent.json", "title": "HarnessRouter vs mini-swe-agent", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-mini-swe-agent" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-minimax-code.json", "title": "HarnessRouter vs MiniMax Code", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-minimax-code" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-mistral-vibe-cli.json", "title": "HarnessRouter vs Mistral Vibe CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-mistral-vibe-cli" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-muse-code.json", "title": "HarnessRouter vs Muse Code", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-muse-code" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-codex.json", "title": "HarnessRouter vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-opencode.json", "title": "HarnessRouter vs OpenCode", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-openhands.json", "title": "HarnessRouter vs OpenHands", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-openmausbot.json", "title": "HarnessRouter vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-prime-agent.json", "title": "HarnessRouter vs Prime Agent", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-qoder-cli.json", "title": "HarnessRouter vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-qwen-code.json", "title": "HarnessRouter vs Qwen Code", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-reflection-mirror.json", "title": "HarnessRouter vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-rovo-dev-cli.json", "title": "HarnessRouter vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-unstoppable.json", "title": "HarnessRouter vs Unstoppable", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-vibe-trading.json", "title": "HarnessRouter vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-warp.json", "title": "HarnessRouter vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/jules-vs-openai-agents-api.json", "title": "Jules vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/jules-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/junie-vs-openai-agents-api.json", "title": "Junie CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/junie-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-agents-api.json", "title": "Kilo Code CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-openai-agents-api.json", "title": "Kimi Code CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-openai-agents-api.json", "title": "Kiro CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-openai-agents-api.json", "title": "mini-swe-agent vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/minimax-code-vs-openai-agents-api.json", "title": "MiniMax Code vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/minimax-code-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-agents-api.json", "title": "Mistral Vibe CLI vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/muse-code-vs-openai-agents-api.json", "title": "Muse Code vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/muse-code-vs-openai-agents-api" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openai-codex.json", "title": "OpenAI Agents API vs OpenAI Codex", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openai-codex" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-opencode.json", "title": "OpenAI Agents API vs OpenCode", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-opencode" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openhands.json", "title": "OpenAI Agents API vs OpenHands", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openhands" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openmausbot.json", "title": "OpenAI Agents API vs OpenMausBot", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-openmausbot" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-prime-agent.json", "title": "OpenAI Agents API vs Prime Agent", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-prime-agent" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-qoder-cli.json", "title": "OpenAI Agents API vs Qoder CLI", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-qoder-cli" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-qwen-code.json", "title": "OpenAI Agents API vs Qwen Code", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-qwen-code" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-reflection-mirror.json", "title": "OpenAI Agents API vs Mirror