{ "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": 1131, "ranked": true, "rankOf": 1486, "categoryRank": 46, "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": "2026-11-07T18:20:29.556272565Z", "lastOk": true, "lastStatus": 404, "lastMs": 313, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 291, "p95ms24h": 400, "samples24h": 239, "samples30d": 5145, "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": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "versions": [ { "registry": "github", "name": "HarnessRouter/harnessrouter", "version": "v0.38.2", "released": "2026-11-04", "seenAt": "2026-11-06T23:32:20.439259022Z" } ], "githubStars": 4262, "securityTxt": { "url": "https://harnessrouter.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:32.980927731Z" }, "llmsTxt": { "url": "https://harnessrouter.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:40.598398049Z" }, "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": "2026-11-07T14:22:52.813950452Z", "changedAt": "2026-11-04T08:35:29.196603298Z", "fingerprint": "df248ace8f95" }, { "url": "https://harnessrouter.ai/pricing.md", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:10:52.413474371Z", "changedAt": "2026-10-18T23:31:33.798956939Z", "fingerprint": "b31b753df12b" }, { "url": "https://harnessrouter.ai/legal/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:10:48.041658297Z", "changedAt": "2026-11-03T07:51:05.619736871Z", "fingerprint": "3de312eb4d16" }, { "url": "https://harnessrouter.ai/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:10:50.353093961Z", "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": "2026-11-07T18:20:29.556272565Z" } }, "answer": "T3 Code scores 51.9 (D) on agent readiness against HarnessRouter's 47.7 (D), and leads in 3 of 7 scored categories. HarnessRouter leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and transparency \u0026 trust.", "b": { "slug": "t3-code", "name": "T3 Code", "vendor": "T3 Tools Inc.", "vendorUrl": "https://t3.codes", "kind": "harness", "category": "agent-harnesses", "summary": "T3 Code is an open-source control surface for the coding agents on your machine, Claude Code, Codex, Cursor, Grok Build, OpenCode, Antigravity and fx, from desktop, web and iOS and Android apps.", "url": "https://www.anchorterminal.com/tools/t3-code", "markdownUrl": "https://www.anchorterminal.com/tools/t3-code.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/t3-code.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/t3-code.json", "dns": "t3-code.grade.anchorterminal.com", "repo": "https://github.com/pingdotgg/t3code", "license": "MIT", "transports": [], "packages": [], "auth": "none", "pricing": "free", "pricingNotes": "Free and open source. You pay for the coding agents it runs, through your own subscriptions or API keys (checked 2026-11-07).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No payment protocol in the repository or README (checked 2026-11-07).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-07" }, "docsUrl": "https://github.com/pingdotgg/t3code/tree/main/docs", "capabilities": [ "agent.harness", "agent.multi-agent" ], "tags": [ "open-source", "mit", "desktop-app", "mobile", "telemetry", "new" ], "lastRelease": "2026-11-06", "graded": true, "anchor": { "graded": true, "score": 51.9, "grade": "D", "agentReady": false, "rank": 1002, "ranked": true, "rankOf": 1486, "categoryRank": 40, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 60, "maintenance": 75, "payments": 60, "reliability": 43, "schema": 55, "security": 35, "transparency": 51 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-07" }, "negative": 0, "verdict": "A fast-moving open-source way to run and steer several coding agents from desktop, browser or phone, using the subscriptions you already have. It's pre-1.0, and it sends usage data by default, including hashed identifiers for your OpenAI and Claude accounts, with the opt-out documented outside the README.", "bestFor": "Developers who want one app, including on their phone, to drive several coding agents they already pay for.", "strengths": [ "Controls Claude Code, Codex, Cursor, Grok Build, OpenCode, Antigravity and fx with your existing subscriptions", "iOS and Android apps to steer agents running on your machine", "Managed policies for teams, including turning telemetry off", "MIT, with active CI and daily nightlies" ], "weaknesses": [ "Usage data on by default, with hashed OpenAI and Claude account identifiers, and relay traces to Axiom", "The telemetry opt-out is in the docs, not the README", "Pre-1.0, at 0.1.7 stable", "Installs with curl piped to sh" ], "agentNotes": [ "Set T3CODE_TELEMETRY_ENABLED=false before starting the server if you don't want usage events sent", "Install and log in to at least one provider CLI first, such as codex login or claude auth login", "Use a managed policy to fix settings across a team" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 51.9 } ], "editorialScores": { "ergonomics": 60, "maintenance": 75, "payments": 60, "reliability": 43, "schema": 55, "security": 35, "transparency": 62 }, "provenanceScore": 40, "checked": { "categories": { "ergonomics": "2026-11-07", "maintenance": "2026-11-07", "payments": "2026-11-07", "reliability": "2026-11-07", "schema": "2026-11-07", "security": "2026-11-07", "transparency": "2026-11-07" }, "last": "2026-11-07", "oldest": "2026-11-07", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "curl -fsSL https://t3.codes/install.sh | sh" }, "letme": { "capability": "https://letme.dev/agent.harness", "tool": "https://letme.dev/t3-code" }, "area": "frameworks", "provenance": { "legalEntity": "T3 Tools Inc.", "domain": "t3.codes", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-07", "notes": [ "The licence names T3 Tools Inc.. The repository is github.com/pingdotgg/t3code." