{ "data": { "a": { "slug": "gauge-cli", "name": "Gauge CLI", "vendor": "Gauge", "vendorUrl": "https://www.withgauge.com/agents/", "kind": "cli", "category": "agent-observability", "summary": "Gauge CLI runs real coding agents (Claude Code, Codex, Pi, OpenCode) against your skills, CLIs, SDKs, MCP servers and docs in Docker, records where they get stuck, and lets your agent test fixes before release.", "url": "https://www.anchorterminal.com/tools/gauge-cli", "markdownUrl": "https://www.anchorterminal.com/tools/gauge-cli.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gauge-cli.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gauge-cli.json", "dns": "gauge-cli.grade.anchorterminal.com", "repo": "https://github.com/gauge-sh/gauge-cli", "license": "MIT", "transports": [], "packages": [ { "registry": "npm", "name": "@withgauge/cli" } ], "auth": "none", "authNotes": "Local mode needs no Gauge account, only credentials for the agent under test (native Claude or Codex logins, or API keys). Hosted Gauge uses `gauge auth login`, with a device flow for remote terminals.", "pricing": "freemium", "pricingNotes": "The CLI and local mode are free and MIT-licensed; agent usage is billed by your provider or subscription. Hosted Gauge runs on workspace credits, whose prices weren't read (checked 2026-11-06).", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No payment protocol in the CLI or its README; hosted runs use workspace credits (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.withgauge.com/agents", "capabilities": [ "obs.evals" ], "tags": [ "open-source", "mit", "cli", "node", "docker", "telemetry", "new" ], "lastRelease": "2026-11-04", "graded": true, "anchor": { "graded": true, "score": 60.4, "grade": "C", "agentReady": false, "rank": 590, "ranked": true, "rankOf": 1354, "categoryRank": 13, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 82, "payments": 40, "reliability": 60, "schema": 60, "security": 55, "transparency": 53 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-06" }, "negative": 0, "verdict": "An open-source CLI that measures how coding agents get on with your product and checks fixes before you ship them, locally in Docker with no account. It's young and pre-1.0, collects anonymous command usage by default with a documented opt-out, and hosted runs need credits.", "bestFor": "Teams that build skills, CLIs, SDKs or MCP servers and want to see where coding agents get stuck with them, and to test fixes before release.", "strengths": [ "Runs Claude Code, Codex, Pi and OpenCode in fresh Docker sessions against working-tree or pre-release versions", "Local mode needs no Gauge account, only your existing agent credentials", "Dated changelog with six releases in about two weeks", "Instructions bundled in the CLI for coding agents, and -o json on read commands", "CI runs checks on every push and pull request" ], "weaknesses": [ "Collects anonymous command usage by default, with an opt-out", "Pre-1.0 and about two weeks old in this repository", "Docs, authenticated MCP servers and authenticated APIs need hosted Gauge and credits", "Hosted credit prices weren't found on the pages read" ], "agentNotes": [ "npm install -g @withgauge/cli, then gauge local runtime pull and gauge init --local in the project", "Run gauge install-skill so your coding agent finds the CLI's own instructions", "Set GAUGE_TELEMETRY_DISABLED=1 in CI if you don't want command usage collected", "Rebuild and pack an npm CLI or SDK before rerunning, so test sessions get the new tarball", "Keep .gauge/ private; it holds measurements and analyses" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 60.4 } ], "editorialScores": { "ergonomics": 75, "maintenance": 82, "payments": 40, "reliability": 60, "schema": 60, "security": 55, "transparency": 78 }, "provenanceScore": 27, "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": { "install": "npm install -g @withgauge/cli\ngauge local runtime pull\ngauge init --local\ngauge install-skill" }, "letme": { "capability": "https://letme.dev/obs.evals", "tool": "https://letme.dev/gauge-cli" }, "area": "developer", "provenance": { "legalEntity": "", "domain": "withgauge.com", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/gauge-sh/gauge-cli/blob/main/cli/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The npm package's author is Gauge \u003csupport@withgauge.com\u003e, its homepage agents.withgauge.com, and its repository field points at gauge-sh/gauge-cli. The licence names Gauge.", "Hosted Gauge's terms and privacy weren't read, and security.txt wasn't checked." ], "score": 27 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gauge-cli.json" }, "answer": "LangWatch scores 65.6 (B) on agent readiness against Gauge CLI's 60.4 (C), and leads in 5 of 7 scored categories. Gauge CLI leads on agent ergonomics.", "b": { "slug": "langwatch", "name": "LangWatch", "vendor": "Reasoning Engine B.V. (LangWatch)", "vendorUrl": "https://langwatch.ai", "kind": "http-api", "category": "agent-observability", "summary": "LangWatch is an open-source platform for tracing, evaluating and testing LLM applications and agents, with prompt management, datasets and an AI gateway. It runs hosted or self-hosted, with a REST API, SDKs, a CLI and an MCP server.", "url": "https://www.anchorterminal.com/tools/langwatch", "markdownUrl": "https://www.anchorterminal.com/tools/langwatch.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/langwatch.