CLI", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-reflection-mirror" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-rovo-dev-cli.json", "title": "OpenAI Agents API vs Rovo Dev CLI", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-rovo-dev-cli" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-unstoppable.json", "title": "OpenAI Agents API vs Unstoppable", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-vibe-trading.json", "title": "OpenAI Agents API vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-warp.json", "title": "OpenAI Agents API vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-warp" }, { "json": "https://www.anchorterminal.com/compare/clawboo-vs-harnessrouter.json", "title": "Clawboo vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/clawboo-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/cli-manager-vs-harnessrouter.json", "title": "CLI Manager vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/harness-autonomous-vs-harnessrouter.json", "title": "Harness vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-paperclip.json", "title": "HarnessRouter vs Paperclip", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-paperclip" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-parallax-agents.json", "title": "HarnessRouter vs Parallax", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-parallax-agents" } ], "panel": null, "scores": [ { "by": 25, "edge": "openai-agents-api", "harnessrouter": 35, "key": "reliability", "name": "Reliability", "openai-agents-api": 60, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 5, "edge": "openai-agents-api", "harnessrouter": 83, "key": "schema", "name": "Schema \u0026 documentation", "openai-agents-api": 88, "weight": 13 }, { "by": 7, "edge": "openai-agents-api", "harnessrouter": 73, "key": "ergonomics", "name": "Agent ergonomics", "openai-agents-api": 80, "weight": 13 }, { "by": 27, "edge": "openai-agents-api", "harnessrouter": 60, "key": "security", "name": "Security \u0026 auth", "openai-agents-api": 87, "weight": 14 }, { "by": 5, "edge": "openai-agents-api", "harnessrouter": 25, "key": "payments", "name": "Payments \u0026 pricing", "openai-agents-api": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 15, "edge": "openai-agents-api", "harnessrouter": 72, "key": "maintenance", "name": "Maintenance \u0026 community", "openai-agents-api": 87, "weight": 7 }, { "by": 12, "edge": "openai-agents-api", "harnessrouter": 73, "key": "transparency", "name": "Transparency \u0026 trust", "openai-agents-api": 85, "weight": 7 } ], "summary": "OpenAI Agents API scores 73.3 (BB) on agent readiness against HarnessRouter's 47.7 (D), and leads in every scored category. Both do agent harnesses.", "tasks": null, "tutorials": [], "verdicts": { "harnessrouter": "A product's server sends a task to a named harness and gets streamed progress, sessions and files back, under a published OpenAPI contract with idempotency keys and a closed set of error codes. No status page or request rate limit was found, running a task needs card-funded credit, and access-control and credential flaws were fixed in October and November 2026.", "openai-agents-api": "OpenAI's hosted agent runtime, the Codex harness behind one session call, with MCP, functions, web search, computer use, subagents and sandboxes on OpenAI or your own infrastructure. Documentation, errors and SDKs are thorough. It's still public beta, can't use Zero Data Retention and keeps data in the United States only." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api", "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api.min.md" }, "markdown": "OpenAI Agents API scores 73.3 (BB) on agent readiness against HarnessRouter's 47.7 (D), and leads in every scored category. Both do agent harnesses.\n\n- HarnessRouter: grade D, 47.7/100, rank #1028 of 1354. Markdown https://www.anchorterminal.com/tools/harnessrouter.md · JSON https://www.anchorterminal.com/api/v1/tools/harnessrouter.json\n- OpenAI Agents API: grade BB, 73.3/100, rank #99 of 1354. Markdown https://www.anchorterminal.com/tools/openai-agents-api.md · JSON https://www.anchorterminal.com/api/v1/tools/openai-agents-api.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1041 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md\n\n## Which one, for what\n\n### HarnessRouter (D)\n\nGood for: A product team that wants to run Codex, Claude Code, Hermes or 27 other harnesses server-side behind one task, session and file contract, and switch between them by changing an ID.