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/t3-code.json", "live": { "slug": "t3-code", "securityTxt": { "url": "https://t3.codes/.well-known/security.txt", "state": "valid", "expires": "2027-11-07T09:42:17.281Z", "checkedAt": "2026-11-07T16:01:55.404622007Z" }, "updatedAt": "2026-11-07T16:01:55.404622007Z" } }, "edges": [ { "by": 35, "category": "payments", "leads": "t3-code", "name": "Payments \u0026 pricing", "reasons": { "a": "Published rubric, for the hosted service. No machine payment protocol (0). Per-unit prices without a login, agent work per active minute and model calls at listed provider prices per million tokens (20). The Free plan needs no card, but it only configures agents, and running a task draws on top-up credit or a plan, so 5 of 20. A person signs up in a browser and creates the key in the console (0). 0 + 20 + 5 + 0 = 25. Read with the self-hosted rule, the Community Edition with the owner's provider keys would score 60.", "b": "Free self-hosted software with nothing to buy, so 0 for a protocol and 20 each for public pricing, a free tier and onboarding with no sign-up, 60." }, "scores": { "a": 25, "b": 60 } }, { "by": 28, "category": "schema", "leads": "harnessrouter", "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": "Harness reading. User docs in the repository (managed policy, handoffs, providers, telemetry), AGENTS.md for contributors, a server other clients connect to (55)." }, "scores": { "a": 83, "b": 55 } }, { "by": 25, "category": "security", "leads": "harnessrouter", "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": "Harness reading. Product usage events go by default to ingest.t3.codes and PostHog, with hashed identifiers for your T3 Connect, OpenAI and Claude accounts, and relay traces to Axiom, which can include machine names and error text. Off with T3CODE_TELEMETRY_ENABLED=false or a managed policy. Disclosed in docs/user/telemetry.md, not the README (10 of 30). Permission modes and managed policies (12 of 20). No prompt-injection guidance (5). No audit log (5). No security policy file found (3). 10 + 12 + 5 + 5 + 3 = 35." }, "scores": { "a": 60, "b": 35 } }, { "by": 22, "category": "transparency", "leads": "harnessrouter", "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": "MIT (30). docs/user/telemetry.md lists what is sent and what isn't, but includes hashed third-party account identifiers and the README doesn't mention it (15 of 30). No deprecation policy (5). Disclosed with an opt-out, on by default (12 of 20). 30 + 15 + 5 + 12 = 62." }, "scores": { "a": 73, "b": 51 } }, { "by": 13, "category": "ergonomics", "leads": "harnessrouter", "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": "Harness reading. Remote control from phone or browser, portable handoffs between providers and managed policies for teams (60)." }, "scores": { "a": 73, "b": 60 } }, { "by": 8, "category": "reliability", "leads": "t3-code", "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": "Local software. An install script and desktop and mobile apps from the vendor (20). ci.yml and windows-tests.yml run on the repository; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Stable tags v0.1.5 to v0.1.7 with many nightlies, no changelog file (8). Version 0.1.7 (0). 20 + 15 + 0 + 8 + 0 = 43." }, "scores": { "a": 35, "b": 43 } } ], "facts": [ { "a": "Agent harness", "b": "Agent harness", "name": "Kind" }, { "a": "HarnessRouter (Lumentree Corporation)", "b": "T3 Tools Inc.", "name": "Vendor" }, { "a": "https://api.harnessrouter.ai", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "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": "MIT", "name": "Licence" }, { "a": "0", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-11-03", "b": "2026-11-06", "name": "Last release" }, { "a": "no date given", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-07-30", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "not read yet", "name": "Customer content may train models" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not read yet", "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": "T3 Code scores 51.9 (D) on agent readiness against HarnessRouter's 47.7 (D), and leads in 3 of 7 scored categories. HarnessRouter leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and transparency \u0026 trust.", "question": "Which is better for AI agents, HarnessRouter or T3 Code?" }, { "answer": "Yes. 