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/langwatch.json", "dns": "langwatch.grade.anchorterminal.com", "repo": "https://github.com/langwatch/langwatch", "license": "Apache 2.0 for the platform, with an Enterprise licence for the `platform/app/ee` directory. The SDKs and the MCP server are MIT", "transports": [ "http", "streamable-http", "sse", "stdio" ], "remoteUrl": "https://app.langwatch.ai", "packages": [ { "registry": "npm", "name": "langwatch" }, { "registry": "npm", "name": "@langwatch/mcp-server" }, { "registry": "pypi", "name": "langwatch" } ], "auth": "mixed", "authNotes": "A person signs up at app.langwatch.ai and creates keys under Settings, API Keys, with no review step. API keys (`sk-lw-`) go in `X-Auth-Token` or as a Bearer token. A personal key never exceeds its owner's permissions, a service key belongs to the organisation and only admins create one. Either can be All or Restricted to read or write per permission category, scoped to projects, teams or the organisation, given an expiry and revoked. Ingestion keys (`ik-lw-`) can only write traces to one project. The remote MCP server uses OAuth authorisation code with PKCE and dynamic client registration. The CLI logs in with a device code approved in a browser.", "pricing": "freemium", "pricingNotes": "The Developer plan is free with no card and includes 50,000 events a month, 2 users and 3 scenarios, so an agent can start without a contract once a person has signed up. Growth is 29 euros per core seat a month with 200,000 events, then 5 euros per 100,000 events and 3 euros per GB kept beyond the included retention. Enterprise is sold through sales. Instant Evals cost $0.0546 per million input tokens, with a $1 budget on unpaid organisations. The pricing page has a currency switch and we read the euro prices only. Self-hosting under Apache 2.0 is free with no volume cap, and an Enterprise licence is priced per seat (https://langwatch.ai/pricing, https://langwatch.ai/docs/pricing.md).", "priceSummary": "Freemium", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the OpenAPI document or the pricing page (checked 2026-10-09).", "endpoints": [] }, "toolCount": 110, "popularity": { "githubStars": 4925, "npmWeekly": 50105, "pypiWeekly": 87325, "asOf": "2026-10-09" }, "docsUrl": "https://langwatch.ai/docs/introduction", "llmsTxt": "https://langwatch.ai/docs/llms.txt", "openapi": "https://app.langwatch.ai/api/gateway/v1/openapi.json", "capabilities": [ "obs.traces", "obs.evals", "obs.prompts", "obs.datasets", "obs.gateway" ], "tags": [ "hosted", "freemium", "no-card", "open-source", "self-hosted", "mcp", "oauth", "llms-txt", "openapi", "opentelemetry", "python", "typescript", "go", "cli", "status-page", "eu-hosted" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 65.6, "grade": "B", "agentReady": false, "rank": 373, "ranked": true, "rankOf": 1354, "categoryRank": 6, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 90, "payments": 40, "reliability": 63, "schema": 87, "security": 71, "transparency": 76 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -4, "negativeNotes": [ "2026-08-19. Advisory GHSA-h25p-f8f6-2ccf, rated moderate. The standalone HTTP mode of `@langwatch/mcp-server` 0.7.0 to 1.0.0 authorised requests by session id alone and accepted an API key in the URL. Fixed in 2.0.0 on 7 August 2026 and flagged as a breaking change. The advisory says the default stdio mode and the hosted handler were never affected. Read on GitHub on 9 October (OSV doesn't hold it). A fixed Moderate more than two months old costs 1 in this run, down from 2 (https://github.com/langwatch/langwatch/security/advisories/GHSA-h25p-f8f6-2ccf)", "2026-10-15. The hosted MCP server retired its documented SSE transport. The docs had told remote clients to enter https://app.langwatch.ai/sse and said clients that speak the older SSE transport use it. The change (commit of 15 October, listed under Bug Fixes in the 3.21.0 changelog of 21 October) made `/sse` serve Streamable HTTP and removed `/messages`, and the same change rewrote the docs. No earlier notice was found in the changelogs or the public changelog, so -3 for a published behaviour changed for existing clients without notice (https://github.com/langwatch/langwatch/blob/main/CHANGELOG.md)" ], "verdict": "API keys can be limited to read or write per permission category, expire, and be revoked, and the remote MCP server uses OAuth with PKCE. The MCP server registers 110 tools with no read-only or destructive annotations, no platform API rate limit was found, and the hosted server dropped its documented SSE transport in the 21 October release without notice.", "bestFor": "Teams that want tracing, evaluations and simulated-user agent tests in one open-source product, hosted in the EU or self-hosted, and that drive it from a coding assistant through MCP or the CLI.", "strengths": [ "API keys take read or write per permission category, a project, team or organisation scope and an expiry. Ingestion keys can only write traces", "A public OpenAPI 3.1 document covers 406 operations and is served without a key, with llms.txt and a Markdown twin of every docs page", "Apache 2.0 platform with MIT SDKs and MCP server. Self-hosting has no volume cap, and every outbound call is documented with its off switch", "The free Developer plan needs no card and includes 50,000 events a month. Paid usage is published at 5 euros per 100,000 events", "Platform 3.21.0 shipped on 21 October 2026 and MCP server 3.0.0 on 30 October, with 19 platform releases dated since 3 August" ], "weaknesses": [ "The MCP server registers 110 tools, deletes and key creation among them, with no toolsets and no `readOnlyHint` or `destructiveHint` annotations in the source", "No request rate limit for the platform API was found in the reviewed documentation. Only three operations in the OpenAPI document declare a 429", "The hosted MCP server retired its documented SSE transport on 15 October 2026 with no notice found, so SSE-only clients pointed at `/sse` stopped working", "Scenarios was down on 13 days and Langy on 16 days between 3 August and 1 November 2026, the longest 9 hours 34 minutes", "The Terms of Service of 22 September 2026 