\n\nAlso in its favour:\n- Open source\n\nWatch for: No status page found (status.harnessrouter.ai has no DNS record), and the terms give no service level without a signed Order Form\n\n### OpenAI Agents API (BB)\n\nGood for: Teams that want OpenAI to run the agent loop, with sandboxes, MCP tools and subagents, and are fine with a beta API, US-only data residency and no Zero Data Retention.\n\nAhead on:\n- Reliability, 60 against 35\n- Schema \u0026 documentation, 88 against 83\n- Agent ergonomics, 80 against 73\n- Security \u0026 auth, 87 against 60\n- Payments \u0026 pricing, 30 against 25\n- Maintenance \u0026 community, 87 against 72\n- Transparency \u0026 trust, 85 against 73\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- No incidents deducted, where HarnessRouter loses 11 points for them\n\nWatch for: Public beta since 10 September 2026 behind the agents=v1 beta header, with no GA date\n\n\n## Why the edge\n\n### Security \u0026 auth: OpenAI Agents API +27\n\n- HarnessRouter (60): Hosted reading. Bearer Workspace API keys, revocable at once through the API, held to one workspace or reaching the organisation, with harness-bound calibration credentials. No OAuth, per-endpoint scopes or expiry found (20 of 30). Least privilege 10 of 20. disabled_tools per configured agent, enforced by the runtime only where GET /v1/bases says hard, and per-turn cost and step caps, with no approval step for actions a harness takes. Prompt injection 10 of 15. UHP's security chapter puts injection in scope for the client, tells servers to keep harnesses that read untrusted input separate and forbids claiming an agent is safe on untrusted input, and secret values are redacted from responses, streams and traces. Operator visibility 10 of 15. A cost breakdown per task on every plan, and the step-by-step trace is beta, included in Scale or $50 a month. Security programme 10 of 20 (was 8). A disclosure policy (v1.0, effective 30 July 2026) with safe harbour and no bounty, SECURITY.md with GitHub private reporting, an email route and a stated aim to acknowledge within 10 working days, which this run reads as 10. GHSA identifiers are cited in public fix commits; no security.txt and no SOC 2 or ISO 27001 found. 20 + 10 + 10 + 10 + 10 = 60.\n- OpenAI Agents API (87): Project keys with restricted per-endpoint permissions, service accounts and workload identity, per the openai-api listing; we didn't confirm a key can be limited to /v1/agents (27 of 30). Automatic review for approvals, a sandbox network restricted to a host allowlist, vaults for secrets and a sandbox security guide (17 of 20). The agent reads web pages, MCP results and browser content; the sandbox security guide and approval flow are the mitigations, with no prompt-injection guide of its own found (8 of 15). Tracing, observability and usage per session and admin audit logs (15). SOC 2 Type 2, ISO 27001 family, Bugcrowd bounty and a disclosure policy, per the openai-api listing (20). Not ZDR-eligible and US residency only, recorded under transparency. 27 + 17 + 8 + 15 + 20 = 87.\n\n### Reliability: OpenAI Agents API +25\n\n- HarnessRouter (35): Hosted reading, for HarnessRouter Cloud at api.harnessrouter.ai, as on 17 October. No status page (status.harnessrouter.ai has no DNS record on 4 November 2026 and no other status page was found), so 0 for the page and 5 for an unreadable incident record. No request rate limit with numbers was found. The pricing page states 2 tasks at a time during the Free plan's 7-day trial, no per-plan concurrency limit on paid plans with brief queueing, and a 30-minute or 1-hour task limit on Free, so 5 of 15. 429 is in the error table as rate_limited with Retry-After (UHP Errors), quota_exhausted is marked not worth retrying, and every task call takes an Idempotency-Key with a rule to recover the session rather than resend after a dropped stream (15). Terms §5.4 still give no service level outside a signed Order Form (0). The task API isn't labelled beta, while tracing and agent memory are (10). 0 + 5 + 5 + 15 + 0 + 10 = 35.\n- OpenAI Agents API (60): Read as a hosted API. status.openai.com has an Agents component under APIs (20). Since release on 10 September (57 days, not 90), the feed names the Agents API in a degraded-performance incident on 14 September, the elevated errors across ChatGPT, Codex and the API on 29 September (the openai-api listing reads that one as a major, 17:52 to 23:14 UTC), computer use issues and degraded workspace agents on 6 and 7 October, degraded performance across the APIs for 22 minutes on 21 October, and overbilling for hosted containers on 19 September. One major, the rest minor (10). Rate limits come from the shared guide, published per tier and model with headers, and the errors page adds a Files API allowance on session creation (15). 