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.). T3 Code is open source (MIT).", "question": "Are HarnessRouter and T3 Code open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 83 against 55", "Agent ergonomics, 73 against 60", "Security \u0026 auth, 60 against 35", "Transparency \u0026 trust, 73 against 51" ], "also": [ "A hosted endpoint, with nothing to install" ], "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, 43 against 35", "Payments \u0026 pricing, 60 against 25" ], "also": [ "No key needed to call it", "No incidents deducted, where HarnessRouter loses 11 points for them" ], "goodFor": "Developers who want one app, including on their phone, to drive several coding agents they already pay for.", "slug": "t3-code", "watchFor": "Usage data on by default, with hashed OpenAI and Claude account identifiers, and relay traces to Axiom" } ], "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" } ], "t3-code": 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-t3-code.json", "title": "Agent Zero vs T3 Code", "url": "https://www.anchorterminal.com/compare/agent-zero-vs-t3-code" }, { "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-t3-code.json", "title": "Aider vs T3 Code", "url": "https://www.anchorterminal.com/compare/aider-vs-t3-code" }, { "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-t3-code.json", "title": "Amp vs T3 Code", "url": "https://www.anchorterminal.com/compare/amp-vs-t3-code" }, { "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-t3-code.json", "title": "Antigravity CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/antigravity-cli-vs-t3-code" }, { "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-t3-code.json", "title": "Auggie CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/auggie-vs-t3-code" }, { "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-t3-code.json", "title": "AXLR vs T3 Code", "url": "https://www.anchorterminal.com/compare/axlr-vs-t3-code" }, { "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-t3-code.json", "title": "Claude Code vs T3 Code", "url": "https://www.anchorterminal.com/compare/claude-code-vs-t3-code" }, { "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-t3-code.json", "title": "Cline vs T3 Code", "url": "https://www.anchorterminal.com/compare/cline-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/conductor-vs-harnessrouter.json", "title": "Conductor vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/conductor-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/conductor-vs-t3-code.json", "title": "Conductor vs T3 Code", "url": "https://www.anchorterminal.com/compare/conductor-vs-t3-code" }, { "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-t3-code.json", "title": "Crush vs T3 Code", "url": "https://www.anchorterminal.com/compare/crush-vs-t3-code" }, { "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-t3-code.json", "title": "Cursor CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/cursor-cli-vs-t3-code" }, { "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-t3-code.json", "title": "DeepSeek Harness (dsh) vs T3 Code", "url": "https://www.anchorterminal.com/compare/deepseek-harness-vs-t3-code" }, { "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-t3-code.json", "title": "dsh-superagent (DeepSeek) vs T3 Code", "url": "https://www.anchorterminal.com/compare/deepseek-superagent-vs-t3-code" }, { "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-t3-code.json", "title": "Devin vs T3 Code", "url": "https://www.anchorterminal.com/compare/devin-vs-t3-code" }, { "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-t3-code.json", "title": "Droid CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/droid-cli-vs-t3-code" }, { "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-t3-code.json", "title": "Pi vs T3 Code", "url": "https://www.anchorterminal.com/compare/earendil-pi-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-harnessrouter.json", "title": "Emdash vs HarnessRouter", "url": "https://www.anchorterminal.com/compare/emdash-vs-harnessrouter" }, { "json": "https://www.anchorterminal.com/compare/emdash-vs-t3-code.json", "title": "Emdash vs T3 Code", "url": "https://www.anchorterminal.com/compare/emdash-vs-t3-code" }, { "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-t3-code.json", "title": "Gemini CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/gemini-cli-vs-t3-code" }, { "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-t3-code.json", "title": "GitHub Copilot CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/github-copilot-cli-vs-t3-code" }, { "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-t3-code.json", "title": "goose vs T3 Code", "url": "https://www.anchorterminal.com/compare/goose-vs-t3-code" }, { "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-t3-code.json", "title": "Harness² vs T3 Code", "url": "https://www.anchorterminal.com/compare/harness2-vs-t3-code" }, { "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-letta.json", "title": "HarnessRouter vs