say users will not access the platform through automated or non-human means, which the API and MCP server contradict" ], "agentNotes": [ "Create a Restricted key with read access to only the categories the task needs. A personal key with All permissions carries everything its owner can do", "Set both `LANGWATCH_API_KEY` and `LANGWATCH_PROJECT_ID` for the MCP server unless the key reaches only one project", "Connect remote MCP clients to `https://app.langwatch.ai/mcp` over Streamable HTTP. The older SSE transport was retired on 15 October 2026", "Call `discover_schema` before `search_traces` or `get_analytics`, and keep the default `digest` format. `json` returns the full raw trace", "Allowlist MCP tools in the client. All 110 load by default, among them `platform_create_api_key` and the delete tools", "Follow `next_cursor` until it is null on list endpoints. A full page does not mean more rows exist" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.6 } ], "editorialScores": { "ergonomics": 67, "maintenance": 90, "payments": 40, "reliability": 63, "schema": 87, "security": 71, "transparency": 73 }, "provenanceScore": 79, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install -g langwatch", "http": "curl https://app.langwatch.ai/api/gateway/v1/openapi.json", "claudeCode": "claude mcp add langwatch --env LANGWATCH_API_KEY=sk-lw-... --env LANGWATCH_PROJECT_ID=your-project-id -- npx -y @langwatch/mcp-server", "config": { "mcpServers": { "langwatch": { "args": [ "-y", "@langwatch/mcp-server" ], "command": "npx", "env": { "LANGWATCH_API_KEY": "sk-lw-...", "LANGWATCH_PROJECT_ID": "your-project-id" } } } } }, "letme": { "capability": "https://letme.dev/obs.traces", "tool": "https://letme.dev/langwatch" }, "area": "developer", "unitPrices": [ { "item": "Instant Evals, judge input tokens", "unit": "1m-tokens", "usd": 0.0546, "note": "Output is free. Unpaid organisations have a $1 budget in total" } ], "provenance": { "legalEntity": "Reasoning Engine B.V. (doing business as LangWatch)", "domain": "langwatch.ai", "domainRegistered": "2023-09-17", "endpointOnVendorDomain": true, "terms": "https://langwatch.ai/legal/terms-conditions", "privacy": "https://langwatch.ai/legal/privacy-policy", "statusPage": "https://status.langwatch.ai", "changelog": "https://langwatch.ai/changelog", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The privacy policy (last updated 29 September 2026) applies to Reasoning Engine B.V., doing business as LangWatch, and covers the website and the Cloud Service. The Terms of Service (last updated 22 September 2026) cover the platform and the on-premise product.", "The terms page names the entity as Reasoning Engines B.V. in its heading and Reasoning Engine B.V. in its definitions, gives Singel 126, Amsterdam as the registered office and Herengracht 551, Amsterdam as the contact address. The site footer reads LangWatch B.V.", "The API, the hosted MCP server and the OpenAPI document are served from app.langwatch.ai. Hosted services for self-hosted installs with a licence use connect.langwatch.ai and gateway.langwatch.ai.", "https://langwatch.ai/.well-known/security.txt returns the website's HTML shell, not a security.txt file. SECURITY.md in the repository gives security@langwatch.ai and GitHub private reporting.", "RDAP for langwatch.ai gives a registration date of 2023-09-17 and GoDaddy.com, LLC as registrar.", "The trust report and sub-processor list are on app.eu.vanta.com, whose robots.txt disallows every path, so we did not read them." ], "score": 79 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/langwatch.json", "live": { "slug": "langwatch", "probe": { "target": "https://app.langwatch.ai", "method": "get", "lastAt": "2026-11-06T09:47:35.14363005Z", "lastOk": true, "lastStatus": 200, "lastMs": 109, "authRequired": false, "uptime24h": 100, "uptime30d": 99.99, "p50ms24h": 119, "p95ms24h": 241, "samples24h": 221, "samples30d": 6963, "days": [ { "date": "2026-10-09", "probes": 169, "ok": 169 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "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": 247 }, { "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 } ] }, "vendorStatus": { "page": "https://status.langwatch.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-06T05:41:55.431286623Z" }, "versions": [ { "registry": "github", "name": "langwatch/langwatch", "version": "langwatch-3.23.0", "released": "2026-11-05", "seenAt": "2026-11-05T21:42:15.416458883Z" }, { "registry": "npm", "name": "@langwatch/mcp-server", "version": "3.1.0", "seenAt": "2026-11-05T21:42:13.838582822Z" }, { "registry": "npm", "name": "langwatch", "version": "2.2.0", "seenAt": "2026-11-05T21:42:12.941772642Z" }, { "registry": "pypi", "name": "langwatch", "version": "1.4.0", "released": "2026-09-06", "seenAt": "2026-11-05T21:42:15.158373499Z" } ], "githubStars": 5014, "npmWeekly": 48896, "pypiWeekly": 82928, "securityTxt": { "url": "https://langwatch.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-05T15:56:24.057074797Z" }, "llmsTxt": { "url": "https://langwatch.ai/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-05T15:26:22.068597127Z" }, "domain": { "domain": "langwatch.ai", "registered": "2023-09-17", "source": "https://rdap.identitydigital.services/rdap/domain/langwatch.ai", "checkedAt": "2026-11-01T14:23:21.560670398Z" }, "pages": [ { "url": "https://langwatch.ai/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-05T12:57:44.708609423Z", "changedAt": "2026-10-29T05:09:34.124865709Z", "fingerprint": "f0f62aa8633f" }, { "url": "https://langwatch.ai/docs/pricing.md", "kind": "pricing", "status": 200, "checkedAt": "2026-11-05T12:57:46.797303694Z", "changedAt": "2026-10-31T06:14:45.340096601Z", "fingerprint": "1f381ce33456" }, { "url": "https://langwatch.