429 and 503 guidance with Retry-After, capped backoff and a check-then-retry procedure for turns (15). The Scale Tier SLA in the openai-api listing isn't shown to cover a beta API (0). Public beta behind the agents=v1 header (0). 20 + 10 + 15 + 15 + 0 + 0 = 60.\n\n### Maintenance \u0026 community: OpenAI Agents API +15\n\n- HarnessRouter (72): Open-source reading of the repository behind the hosted service. Last tag v0.38.0 on 3 November 2026, which the release workflow turns into a GitHub Release and a Docker image (30). 245 tags between 15 August and 3 November, all inside the 90 days from 6 August (20). GitHub's issue pages and API refused this session, so open issues and reply times are unchecked. Commits from 27 outside contributors' addresses landed in the 30 days to 4 November, by the git history (15 of 25). No official SDK and no MCP server to register (0). A tests workflow runs every suite on each pull request and push to main, with a release workflow and a Docker image, but whether the default branch passes is unchecked (7 of 10). 30 + 20 + 15 + 0 + 7 = 72.\n- OpenAI Agents API (87): Closed API. Last dated change 16 October 2026, Ultrafast mode and document skills (30). Four dated changelog entries in the 57 days since release, 10 September, 29 September, 9 October and 16 October (20). Changelog and help centre, as the openai-api listing reads them (12 of 15). Official SDKs carry beta.agents (15). SDK CI, per the openai-api listing (10). 30 + 20 + 12 + 15 + 10 = 87.\n\n### Transparency \u0026 trust: OpenAI Agents API +12\n\n- HarnessRouter (73): Editorial half. The server, specification, schema and conformance suite are Apache-2.0. The Cloud's own billing and deployment wasn't confirmed to match the open code, and the Agent Skill has a custom licence for some guides (25 of 30). The privacy policy, DPA, subprocessor list and a retention page agree. Customer content isn't used for training without an opt-in, and periods are stated (tasks deleted at once, agents and files after 30 days, backups within 14 days, credentials within 90, free-plan task records 7 days). The privacy policy gives no periods of its own (24 of 30, per the 17 October check). Deprecation 15 of 20 (was 14). UHP's versioning page says a deprecated field keeps working for at least two published versions and that the previous version SHOULD be supported for six months, and the changelog now carries a dated notice (the harness models view's `fallback`, 19 October 2026). The rule is counted in versions, not time, so dated notices give 15. Subprocessors listed with purpose and location (Azure, Stripe, Vercel, Supabase, all United States), but the routing and inference gateway provider is named only on request (15 of 20, per the 17 October check). 25 + 24 + 15 + 15 = 79. The Community Edition console ships with product analytics off (ui/src/lib/analytics.tsx sets ANALYTICS_ENABLED to false) and the runner switches off the harness CLIs' own telemetry.\n- OpenAI Agents API (85): Closed service with clear terms, Apache-2.0 SDKs (15). Session state retained until deleted, deletable sessions and artifacts, not ZDR-eligible, US residency only, and the data-controls guide agrees; no retention period for artifacts after a sandbox expires (25 of 30). Dated deprecation notices with minimum periods for GA models; a beta API can change faster (15 of 20). Subprocessors and processing countries listed, per the openai-api listing (20). 15 + 25 + 15 + 20 = 75.\n\n### Agent ergonomics: OpenAI Agents API +7\n\n- HarnessRouter (73): API reading. Sessions, turns and files are separate reads, and list endpoints take limit and cursor, but there's no field selection on a response (15 of 25). Cursor paging on session and memory lists with a bounded limit, and few filters found (14 of 20). One error envelope with type, code, param and detail, a closed code set, a retry rule per code and a 422 that lists every failed field without echoing the body (18 of 20). Idempotency-Key on task creation, reuse only for the same request, recover from the session after a drop, and an explicit cancel because closing the stream doesn't stop work (18 of 20). Only input is required to run a task, and budgets default to 400 steps, 7,200 seconds and $10. No official SDK, only the OpenAI Responses shape, clients generated from the OpenAPI file and an Agent Skill (8 of 15). 