Letta", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-letta" }, { "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-agents-api.json", "title": "HarnessRouter vs OpenAI Agents API", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api" }, { "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-orca.json", "title": "HarnessRouter vs Orca", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-orca" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-paseo.json", "title": "HarnessRouter vs Paseo", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-paseo" }, { "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-sculptor.json", "title": "HarnessRouter vs Sculptor", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-sculptor" }, { "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-traycer.json", "title": "HarnessRouter vs Traycer", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-traycer" }, { "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-verdent.json", "title": "HarnessRouter vs Verdent", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-verdent" }, { "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-t3-code.json", "title": "Jules vs T3 Code", "url": "https://www.anchorterminal.com/compare/jules-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/junie-vs-t3-code.json", "title": "Junie CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/junie-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-t3-code.json", "title": "Kilo Code CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/kilo-code-cli-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-t3-code.json", "title": "Kimi Code CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/kimi-code-cli-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/kiro-cli-vs-t3-code.json", "title": "Kiro CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/kiro-cli-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/letta-vs-t3-code.json", "title": "Letta vs T3 Code", "url": "https://www.anchorterminal.com/compare/letta-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-t3-code.json", "title": "mini-swe-agent vs T3 Code", "url": "https://www.anchorterminal.com/compare/mini-swe-agent-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/minimax-code-vs-t3-code.json", "title": "MiniMax Code vs T3 Code", "url": "https://www.anchorterminal.com/compare/minimax-code-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-t3-code.json", "title": "Mistral Vibe CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/muse-code-vs-t3-code.json", "title": "Muse Code vs T3 Code", "url": "https://www.anchorterminal.com/compare/muse-code-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/openai-agents-api-vs-t3-code.json", "title": "OpenAI Agents API vs T3 Code", "url": "https://www.anchorterminal.com/compare/openai-agents-api-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/openai-codex-vs-t3-code.json", "title": "OpenAI Codex vs T3 Code", "url": "https://www.anchorterminal.com/compare/openai-codex-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/opencode-vs-t3-code.json", "title": "OpenCode vs T3 Code", "url": "https://www.anchorterminal.com/compare/opencode-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/openhands-vs-t3-code.json", "title": "OpenHands vs T3 Code", "url": "https://www.anchorterminal.com/compare/openhands-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/orca-vs-t3-code.json", "title": "Orca vs T3 Code", "url": "https://www.anchorterminal.com/compare/orca-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/paseo-vs-t3-code.json", "title": "Paseo vs T3 Code", "url": "https://www.anchorterminal.com/compare/paseo-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/prime-agent-vs-t3-code.json", "title": "Prime Agent vs T3 Code", "url": "https://www.anchorterminal.com/compare/prime-agent-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/qoder-cli-vs-t3-code.json", "title": "Qoder CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/qoder-cli-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/qwen-code-vs-t3-code.json", "title": "Qwen Code vs T3 Code", "url": "https://www.anchorterminal.com/compare/qwen-code-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/reflection-mirror-vs-t3-code.json", "title": "Mirror CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/reflection-mirror-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/rovo-dev-cli-vs-t3-code.json", "title": "Rovo Dev CLI vs T3 Code", "url": "https://www.anchorterminal.com/compare/rovo-dev-cli-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/sculptor-vs-t3-code.json", "title": "Sculptor vs T3 Code", "url": "https://www.anchorterminal.com/compare/sculptor-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/t3-code-vs-traycer.json", "title": "T3 Code vs Traycer", "url": "https://www.anchorterminal.com/compare/t3-code-vs-traycer" }, { "json": "https://www.anchorterminal.com/compare/t3-code-vs-unstoppable.json", "title": "T3 Code vs Unstoppable", "url": "https://www.anchorterminal.com/compare/t3-code-vs-unstoppable" }, { "json": "https://www.anchorterminal.com/compare/t3-code-vs-verdent.json", "title": "T3 