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-05T12:57:52.795333025Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "5ca650ce8d8f" }, { "url": "https://langwatch.ai/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-05T12:57:48.870721444Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a70eff21db6c" }, { "url": "https://langwatch.ai/legal/terms-conditions", "kind": "terms", "status": 200, "checkedAt": "2026-11-05T12:57:50.795110537Z", "changedAt": "2026-11-04T08:26:27.518584135Z", "fingerprint": "130cb0782b0f" } ], "github": { "repo": "langwatch/langwatch", "checkedAt": "2026-11-02T08:59:57.075627443Z", "stars": 5004, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T08:55:35Z", "openIssues": 157, "openPRs": 242, "issuesOpened90d": 399, "issuesClosed90d": 348, "prsMerged90d": 1269, "ci": { "branch": "main", "runs": 50, "success": 44, "failure": 0, "other": 6, "latest": "success", "latestAt": "2026-11-02T08:55:59Z" }, "advisories": [ { "ghsa": "GHSA-h25p-f8f6-2ccf", "severity": "medium", "published": "2026-08-19T09:34:31Z" } ], "replies": { "sampled": 25, "unanswered": 21, "medianDays": 0.1 } }, "updatedAt": "2026-11-06T09:47:35.14363005Z" } }, "edges": [ { "by": 27, "category": "schema", "leads": "langwatch", "name": "Schema \u0026 documentation", "reasons": { "a": "CLI reading. No machine-readable contract, -o json on read commands (10 of 25). No llms.txt; instructions bundled in the CLI for agents (5). The README says what it finds and when local or hosted fits (16 of 20). Commands with help text; typed flags (9 of 15). Worked examples, no error reference (8 of 15). Dated changelog and semver tags (12 of 15). 10 + 5 + 16 + 9 + 8 + 12 = 60.", "b": "A public OpenAPI 3.1 document of 281 paths and 406 operations on 1 November, served without a key, and typed zod inputs on every MCP tool (25). llms.txt and a Markdown twin of each docs page (10). Every operation has a summary or description, and MCP descriptions say when to pick a tool, for example `run_query` for counts and rates and `discover_schema` before a search. 192 operations carry no tag (16). 910 `enum` keys in the document, with trace filters still accepted as a free-form map alongside the query language (12). Docs pages carry request examples, and the gateway error list gives 34 codes with cause and remedy. Most platform operations document errors only as an `error` and `message` string pair (11). Dated public changelog, release notes per package and a document version of 1.0.0, with `/api/v1` paths mixed among unversioned ones (13)." }, "scores": { "a": 60, "b": 87 } }, { "by": 23, "category": "transparency", "leads": "langwatch", "name": "Transparency \u0026 trust", "reasons": { "a": "MIT (30). Local data stays in .gauge/ and telemetry fields are listed; hosted data handling wasn't read (18 of 30). Dated changelog, no deprecation policy (10 of 20). Telemetry on by default, disclosed with an opt-out (20). 30 + 18 + 10 + 20 = 78.", "b": "Apache 2.0 platform with the `platform/app/ee` directory under a separate Enterprise licence, and MIT SDKs and MCP server (27). The privacy policy of 29 September 2026 names its processors and the retention docs are detailed, but the documents disagree in places. The pricing page says 30-day retention is included where the docs say 49 days, the terms describe a 14-day free trial where the pricing page says free forever, and the terms give two addresses and two spellings of the entity. The terms also grant LangWatch a perpetual licence to use client data to improve the platform, while saying it will not train on it (18). Deprecated endpoints are marked in the OpenAPI document and the docs, and breaking changes are flagged in the changelogs, but no removal dates or notice period were found (10). EU hosting on AWS is stated and processors are named in the privacy policy. Self-hosted telemetry is documented connection by connection with an off switch. The public sub-processor list is on a host we could not read (18)." }, "scores": { "a": 53, "b": 76 } }, { "by": 16, "category": "security", "leads": "langwatch", "name": "Security \u0026 auth", "reasons": { "a": "Local tool. Agent credentials stay on your machine in local mode; hosted login with a device flow (20 of 30). Test agents run in fresh Docker sessions with injected inputs, and the gateway brokers credentials in hosted mode (12 of 20). Agents under test read your product's docs and outputs, with no prompt-injection guidance (5 of 15). Local transcripts and SQLite evidence per run (10 of 15). No security policy found (8 of 20). 20 + 12 + 5 + 10 + 8 = 55.", "b": "OAuth authorisation code with PKCE and dynamic client registration on the remote MCP server, and API keys with read or write per category, a project, team or organisation scope, expiry and revocation, plus write-only ingestion keys. The `apiKey` query parameter on `/sse` was removed in MCP server 2.0.0 (30). Restricted keys and lite members give read-only access, but no tool asks for confirmation before a delete and the MCP tools carry no annotations (14). Traces hold whatever the application logged, and we found no prompt-injection guidance for agents reading them (3). The audit log is Enterprise only and leaves out sign-ins and reads of product data. The key list shows a last-used date (9). SECURITY.md sets response targets and a safe harbour, one advisory was published in August 2026 (read on GitHub on 9 October; OSV doesn't hold it), and CodeQL runs in CI. ISO 27001 and a CREST penetration test are stated, with reports on request. No security.txt and no bug bounty found (15)." }, "scores": { "a": 55, "b": 71 } }, { "by": 8, "category": "ergonomics", "leads": "gauge-cli", "name": "Agent ergonomics", "reasons": { "a": "CLI reading for an agent driving it. Bundled instructions match the installed version, and output is filterable with -o json (20 of 25). Run summaries and Findings with queryable fields (15 of 20). Errors not documented as a reference (10 of 20). Reruns from checkpoints and a recheck command with a confirm step (15 of 20). Four commands to start, Node only (15 of 15). 