73 in all.\n- OpenAI Agents API (80): Read as an API an agent drives. Context is compacted automatically, and session budgets and streamed events keep output sized (20 of 25). Sessions can be listed, continued and steered, events streamed or sent by webhook, artifacts fetched (15 of 20). Actionable error codes with recovery steps (20). No idempotency key; a documented check-then-retry procedure (10 of 20). One session call with defaults (medium sandbox, network enabled), SDKs in five languages (15). 20 + 15 + 20 + 10 + 15 = 80.\n\n### Schema \u0026 documentation: OpenAI Agents API +5\n\n- HarnessRouter (83): API reading. UHP's OpenAPI 3.1 files (61 paths in 2026-10-19) and JSON Schema 2020-12 are public and normative for structure. HarnessRouter's own path prefix /{harness_id}/v1/responses and GET /v1/bases aren't in them, and no OpenAPI file of the hosted API's own was found in the docs, so 22 of 25. llms.txt, llms-full.txt, agents.md, docs.md, pricing.md and harnesses.md (10). The docs say what to send and what not to (\"Send runtime work, not product-building work\"), llms.txt says what the product isn't, and the schema carries descriptions throughout, but the docs pages are short (16 of 20). Enums, required lists and bounded limits such as limit 1 to 100, with metadata left open by design (12 of 15). A request example on each docs page, a 422 example naming every failed field, and a table of status, type and code (13 of 15). Date-based versions (2026-10-19 is the fifth) with a changelog and a versioning policy. Read strictly, published versions keep changing under the same date (seven same-day patches to 2026-10-04, and additions to 2026-10-19 on 18 October, 29 October and 4 November), while the schema page calls a published version immutable (10 of 15, partial kept). The conformance page and the suite's README now agree on 101 checks. 22 + 10 + 16 + 12 + 13 + 10 = 83.\n- OpenAI Agents API (88): The reference is linked from the overview and the SDKs carry beta.agents types; we didn't confirm /agents/sessions in OpenAI's public OpenAPI file, so 15 of 25. llms.txt with every Agents API page and Markdown twins (10). The overview, architecture page and the agents guide that compares the Agents API, Agents SDK and Responses API say when to use it (20). Typed configuration with enumerated container sizes, network modes and environment types (13 of 15). Examples in six languages and an errors page with codes per HTTP status, turn and session (15). Dated changelog entries and a versioned beta header (15). 15 + 10 + 20 + 13 + 15 + 15 = 88.\n\n## Score by category\n\n| Category | Weight | HarnessRouter | OpenAI Agents API | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 35 | 60 | OpenAI Agents API +25 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 83 | 88 | OpenAI Agents API +5 |\n| Agent ergonomics | 13% (16.2 this run) | 73 | 80 | OpenAI Agents API +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 60 | 87 | OpenAI Agents API +27 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 25 | 30 | OpenAI Agents API +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 72 | 87 | OpenAI Agents API +15 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 73 | 85 | OpenAI Agents API +12 |\n| Negative events | ≤15 | -11 | 0 | |\n| **Total** | | **47.7 · D** | **73.3 · BB** | |\n\n## Facts side by side\n\n| Fact | HarnessRouter | OpenAI Agents API |\n| --- | --- | --- |\n| Kind | Agent harness | HTTP API |\n| Vendor | HarnessRouter (Lumentree Corporation) | OpenAI |\n| Hosted endpoint | `https://api.harnessrouter.ai` | `https://api.openai.com/v1/agents/sessions` |\n| Transports | HTTP | https |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Apache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides. | Proprietary hosted API under OpenAI's Services Agreement. The SDKs are Apache 2.0 |\n| Tools exposed | 0 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-03 | 2026-10-16 |\n| Terms last updated | no date given | couldn't be read |\n| Privacy policy last updated | 2026-07-30 | couldn't be read |\n| Customer content may train models | yes, with an opt-out | couldn't be read |\n| Terms restrict automated access | yes | couldn't be read |\n| Terms restrict benchmarking | not found in the text | couldn't be read |\n| Terms or service can change without notice | not found in the text | couldn't be read |\n| Arbitration or class-action waiver | yes | couldn't be read |\n| Popularity | 4.1k stars | none |\n| Agent reviews | 2.5/5 (4) | none |\n\n## How the scores have moved\n\n### HarnessRouter\n\n- -5.6 on 4 November 2026: correction, negative event\n- -0.1 on 30 October 2026: checklist\n- +0.2 on 27 October 2026: checklist\n\n### OpenAI Agents API\n\nNo score change since it was listed.