Code vs Verdent", "url": "https://www.anchorterminal.com/compare/t3-code-vs-verdent" }, { "json": "https://www.anchorterminal.com/compare/t3-code-vs-vibe-trading.json", "title": "T3 Code vs Vibe-Trading", "url": "https://www.anchorterminal.com/compare/t3-code-vs-vibe-trading" }, { "json": "https://www.anchorterminal.com/compare/t3-code-vs-warp.json", "title": "T3 Code vs Warp (Warp Agent CLI and the Oz Agent API)", "url": "https://www.anchorterminal.com/compare/t3-code-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/clawboo-vs-t3-code.json", "title": "Clawboo vs T3 Code", "url": "https://www.anchorterminal.com/compare/clawboo-vs-t3-code" }, { "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/cli-manager-vs-t3-code.json", "title": "CLI Manager vs T3 Code", "url": "https://www.anchorterminal.com/compare/cli-manager-vs-t3-code" }, { "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/harness-autonomous-vs-t3-code.json", "title": "Harness vs T3 Code", "url": "https://www.anchorterminal.com/compare/harness-autonomous-vs-t3-code" }, { "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" }, { "json": "https://www.anchorterminal.com/compare/openmausbot-vs-t3-code.json", "title": "OpenMausBot vs T3 Code", "url": "https://www.anchorterminal.com/compare/openmausbot-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/paperclip-vs-t3-code.json", "title": "Paperclip vs T3 Code", "url": "https://www.anchorterminal.com/compare/paperclip-vs-t3-code" }, { "json": "https://www.anchorterminal.com/compare/parallax-agents-vs-t3-code.json", "title": "Parallax vs T3 Code", "url": "https://www.anchorterminal.com/compare/parallax-agents-vs-t3-code" } ], "panel": null, "scores": [ { "by": 8, "edge": "t3-code", "harnessrouter": 35, "key": "reliability", "name": "Reliability", "t3-code": 43, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 28, "edge": "harnessrouter", "harnessrouter": 83, "key": "schema", "name": "Schema \u0026 documentation", "t3-code": 55, "weight": 13 }, { "by": 13, "edge": "harnessrouter", "harnessrouter": 73, "key": "ergonomics", "name": "Agent ergonomics", "t3-code": 60, "weight": 13 }, { "by": 25, "edge": "harnessrouter", "harnessrouter": 60, "key": "security", "name": "Security \u0026 auth", "t3-code": 35, "weight": 14 }, { "by": 35, "edge": "t3-code", "harnessrouter": 25, "key": "payments", "name": "Payments \u0026 pricing", "t3-code": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 3, "edge": "t3-code", "harnessrouter": 72, "key": "maintenance", "name": "Maintenance \u0026 community", "t3-code": 75, "weight": 7 }, { "by": 22, "edge": "harnessrouter", "harnessrouter": 73, "key": "transparency", "name": "Transparency \u0026 trust", "t3-code": 51, "weight": 7 } ], "summary": "T3 Code scores 51.9 (D) on agent readiness against HarnessRouter's 47.7 (D), and leads in 3 of 7 scored categories. HarnessRouter leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and transparency \u0026 trust. 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.", "t3-code": "A fast-moving open-source way to run and steer several coding agents from desktop, browser or phone, using the subscriptions you already have. It's pre-1.0, and it sends usage data by default, including hashed identifiers for your OpenAI and Claude accounts, with the opt-out documented outside the README." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/harnessrouter-vs-t3-code", "json": "https://www.anchorterminal.com/compare/harnessrouter-vs-t3-code.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/harnessrouter-vs-t3-code.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/harnessrouter-vs-t3-code.min.md" }, "markdown": "T3 Code scores 51.9 (D) on agent readiness against HarnessRouter's 47.7 (D), and leads in 3 of 7 scored categories. HarnessRouter leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and transparency \u0026 trust. Both do agent harnesses.\n\n- HarnessRouter: grade D, 47.7/100, rank #1131 of 1486. Markdown https://www.anchorterminal.com/tools/harnessrouter.md · JSON https://www.anchorterminal.com/api/v1/tools/harnessrouter.json\n- T3 Code: grade D, 51.9/100, rank #1002 of 1486. Markdown https://www.anchorterminal.com/tools/t3-code.md · JSON https://www.anchorterminal.com/api/v1/tools/t3-code.json\n- Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md\n- All 1500 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\nAhead on:\n- Schema \u0026 documentation, 83 against 55\n- Agent ergonomics, 73 against 60\n- Security \u0026 auth, 60 against 35\n- Transparency \u0026 trust, 73 against 51\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\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### T3 Code (D)\n\nGood for: Developers who want one app, including on their phone, to drive several coding agents they already pay for.