20 + 15 + 10 + 15 + 15 = 75.", "b": "The MCP server registers 110 tools in the 3.0.0 source, with no toolsets or dynamic loading found. Trace tools return a compact digest by default, which earns 3 back (8). Cursor paging with `next_cursor`, `limit` and `pageSize`, filters, a projection DSL on trace search and a `digest` or `json` format switch (20). Gateway errors carry a stable code, tips, a docs link and a `fault` field, and the MCP client passes them on. Platform errors are plainer (16). No `readOnlyHint` or `destructiveHint` in the MCP source. Idempotency exists for evaluations and ingested events, and several delete tools archive instead of removing (8). Python, TypeScript and Go SDKs, a CLI, and few required parameters (15)." }, "scores": { "a": 75, "b": 67 } }, { "by": 8, "category": "maintenance", "leads": "langwatch", "name": "Maintenance \u0026 community", "reasons": { "a": "CLI 0.28.0 on 4 November 2026 (30). Six releases in 90 days (20). Issues and pull requests weren't read; a support address and issue tracker are published (12 of 25). Current official package (15). CI on push and pull request (5 of 10, results not read). 30 + 20 + 12 + 15 + 5 = 82.", "b": "Platform 3.21.0 on 21 October 2026, TypeScript SDK 2.1.0 and MCP server 3.0.0 on 30 October (30). 19 platform releases dated since 3 August in CHANGELOG.md, and weekly dated entries on the public changelog to 25 October (20). Per the 9 October check, not re-read on 1 November (GitHub's pages refuse our reader), 52 open issues and 222 open pull requests, with new issues labelled and prioritised by maintainers within a week, and support by email, Discord and GitHub (17). Current official SDKs, Python 1.4.0 on 6 September, TypeScript 2.1.0 on 30 October and Go 1.0.0 on 9 September. The MCP server is still not in the official MCP registry (15). CI workflows for the app, each SDK and the MCP server, CodeQL and dependency bumps in the changelog, with fixes for dependency alerts in October. We could not confirm the pass state (8)." }, "scores": { "a": 82, "b": 90 } } ], "facts": [ { "a": "cli", "b": "HTTP API", "name": "Kind" }, { "a": "Gauge", "b": "Reasoning Engine B.V. (LangWatch)", "name": "Vendor" }, { "a": "no (local only)", "b": "https://app.langwatch.ai", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP, Streamable HTTP, SSE (legacy), stdio", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "not published", "b": "$0.0546 per 1M tokens", "name": "Price for evaluations" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Apache 2.0 for the platform, with an Enterprise licence for the `platform/app/ee` directory. The SDKs and the MCP server are MIT", "name": "Licence" }, { "a": "none", "b": "110", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-04", "b": "2026-10-30", "name": "Last release" }, { "a": "no document linked", "b": "2026-09-22", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-09-29", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not read yet", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "4.9k stars, 50k npm/wk, 87k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "LangWatch scores 65.6 (B) on agent readiness against Gauge CLI's 60.4 (C), and leads in 5 of 7 scored categories. Gauge CLI leads on agent ergonomics.", "question": "Which is better for AI agents, Gauge CLI or LangWatch?" }, { "answer": "No hosted endpoint is listed for Gauge CLI. LangWatch has a hosted endpoint at https://app.langwatch.ai.", "question": "Can an agent call Gauge CLI and LangWatch without installing anything?" }, { "answer": "Yes. Gauge CLI is open source (MIT). LangWatch is open source (Apache 2.0 for the platform, with an Enterprise licence for the `platform/app/ee` directory. The SDKs and the MCP server are MIT).", "question": "Are Gauge CLI and LangWatch open source?" } ], "goodFor": [ { "aheadOn": [ "Agent ergonomics, 75 against 67" ], "also": [ "No key needed to call it", "No incidents deducted, where LangWatch loses 4 points for them" ], "goodFor": "Teams that build skills, CLIs, SDKs or MCP servers and want to see where coding agents get stuck with them, and to test fixes before release.", "slug": "gauge-cli", "watchFor": "Collects anonymous command usage by default, with an opt-out" }, { "aheadOn": [ "Schema \u0026 documentation, 87 against 60", "Security \u0026 auth, 71 against 55", "Maintenance \u0026 community, 90 against 82", "Transparency \u0026 trust, 76 against 53" ], "also": [ "A hosted endpoint, with nothing to install", "Runs on your own machine", "Free to start without a card" ], "goodFor": "Teams that want tracing, evaluations and simulated-user agent tests in one open-source product, hosted in the EU or self-hosted, and that drive it from a coding assistant through MCP or the CLI.", "slug": "langwatch", "watchFor": "The MCP server registers 110 tools, deletes and key creation among them, with no toolsets and no `readOnlyHint` or `destructiveHint` annotations in the source" } ], "history": { "gauge-cli": null, "langwatch": [ { "causes": [ "correction", "event" ], "date": "2026-11-01", "delta": 0, "from": 65.6, "fromGrade": "B", "to": 65.6, "toGrade": "B" }, { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0.1, "from": 65.5, "fromGrade": "B", "to": 65.6, "toGrade": "B" } ] }, "job": { "capability": "obs.evals", "name": "Evaluations" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-tree-vs-langwatch.json", "title": "Agent Tree vs LangWatch", "url": "https://www.anchorterminal.com/compare/agent-tree-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/agents-tree-vs-langwatch.json", "title": "agents-tree