\n\n## Verdicts\n\n**HarnessRouter.** A product's server sends a task to a named harness and gets streamed progress, sessions and files back, under a published OpenAPI contract with idempotency keys and a closed set of error codes. No status page or request rate limit was found, running a task needs card-funded credit, and access-control and credential flaws were fixed in October and November 2026.\n\n**OpenAI Agents API.** OpenAI's hosted agent runtime, the Codex harness behind one session call, with MCP, functions, web search, computer use, subagents and sandboxes on OpenAI or your own infrastructure. Documentation, errors and SDKs are thorough. It's still public beta, can't use Zero Data Retention and keeps data in the United States only.\n\n## Before you call either\n\n### HarnessRouter\n\n1. Name the harness yourself. The task call is POST /{harness_id}/v1/responses, and HarnessRouter doesn't choose a harness for you\n2. Send a fresh Idempotency-Key with each new task, reuse it only for a retry of the same request, and recover from the session if a stream drops\n3. Call cancel to stop work. Closing the SSE connection leaves the agent running and billing\n4. Keep the Workspace API key on the server. The docs forbid calling the API from a browser with it\n5. Check each tool's enforcement in GET /v1/bases. On bases marked instruction, disabled_tools is a request to the model, not a block\n\n### OpenAI Agents API\n\n1. POST https://api.openai.com/v1/agents/sessions with a project key and the header OpenAI-Beta: agents=v1, or use client.beta.agents in the SDKs\n2. Before retrying, retrieve the session and turn and check which actions completed, since there's no idempotency key\n3. Set the sandbox network to restricted with an allowlist of up to 100 hosts when the agent doesn't need the open web\n4. Save files from /workspace/outputs before deleting a session; no retention period is stated for artifacts\n5. Don't send data that needs Zero Data Retention or non-US residency; the Agents API supports neither\n\n## Questions\n\n### Which is better for AI agents, HarnessRouter or OpenAI Agents API?\n\nOpenAI Agents API scores 73.3 (BB) on agent readiness against HarnessRouter's 47.7 (D), and leads in every scored category.\n\n### Can an agent call HarnessRouter and OpenAI Agents API without installing anything?\n\nYes. HarnessRouter has a hosted endpoint at https://api.harnessrouter.ai and OpenAI Agents API at https://api.openai.com/v1/agents/sessions.\n\n### Are HarnessRouter and OpenAI Agents API open source?\n\nHarnessRouter is open source (Apache-2.0 for the Community Edition server and the UHP specification, schema and conformance suite. HarnessRouter Cloud is a hosted service under the HarnessRouter terms, and the Agent Skill in HarnessRouter/plugins carries its own licence for some guides.). No open-source release is listed for OpenAI Agents API.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harnessrouter\", \"b\": \"openai-agents-api\"}`. From a terminal: `anchor compare harnessrouter openai-agents-api`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harnessrouter.json and https://www.anchorterminal.com/api/v1/tools/openai-agents-api.json\n\n## Other comparisons with HarnessRouter or OpenAI Agents API\n\n- [Agent Zero vs HarnessRouter](https://www.anchorterminal.com/compare/agent-zero-vs-harnessrouter.md)\n- [Agent Zero vs OpenAI Agents API](https://www.anchorterminal.com/compare/agent-zero-vs-openai-agents-api.md)\n- [Aider vs HarnessRouter](https://www.anchorterminal.com/compare/aider-vs-harnessrouter.md)\n- [Aider vs OpenAI Agents API](https://www.anchorterminal.com/compare/aider-vs-openai-agents-api.md)\n- [Amp vs HarnessRouter](https://www.anchorterminal.com/compare/amp-vs-harnessrouter.md)\n- [Amp vs OpenAI Agents API](https://www.anchorterminal.com/compare/amp-vs-openai-agents-api.md)\n- [Antigravity CLI vs HarnessRouter](https://www.anchorterminal.com/compare/antigravity-cli-vs-harnessrouter.md)\n- [Antigravity CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/antigravity-cli-vs-openai-agents-api.md)\n- [Auggie CLI vs HarnessRouter](https://www.anchorterminal.com/compare/auggie-vs-harnessrouter.md)\n- [Auggie CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/auggie-vs-openai-agents-api.md)\n- [AXLR vs HarnessRouter](https://www.anchorterminal.com/compare/axlr-vs-harnessrouter.md)\n- [AXLR vs OpenAI Agents API](https://www.anchorterminal.com/compare/axlr-vs-openai-agents-api.md)\n- [Claude Code vs HarnessRouter](https://www.anchorterminal.com/compare/claude-code-vs-harnessrouter.md)\n- [Claude Code vs OpenAI Agents API](https://www.anchorterminal.com/compare/claude-code-vs-openai-agents-api.md)\n- [Cline vs HarnessRouter](https://www.anchorterminal.com/compare/cline-vs-harnessrouter.md)\n- [Cline vs OpenAI Agents API](https://www.anchorterminal.com/compare/cline-vs-openai-agents-api.md)\n- [Crush vs HarnessRouter](https://www.anchorterminal.com/compare/crush-vs-harnessrouter.md)\n- [Crush vs OpenAI Agents API](https://www.anchorterminal.com/compare/crush-vs-openai-agents-api.md)\n- [Cursor CLI vs HarnessRouter](https://www.anchorterminal.com/compare/cursor-cli-vs-harnessrouter.md)\n- [Cursor CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/cursor-cli-vs-openai-agents-api.md)\n- [DeepSeek Harness (dsh) vs HarnessRouter](https://www.anchorterminal.com/compare/deepseek-harness-vs-harnessrouter.md)\n- [DeepSeek Harness (dsh) vs OpenAI Agents API](https://www.anchorterminal.com/compare/deepseek-harness-vs-openai-agents-api.md)\n- [dsh-superagent (DeepSeek) vs HarnessRouter](https://www.anchorterminal.com/compare/deepseek-superagent-vs-harnessrouter.md)\n- [dsh-superagent (DeepSeek) vs OpenAI Agents API](https://www.anchorterminal.com/compare/deepseek-superagent-vs-openai-agents-api.md)\n- [Devin vs HarnessRouter](https://www.anchorterminal.com/compare/devin-vs-harnessrouter.md)\n- [Devin vs OpenAI Agents API](https://www.anchorterminal.com/compare/devin-vs-openai-agents-api.md)\n- [Droid CLI vs HarnessRouter](https://www.anchorterminal.com/compare/droid-cli-vs-harnessrouter.md)\n- [Droid CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/droid-cli-vs-openai-agents-api.md)\n- [Pi vs HarnessRouter](https://www.anchorterminal.com/compare/earendil-pi-vs-harnessrouter.md)\n- [Pi vs OpenAI Agents API](https://www.anchorterminal.com/compare/earendil-pi-vs-openai-agents-api.md)\n- [Gemini CLI vs HarnessRouter](https://www.anchorterminal.com/compare/gemini-cli-vs-harnessrouter.md)\n- [Gemini CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/gemini-cli-vs-openai-agents-api.md)\n- [GitHub Copilot CLI vs HarnessRouter](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harnessrouter.md)\n- [GitHub Copilot CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/github-copilot-cli-vs-openai-agents-api.md)\n- [goose vs HarnessRouter](https://www.anchorterminal.com/compare/goose-vs-harnessrouter.md)\n- [goose vs OpenAI Agents API](https://www.anchorterminal.com/compare/goose-vs-openai-agents-api.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)\n- [Harness² vs OpenAI Agents API](https://www.anchorterminal.com/compare/harness2-vs-openai-agents-api.md)\n- [HarnessRouter vs Jules](https://www.anchorterminal.com/compare/harnessrouter-vs-jules.md)\n- [HarnessRouter vs Junie CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-junie.md)\n- [HarnessRouter vs Kilo Code CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-kilo-code-cli.md)\n- [HarnessRouter vs Kimi Code CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-kimi-code-cli.md)\n- [HarnessRouter vs Kiro CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-kiro-cli.md)\n- [HarnessRouter vs mini-swe-agent](https://www.anchorterminal.com/compare/harnessrouter-vs-mini-swe-agent.md)\n- [HarnessRouter vs MiniMax Code](https://www.anchorterminal.com/compare/harnessrouter-vs-minimax-code.md)\n- [HarnessRouter vs Mistral Vibe CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-mistral-vibe-cli.md)\n- [HarnessRouter vs Muse Code](https://www.anchorterminal.com/compare/harnessrouter-vs-muse-code.md)\n- [HarnessRouter vs OpenAI Codex](https://www.anchorterminal.com/compare/harnessrouter-vs-openai-codex.md)\n- [HarnessRouter vs OpenCode](https://www.anchorterminal.com/compare/harnessrouter-vs-opencode.md)\n- [HarnessRouter vs OpenHands](https://www.anchorterminal.com/compare/harnessrouter-vs-openhands.md)\n- [HarnessRouter vs