\n\nAhead on:\n- Reliability, 43 against 35\n- Payments \u0026 pricing, 60 against 25\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where HarnessRouter loses 11 points for them\n\nWatch for: Usage data on by default, with hashed OpenAI and Claude account identifiers, and relay traces to Axiom\n\n\n## Why the edge\n\n### Payments \u0026 pricing: T3 Code +35\n\n- HarnessRouter (25): Published rubric, for the hosted service. No machine payment protocol (0). Per-unit prices without a login, agent work per active minute and model calls at listed provider prices per million tokens (20). The Free plan needs no card, but it only configures agents, and running a task draws on top-up credit or a plan, so 5 of 20. A person signs up in a browser and creates the key in the console (0). 0 + 20 + 5 + 0 = 25. Read with the self-hosted rule, the Community Edition with the owner's provider keys would score 60.\n- T3 Code (60): Free self-hosted software with nothing to buy, so 0 for a protocol and 20 each for public pricing, a free tier and onboarding with no sign-up, 60.\n\n### Schema \u0026 documentation: HarnessRouter +28\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- T3 Code (55): Harness reading. User docs in the repository (managed policy, handoffs, providers, telemetry), AGENTS.md for contributors, a server other clients connect to (55).\n\n### Security \u0026 auth: HarnessRouter +25\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- T3 Code (35): Harness reading. Product usage events go by default to ingest.t3.codes and PostHog, with hashed identifiers for your T3 Connect, OpenAI and Claude accounts, and relay traces to Axiom, which can include machine names and error text. Off with T3CODE_TELEMETRY_ENABLED=false or a managed policy. Disclosed in docs/user/telemetry.md, not the README (10 of 30). Permission modes and managed policies (12 of 20). No prompt-injection guidance (5). No audit log (5). No security policy file found (3). 10 + 12 + 5 + 5 + 3 = 35.\n\n### Transparency \u0026 trust: HarnessRouter +22\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- T3 Code (51): MIT (30). docs/user/telemetry.md lists what is sent and what isn't, but includes hashed third-party account identifiers and the README doesn't mention it (15 of 30). No deprecation policy (5). Disclosed with an opt-out, on by default (12 of 20). 30 + 15 + 5 + 12 = 62.\n\n### Agent ergonomics: HarnessRouter +13\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- T3 Code (60): Harness reading. Remote control from phone or browser, portable handoffs between providers and managed policies for teams (60).\n\n### Reliability: T3 Code +8\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- T3 Code (43): Local software. An install script and desktop and mobile apps from the vendor (20). ci.yml and windows-tests.yml run on the repository; pass state not read (15). GitHub issues and pull requests weren't read (GitHub's pages refuse these sessions), so that line is scored absent (0). Stable tags v0.1.5 to v0.1.7 with many nightlies, no changelog file (8). Version 0.1.7 (0). 20 + 15 + 0 + 8 + 0 = 43.\n\n## Score by category\n\n| Category | Weight | HarnessRouter | T3 Code | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 35 | 43 | T3 Code +8 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 83 | 55 | HarnessRouter +28 |\n| Agent ergonomics | 13% (16.2 this run) | 73 | 60 | HarnessRouter +13 |\n| Security \u0026 auth | 14% (17.5 this run) | 60 | 35 | HarnessRouter +25 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 25 | 60 | T3 Code +35 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 72 | 75 | T3 Code +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 73 | 51 | HarnessRouter +22 |\n| Negative events | ≤15 | -11 | 0 | |\n| **Total** | | **47.7 · D** | **51.9 · D** | |\n\n## Facts side by side\n\n| Fact | HarnessRouter | T3 Code |\n| --- | --- | --- |\n| Kind | Agent harness | Agent harness |\n| Vendor | HarnessRouter (Lumentree Corporation) | T3 Tools Inc. |\n| Hosted endpoint | `https://api.harnessrouter.ai` | no (local only) |\n| Transports | HTTP | |\n| Auth | API key | None |\n| Pricing | Pay per use | Free |\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. | MIT |\n| Tools exposed | 0 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-11-03 | 2026-11-06 |\n| Terms last updated | no date given | no document linked |\n| Privacy policy last updated | 2026-07-30 | no document linked |\n| Customer content may train models | yes, with an opt-out | not read yet |\n| Terms restrict automated access | yes | not read yet |\n| Terms restrict benchmarking | not found in the text | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | yes | not read yet |\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### T3 Code\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**T3 Code.** A fast-moving open-source way to run and steer several coding agents from desktop, browser or phone, using the subscriptions you already have. It's pre-1.0, and it sends usage data by default, including hashed identifiers for your OpenAI and Claude accounts, with the opt-out documented outside the README.