vs LangWatch", "url": "https://www.anchorterminal.com/compare/agents-tree-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/arize-phoenix-vs-langwatch.json", "title": "Arize Phoenix vs LangWatch", "url": "https://www.anchorterminal.com/compare/arize-phoenix-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/baserun-vs-langwatch.json", "title": "Baserun vs LangWatch", "url": "https://www.anchorterminal.com/compare/baserun-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/botgauge-vs-langwatch.json", "title": "BotGauge vs LangWatch", "url": "https://www.anchorterminal.com/compare/botgauge-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/braintrust-vs-langwatch.json", "title": "Braintrust API + MCP vs LangWatch", "url": "https://www.anchorterminal.com/compare/braintrust-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/galileo-vs-langwatch.json", "title": "Galileo API + MCP vs LangWatch", "url": "https://www.anchorterminal.com/compare/galileo-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/helicone-vs-langwatch.json", "title": "Helicone AI Gateway + MCP vs LangWatch", "url": "https://www.anchorterminal.com/compare/helicone-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/honeyhive-vs-langwatch.json", "title": "HoneyHive vs LangWatch", "url": "https://www.anchorterminal.com/compare/honeyhive-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/laminar-vs-langwatch.json", "title": "Laminar API + MCP vs LangWatch", "url": "https://www.anchorterminal.com/compare/laminar-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/langfuse-vs-langwatch.json", "title": "Langfuse API + MCP vs LangWatch", "url": "https://www.anchorterminal.com/compare/langfuse-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/langsmith-vs-langwatch.json", "title": "LangSmith API + MCP vs LangWatch", "url": "https://www.anchorterminal.com/compare/langsmith-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/langwatch-vs-mlflow-tracing.json", "title": "LangWatch vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/langwatch-vs-mlflow-tracing" }, { "json": "https://www.anchorterminal.com/compare/langwatch-vs-navige.json", "title": "LangWatch vs Navige", "url": "https://www.anchorterminal.com/compare/langwatch-vs-navige" }, { "json": "https://www.anchorterminal.com/compare/langwatch-vs-opik.json", "title": "LangWatch vs Opik API + MCP", "url": "https://www.anchorterminal.com/compare/langwatch-vs-opik" }, { "json": "https://www.anchorterminal.com/compare/langwatch-vs-overmind.json", "title": "LangWatch vs Overmind", "url": "https://www.anchorterminal.com/compare/langwatch-vs-overmind" }, { "json": "https://www.anchorterminal.com/compare/langwatch-vs-prefactor.json", "title": "LangWatch vs Prefactor", "url": "https://www.anchorterminal.com/compare/langwatch-vs-prefactor" }, { "json": "https://www.anchorterminal.com/compare/langwatch-vs-pydantic-logfire.json", "title": "LangWatch vs Pydantic Logfire", "url": "https://www.anchorterminal.com/compare/langwatch-vs-pydantic-logfire" }, { "json": "https://www.anchorterminal.com/compare/langwatch-vs-respan.json", "title": "LangWatch vs Respan API + MCP", "url": "https://www.anchorterminal.com/compare/langwatch-vs-respan" }, { "json": "https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave.json", "title": "LangWatch vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave" }, { "json": "https://www.anchorterminal.com/compare/arize-phoenix-vs-gauge-cli.json", "title": "Arize Phoenix vs Gauge CLI", "url": "https://www.anchorterminal.com/compare/arize-phoenix-vs-gauge-cli" }, { "json": "https://www.anchorterminal.com/compare/baserun-vs-gauge-cli.json", "title": "Baserun vs Gauge CLI", "url": "https://www.anchorterminal.com/compare/baserun-vs-gauge-cli" }, { "json": "https://www.anchorterminal.com/compare/botgauge-vs-gauge-cli.json", "title": "BotGauge vs Gauge CLI", "url": "https://www.anchorterminal.com/compare/botgauge-vs-gauge-cli" }, { "json": "https://www.anchorterminal.com/compare/braintrust-vs-gauge-cli.json", "title": "Braintrust API + MCP vs Gauge CLI", "url": "https://www.anchorterminal.com/compare/braintrust-vs-gauge-cli" }, { "json": "https://www.anchorterminal.com/compare/deepeval-vs-gauge-cli.json", "title": "DeepEval vs Gauge CLI", "url": "https://www.anchorterminal.com/compare/deepeval-vs-gauge-cli" }, { "json": "https://www.anchorterminal.com/compare/deepeval-vs-langwatch.json", "title": "DeepEval vs LangWatch", "url": "https://www.anchorterminal.com/compare/deepeval-vs-langwatch" }, { "json": "https://www.anchorterminal.com/compare/galileo-vs-gauge-cli.json", "title": "Galileo API + MCP vs Gauge CLI", "url": "https://www.anchorterminal.com/compare/galileo-vs-gauge-cli" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-helicone.json", "title": "Gauge CLI vs Helicone AI Gateway + MCP", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-helicone" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-honeyhive.json", "title": "Gauge CLI vs HoneyHive", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-honeyhive" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-laminar.json", "title": "Gauge CLI vs Laminar API + MCP", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-laminar" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-langfuse.json", "title": "Gauge CLI vs Langfuse API + MCP", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-langfuse" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-langsmith.json", "title": "Gauge CLI vs LangSmith API + MCP", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-langsmith" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-mlflow-tracing.json", "title": "Gauge CLI vs MLflow Tracing", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-mlflow-tracing" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-opik.json", "title": "Gauge