OpenMausBot](https://www.anchorterminal.com/compare/harnessrouter-vs-openmausbot.md)\n- [HarnessRouter vs Prime Agent](https://www.anchorterminal.com/compare/harnessrouter-vs-prime-agent.md)\n- [HarnessRouter vs Qoder CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-qoder-cli.md)\n- [HarnessRouter vs Qwen Code](https://www.anchorterminal.com/compare/harnessrouter-vs-qwen-code.md)\n- [HarnessRouter vs Mirror CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-reflection-mirror.md)\n- [HarnessRouter vs Rovo Dev CLI](https://www.anchorterminal.com/compare/harnessrouter-vs-rovo-dev-cli.md)\n- [HarnessRouter vs Unstoppable](https://www.anchorterminal.com/compare/harnessrouter-vs-unstoppable.md)\n- [HarnessRouter vs Vibe-Trading](https://www.anchorterminal.com/compare/harnessrouter-vs-vibe-trading.md)\n- [HarnessRouter vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/harnessrouter-vs-warp.md)\n- [Jules vs OpenAI Agents API](https://www.anchorterminal.com/compare/jules-vs-openai-agents-api.md)\n- [Junie CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/junie-vs-openai-agents-api.md)\n- [Kilo Code CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/kilo-code-cli-vs-openai-agents-api.md)\n- [Kimi Code CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/kimi-code-cli-vs-openai-agents-api.md)\n- [Kiro CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/kiro-cli-vs-openai-agents-api.md)\n- [mini-swe-agent vs OpenAI Agents API](https://www.anchorterminal.com/compare/mini-swe-agent-vs-openai-agents-api.md)\n- [MiniMax Code vs OpenAI Agents API](https://www.anchorterminal.com/compare/minimax-code-vs-openai-agents-api.md)\n- [Mistral Vibe CLI vs OpenAI Agents API](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-openai-agents-api.md)\n- [Muse Code vs OpenAI Agents API](https://www.anchorterminal.com/compare/muse-code-vs-openai-agents-api.md)\n- [OpenAI Agents API vs OpenAI Codex](https://www.anchorterminal.com/compare/openai-agents-api-vs-openai-codex.md)\n- [OpenAI Agents API vs OpenCode](https://www.anchorterminal.com/compare/openai-agents-api-vs-opencode.md)\n- [OpenAI Agents API vs OpenHands](https://www.anchorterminal.com/compare/openai-agents-api-vs-openhands.md)\n- [OpenAI Agents API vs OpenMausBot](https://www.anchorterminal.com/compare/openai-agents-api-vs-openmausbot.md)\n- [OpenAI Agents API vs Prime Agent](https://www.anchorterminal.com/compare/openai-agents-api-vs-prime-agent.md)\n- [OpenAI Agents API vs Qoder CLI](https://www.anchorterminal.com/compare/openai-agents-api-vs-qoder-cli.md)\n- [OpenAI Agents API vs Qwen Code](https://www.anchorterminal.com/compare/openai-agents-api-vs-qwen-code.md)\n- [OpenAI Agents API vs Mirror CLI](https://www.anchorterminal.com/compare/openai-agents-api-vs-reflection-mirror.md)\n- [OpenAI Agents API vs Rovo Dev CLI](https://www.anchorterminal.com/compare/openai-agents-api-vs-rovo-dev-cli.md)\n- [OpenAI Agents API vs Unstoppable](https://www.anchorterminal.com/compare/openai-agents-api-vs-unstoppable.md)\n- [OpenAI Agents API vs Vibe-Trading](https://www.anchorterminal.com/compare/openai-agents-api-vs-vibe-trading.md)\n- [OpenAI Agents API vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/openai-agents-api-vs-warp.md)\n- [Clawboo vs HarnessRouter](https://www.anchorterminal.com/compare/clawboo-vs-harnessrouter.md)\n- [CLI Manager vs HarnessRouter](https://www.anchorterminal.com/compare/cli-manager-vs-harnessrouter.md)\n- [Harness vs HarnessRouter](https://www.anchorterminal.com/compare/harness-autonomous-vs-harnessrouter.md)\n- [HarnessRouter vs Paperclip](https://www.anchorterminal.com/compare/harnessrouter-vs-paperclip.md)\n- [HarnessRouter vs Parallax](https://www.anchorterminal.com/compare/harnessrouter-vs-parallax-agents.md)\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": "2026-11-06", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "HarnessRouter vs OpenAI Agents API", "url": "" } ], "description": "OpenAI Agents scores 73.3 (BB) to HarnessRouter's 47.7 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "HarnessRouter D 47.7", "OpenAI Agents API BB 73.3", "scores" ], "h1": "HarnessRouter vs OpenAI Agents API", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/harnessrouter-vs-openai-agents-api", "published": "2026-10-01", "section": "tools", "title": "HarnessRouter vs OpenAI Agents for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-11-06", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api" }, "tokens": { "markdown": 7150, "slim": 3530 }, "version": 1 }