\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### T3 Code\n\n1. Set T3CODE_TELEMETRY_ENABLED=false before starting the server if you don't want usage events sent\n2. Install and log in to at least one provider CLI first, such as codex login or claude auth login\n3. Use a managed policy to fix settings across a team\n\n## Questions\n\n### Which is better for AI agents, HarnessRouter or T3 Code?\n\nT3 Code scores 51.9 (D) on agent readiness against HarnessRouter's 47.7 (D), and leads in 3 of 7 scored categories. HarnessRouter leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and transparency \u0026 trust.\n\n### Are HarnessRouter and T3 Code open source?\n\nYes. 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.). T3 Code is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/harnessrouter-vs-t3-code.json, and with the fewest tokens: https://www.anchorterminal.com/compare/harnessrouter-vs-t3-code.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"harnessrouter\", \"b\": \"t3-code\"}`. From a terminal: `anchor compare harnessrouter t3-code`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/harnessrouter.json and https://www.anchorterminal.com/api/v1/tools/t3-code.json\n\n## Other comparisons with HarnessRouter or T3 Code\n\n- [Agent Zero vs HarnessRouter](https://www.anchorterminal.com/compare/agent-zero-vs-harnessrouter.md)\n- [Agent Zero vs T3 Code](https://www.anchorterminal.com/compare/agent-zero-vs-t3-code.md)\n- [Aider vs HarnessRouter](https://www.anchorterminal.com/compare/aider-vs-harnessrouter.md)\n- [Aider vs T3 Code](https://www.anchorterminal.com/compare/aider-vs-t3-code.md)\n- [Amp vs HarnessRouter](https://www.anchorterminal.com/compare/amp-vs-harnessrouter.md)\n- [Amp vs T3 Code](https://www.anchorterminal.com/compare/amp-vs-t3-code.md)\n- [Antigravity CLI vs HarnessRouter](https://www.anchorterminal.com/compare/antigravity-cli-vs-harnessrouter.md)\n- [Antigravity CLI vs T3 Code](https://www.anchorterminal.com/compare/antigravity-cli-vs-t3-code.md)\n- [Auggie CLI vs HarnessRouter](https://www.anchorterminal.com/compare/auggie-vs-harnessrouter.md)\n- [Auggie CLI vs T3 Code](https://www.anchorterminal.com/compare/auggie-vs-t3-code.md)\n- [AXLR vs HarnessRouter](https://www.anchorterminal.com/compare/axlr-vs-harnessrouter.md)\n- [AXLR vs T3 Code](https://www.anchorterminal.com/compare/axlr-vs-t3-code.md)\n- [Claude Code vs HarnessRouter](https://www.anchorterminal.com/compare/claude-code-vs-harnessrouter.md)\n- [Claude Code vs T3 Code](https://www.anchorterminal.com/compare/claude-code-vs-t3-code.md)\n- [Cline vs HarnessRouter](https://www.anchorterminal.com/compare/cline-vs-harnessrouter.md)\n- [Cline vs T3 Code](https://www.anchorterminal.com/compare/cline-vs-t3-code.md)\n- [Conductor vs HarnessRouter](https://www.anchorterminal.com/compare/conductor-vs-harnessrouter.md)\n- [Conductor vs T3 Code](https://www.anchorterminal.com/compare/conductor-vs-t3-code.md)\n- [Crush vs HarnessRouter](https://www.anchorterminal.com/compare/crush-vs-harnessrouter.md)\n- [Crush vs T3 Code](https://www.anchorterminal.com/compare/crush-vs-t3-code.md)\n- [Cursor CLI vs HarnessRouter](https://www.anchorterminal.com/compare/cursor-cli-vs-harnessrouter.md)\n- [Cursor CLI vs T3 Code](https://www.anchorterminal.com/compare/cursor-cli-vs-t3-code.md)\n- [DeepSeek Harness (dsh) vs HarnessRouter](https://www.anchorterminal.com/compare/deepseek-harness-vs-harnessrouter.md)\n- [DeepSeek Harness (dsh) vs T3 Code](https://www.anchorterminal.com/compare/deepseek-harness-vs-t3-code.md)\n- [dsh-superagent (DeepSeek) vs HarnessRouter](https://www.anchorterminal.com/compare/deepseek-superagent-vs-harnessrouter.md)\n- [dsh-superagent (DeepSeek) vs T3 Code](https://www.anchorterminal.com/compare/deepseek-superagent-vs-t3-code.md)\n- [Devin vs HarnessRouter](https://www.anchorterminal.com/compare/devin-vs-harnessrouter.md)\n- [Devin vs T3 Code](https://www.anchorterminal.com/compare/devin-vs-t3-code.md)\n- [Droid CLI vs HarnessRouter](https://www.anchorterminal.com/compare/droid-cli-vs-harnessrouter.md)\n- [Droid CLI vs T3 Code](https://www.anchorterminal.com/compare/droid-cli-vs-t3-code.md)\n- [Pi vs HarnessRouter](https://www.anchorterminal.com/compare/earendil-pi-vs-harnessrouter.md)\n- [Pi vs T3 Code](https://www.anchorterminal.com/compare/earendil-pi-vs-t3-code.md)\n- [Emdash vs HarnessRouter](https://www.anchorterminal.com/compare/emdash-vs-harnessrouter.md)\n- [Emdash vs T3 Code](https://www.anchorterminal.com/compare/emdash-vs-t3-code.md)\n- [Gemini CLI vs HarnessRouter](https://www.anchorterminal.com/compare/gemini-cli-vs-harnessrouter.md)\n- [Gemini CLI vs T3 Code](https://www.anchorterminal.com/compare/gemini-cli-vs-t3-code.md)\n- [GitHub Copilot CLI vs HarnessRouter](https://www.anchorterminal.com/compare/github-copilot-cli-vs-harnessrouter.md)\n- [GitHub Copilot CLI vs T3 Code](https://www.anchorterminal.com/compare/github-copilot-cli-vs-t3-code.md)\n- [goose vs HarnessRouter](https://www.anchorterminal.com/compare/goose-vs-harnessrouter.md)\n- [goose vs T3 Code](https://www.anchorterminal.com/compare/goose-vs-t3-code.md)\n- [Harness² vs HarnessRouter](https://www.anchorterminal.com/compare/harness2-vs-harnessrouter.md)\n- [Harness² vs T3 Code](https://www.anchorterminal.com/compare/harness2-vs-t3-code.