CLI vs Opik API + MCP", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-opik" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-overmind.json", "title": "Gauge CLI vs Overmind", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-overmind" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-prefactor.json", "title": "Gauge CLI vs Prefactor", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-prefactor" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-pydantic-logfire.json", "title": "Gauge CLI vs Pydantic Logfire", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-pydantic-logfire" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-respan.json", "title": "Gauge CLI vs Respan API + MCP", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-respan" }, { "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-wandb-weave.json", "title": "Gauge CLI vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-wandb-weave" } ], "panel": null, "scores": [ { "by": 3, "edge": "langwatch", "gauge-cli": 60, "key": "reliability", "langwatch": 63, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 27, "edge": "langwatch", "gauge-cli": 60, "key": "schema", "langwatch": 87, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 8, "edge": "gauge-cli", "gauge-cli": 75, "key": "ergonomics", "langwatch": 67, "name": "Agent ergonomics", "weight": 13 }, { "by": 16, "edge": "langwatch", "gauge-cli": 55, "key": "security", "langwatch": 71, "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "edge": "", "gauge-cli": 40, "key": "payments", "langwatch": 40, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 8, "edge": "langwatch", "gauge-cli": 82, "key": "maintenance", "langwatch": 90, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 23, "edge": "langwatch", "gauge-cli": 53, "key": "transparency", "langwatch": 76, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "LangWatch scores 65.6 (B) on agent readiness against Gauge CLI's 60.4 (C), and leads in 5 of 7 scored categories. Gauge CLI leads on agent ergonomics. Both do evaluations.", "tasks": null, "tutorials": [], "verdicts": { "gauge-cli": "An open-source CLI that measures how coding agents get on with your product and checks fixes before you ship them, locally in Docker with no account. It's young and pre-1.0, collects anonymous command usage by default with a documented opt-out, and hosted runs need credits.", "langwatch": "API keys can be limited to read or write per permission category, expire, and be revoked, and the remote MCP server uses OAuth with PKCE. The MCP server registers 110 tools with no read-only or destructive annotations, no platform API rate limit was found, and the hosted server dropped its documented SSE transport in the 21 October release without notice." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/gauge-cli-vs-langwatch", "json": "https://www.anchorterminal.com/compare/gauge-cli-vs-langwatch.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gauge-cli-vs-langwatch.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/gauge-cli-vs-langwatch.min.md" }, "markdown": "LangWatch scores 65.6 (B) on agent readiness against Gauge CLI's 60.4 (C), and leads in 5 of 7 scored categories. Gauge CLI leads on agent ergonomics. Both do evaluations.\n\n- Gauge CLI: grade C, 60.4/100, rank #590 of 1354. Markdown https://www.anchorterminal.com/tools/gauge-cli.md · JSON https://www.anchorterminal.com/api/v1/tools/gauge-cli.json\n- LangWatch: grade B, 65.6/100, rank #373 of 1354. Markdown https://www.anchorterminal.com/tools/langwatch.md · JSON https://www.anchorterminal.com/api/v1/tools/langwatch.json\n- Best agent tracing, monitoring and evaluation tools: https://www.anchorterminal.com/best/agent-observability/index.md\n- All 250 evals comparisons: https://www.anchorterminal.com/compare/agent-observability/index.md\n\n## Which one, for what\n\n### Gauge CLI (C)\n\nGood for: Teams that build skills, CLIs, SDKs or MCP servers and want to see where coding agents get stuck with them, and to test fixes before release.\n\nAhead on:\n- Agent ergonomics, 75 against 67\n\nAlso in its favour:\n- No key needed to call it\n- No incidents deducted, where LangWatch loses 4 points for them\n\nWatch for: Collects anonymous command usage by default, with an opt-out\n\n### LangWatch (B)\n\nGood for: Teams that want tracing, evaluations and simulated-user agent tests in one open-source product, hosted in the EU or self-hosted, and that drive it from a coding assistant through MCP or the CLI.\n\nAhead on:\n- Schema \u0026 documentation, 87 against 60\n- Security \u0026 auth, 71 against 55\n- Maintenance \u0026 community, 90 against 82\n- Transparency \u0026 trust, 76 against 53\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: The MCP server registers 110 tools, deletes and key creation among them, with no toolsets and no `readOnlyHint` or `destructiveHint` annotations in the source\n\n\n## Why the edge\n\n### Schema \u0026 documentation: LangWatch +27\n\n- Gauge CLI (60): CLI reading. No machine-readable contract, -o json on read commands (10 of 25). No llms.txt; instructions bundled in the CLI for agents (5). The README says what it finds and when local or hosted fits (16 of 20). Commands with help text; typed flags (9 of 15). Worked examples, no error reference (8 of 15). Dated changelog and semver tags (12 of 15). 10 + 5 + 16 + 9 + 8 + 12 = 60.\n- LangWatch (87): A public OpenAPI 3.1 document of 281 paths and 406 operations on 1 November, served without a key, and typed zod inputs on every MCP tool (25). llms.txt and a Markdown twin of each docs page (10). Every operation has a summary or description, and MCP descriptions say when to pick a tool, for example `run_query` for counts and rates and `discover_schema` before a search. 