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 Letta](https://www.anchorterminal.com/compare/harnessrouter-vs-letta.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 Agents API](https://www.anchorterminal.com/compare/harnessrouter-vs-openai-agents-api.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 Orca](https://www.anchorterminal.com/compare/harnessrouter-vs-orca.md)\n- [HarnessRouter vs Paseo](https://www.anchorterminal.com/compare/harnessrouter-vs-paseo.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 Sculptor](https://www.anchorterminal.com/compare/harnessrouter-vs-sculptor.md)\n- [HarnessRouter vs Traycer](https://www.anchorterminal.com/compare/harnessrouter-vs-traycer.md)\n- [HarnessRouter vs Unstoppable](https://www.anchorterminal.com/compare/harnessrouter-vs-unstoppable.md)\n- [HarnessRouter vs Verdent](https://www.anchorterminal.com/compare/harnessrouter-vs-verdent.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 T3 Code](https://www.anchorterminal.com/compare/jules-vs-t3-code.md)\n- [Junie CLI vs T3 Code](https://www.anchorterminal.com/compare/junie-vs-t3-code.md)\n- [Kilo Code CLI vs T3 Code](https://www.anchorterminal.com/compare/kilo-code-cli-vs-t3-code.md)\n- [Kimi Code CLI vs T3 Code](https://www.anchorterminal.com/compare/kimi-code-cli-vs-t3-code.md)\n- [Kiro CLI vs T3 Code](https://www.anchorterminal.com/compare/kiro-cli-vs-t3-code.md)\n- [Letta vs T3 Code](https://www.anchorterminal.com/compare/letta-vs-t3-code.md)\n- [mini-swe-agent vs T3 Code](https://www.anchorterminal.com/compare/mini-swe-agent-vs-t3-code.md)\n- [MiniMax Code vs T3 Code](https://www.anchorterminal.com/compare/minimax-code-vs-t3-code.md)\n- [Mistral Vibe CLI vs T3 Code](https://www.anchorterminal.com/compare/mistral-vibe-cli-vs-t3-code.md)\n- [Muse Code vs T3 Code](https://www.anchorterminal.com/compare/muse-code-vs-t3-code.md)\n- [OpenAI Agents API vs T3 Code](https://www.anchorterminal.com/compare/openai-agents-api-vs-t3-code.md)\n- [OpenAI Codex vs T3 Code](https://www.anchorterminal.com/compare/openai-codex-vs-t3-code.md)\n- [OpenCode vs T3 Code](https://www.anchorterminal.com/compare/opencode-vs-t3-code.md)\n- [OpenHands vs T3 Code](https://www.anchorterminal.com/compare/openhands-vs-t3-code.md)\n- [Orca vs T3 Code](https://www.anchorterminal.com/compare/orca-vs-t3-code.md)\n- [Paseo vs T3 Code](https://www.anchorterminal.com/compare/paseo-vs-t3-code.md)\n- [Prime Agent vs T3 Code](https://www.anchorterminal.com/compare/prime-agent-vs-t3-code.md)\n- [Qoder CLI vs T3 Code](https://www.anchorterminal.com/compare/qoder-cli-vs-t3-code.md)\n- [Qwen Code vs T3 Code](https://www.anchorterminal.com/compare/qwen-code-vs-t3-code.md)\n- [Mirror CLI vs T3 Code](https://www.anchorterminal.com/compare/reflection-mirror-vs-t3-code.md)\n- [Rovo Dev CLI vs T3 Code](https://www.anchorterminal.com/compare/rovo-dev-cli-vs-t3-code.md)\n- [Sculptor vs T3 Code](https://www.anchorterminal.com/compare/sculptor-vs-t3-code.md)\n- [T3 Code vs Traycer](https://www.anchorterminal.com/compare/t3-code-vs-traycer.md)\n- [T3 Code vs Unstoppable](https://www.anchorterminal.com/compare/t3-code-vs-unstoppable.md)\n- [T3 Code vs Verdent](https://www.anchorterminal.com/compare/t3-code-vs-verdent.md)\n- [T3 Code vs Vibe-Trading](https://www.anchorterminal.com/compare/t3-code-vs-vibe-trading.md)\n- [T3 Code vs Warp (Warp Agent CLI and the Oz Agent API)](https://www.anchorterminal.com/compare/t3-code-vs-warp.md)\n- [Clawboo vs HarnessRouter](https://www.anchorterminal.com/compare/clawboo-vs-harnessrouter.md)\n- [Clawboo vs T3 Code](https://www.anchorterminal.com/compare/clawboo-vs-t3-code.md)\n- [CLI Manager vs HarnessRouter](https://www.anchorterminal.com/compare/cli-manager-vs-harnessrouter.md)\n- [CLI Manager vs T3 Code](https://www.anchorterminal.com/compare/cli-manager-vs-t3-code.md)\n- [Harness vs HarnessRouter](https://www.anchorterminal.com/compare/harness-autonomous-vs-harnessrouter.md)\n- [Harness vs T3 Code](https://www.anchorterminal.com/compare/harness-autonomous-vs-t3-code.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- [OpenMausBot vs T3 Code](https://www.anchorterminal.com/compare/openmausbot-vs-t3-code.md)\n- [Paperclip vs T3 Code](https://www.anchorterminal.com/compare/paperclip-vs-t3-code.md)\n- [Parallax vs T3 Code](https://www.anchorterminal.com/compare/parallax-agents-vs-t3-code.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": "2026-11-07", "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 T3 Code", "url": "" } ], "description": "T3 Code scores 51.9 (D) to HarnessRouter's 47.7 (D) for agent harnesses. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "HarnessRouter D 47.7", "T3 Code D 51.9", "scores" ], "h1": "HarnessRouter vs T3 Code", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/harnessrouter-vs-t3-code", "published": "2026-10-01", "section": "tools", "title": "HarnessRouter vs T3 Code for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/harnessrouter-vs-t3-code" }, "tokens": { "markdown": 6650, "slim": 2880 }, "version": 1 }