192 operations carry no tag (16). 910 `enum` keys in the document, with trace filters still accepted as a free-form map alongside the query language (12). Docs pages carry request examples, and the gateway error list gives 34 codes with cause and remedy. Most platform operations document errors only as an `error` and `message` string pair (11). Dated public changelog, release notes per package and a document version of 1.0.0, with `/api/v1` paths mixed among unversioned ones (13).\n\n### Transparency \u0026 trust: LangWatch +23\n\n- Gauge CLI (53): MIT (30). Local data stays in .gauge/ and telemetry fields are listed; hosted data handling wasn't read (18 of 30). Dated changelog, no deprecation policy (10 of 20). Telemetry on by default, disclosed with an opt-out (20). 30 + 18 + 10 + 20 = 78.\n- LangWatch (76): Apache 2.0 platform with the `platform/app/ee` directory under a separate Enterprise licence, and MIT SDKs and MCP server (27). The privacy policy of 29 September 2026 names its processors and the retention docs are detailed, but the documents disagree in places. The pricing page says 30-day retention is included where the docs say 49 days, the terms describe a 14-day free trial where the pricing page says free forever, and the terms give two addresses and two spellings of the entity. The terms also grant LangWatch a perpetual licence to use client data to improve the platform, while saying it will not train on it (18). Deprecated endpoints are marked in the OpenAPI document and the docs, and breaking changes are flagged in the changelogs, but no removal dates or notice period were found (10). EU hosting on AWS is stated and processors are named in the privacy policy. Self-hosted telemetry is documented connection by connection with an off switch. The public sub-processor list is on a host we could not read (18).\n\n### Security \u0026 auth: LangWatch +16\n\n- Gauge CLI (55): Local tool. Agent credentials stay on your machine in local mode; hosted login with a device flow (20 of 30). Test agents run in fresh Docker sessions with injected inputs, and the gateway brokers credentials in hosted mode (12 of 20). Agents under test read your product's docs and outputs, with no prompt-injection guidance (5 of 15). Local transcripts and SQLite evidence per run (10 of 15). No security policy found (8 of 20). 20 + 12 + 5 + 10 + 8 = 55.\n- LangWatch (71): OAuth authorisation code with PKCE and dynamic client registration on the remote MCP server, and API keys with read or write per category, a project, team or organisation scope, expiry and revocation, plus write-only ingestion keys. The `apiKey` query parameter on `/sse` was removed in MCP server 2.0.0 (30). Restricted keys and lite members give read-only access, but no tool asks for confirmation before a delete and the MCP tools carry no annotations (14). Traces hold whatever the application logged, and we found no prompt-injection guidance for agents reading them (3). The audit log is Enterprise only and leaves out sign-ins and reads of product data. The key list shows a last-used date (9). SECURITY.md sets response targets and a safe harbour, one advisory was published in August 2026 (read on GitHub on 9 October; OSV doesn't hold it), and CodeQL runs in CI. ISO 27001 and a CREST penetration test are stated, with reports on request. No security.txt and no bug bounty found (15).\n\n### Agent ergonomics: Gauge CLI +8\n\n- Gauge CLI (75): CLI reading for an agent driving it. Bundled instructions match the installed version, and output is filterable with -o json (20 of 25). Run summaries and Findings with queryable fields (15 of 20). Errors not documented as a reference (10 of 20). Reruns from checkpoints and a recheck command with a confirm step (15 of 20). Four commands to start, Node only (15 of 15). 20 + 15 + 10 + 15 + 15 = 75.\n- LangWatch (67): The MCP server registers 110 tools in the 3.0.0 source, with no toolsets or dynamic loading found. Trace tools return a compact digest by default, which earns 3 back (8). Cursor paging with `next_cursor`, `limit` and `pageSize`, filters, a projection DSL on trace search and a `digest` or `json` format switch (20). Gateway errors carry a stable code, tips, a docs link and a `fault` field, and the MCP client passes them on. Platform errors are plainer (16). No `readOnlyHint` or `destructiveHint` in the MCP source. Idempotency exists for evaluations and ingested events, and several delete tools archive instead of removing (8). Python, TypeScript and Go SDKs, a CLI, and few required parameters (15).\n\n### Maintenance \u0026 community: LangWatch +8\n\n- Gauge CLI (82): CLI 0.28.0 on 4 November 2026 (30). Six releases in 90 days (20). Issues and pull requests weren't read; a support address and issue tracker are published (12 of 25). Current official package (15). CI on push and pull request (5 of 10, results not read). 30 + 20 + 12 + 15 + 5 = 82.\n- LangWatch (90): Platform 3.21.0 on 21 October 2026, TypeScript SDK 2.1.0 and MCP server 3.0.0 on 30 October (30). 19 platform releases dated since 3 August in CHANGELOG.md, and weekly dated entries on the public changelog to 25 October (20). Per the 9 October check, not re-read on 1 November (GitHub's pages refuse our reader), 52 open issues and 222 open pull requests, with new issues labelled and prioritised by maintainers within a week, and support by email, Discord and GitHub (17). Current official SDKs, Python 1.4.0 on 6 September, TypeScript 2.1.0 on 30 October and Go 1.0.0 on 9 September. The MCP server is still not in the official MCP registry (15). CI workflows for the app, each SDK and the MCP server, CodeQL and dependency bumps in the changelog, with fixes for dependency alerts in October. We could not confirm the pass state (8).\n\n## Score by category\n\n| Category | Weight | Gauge CLI | LangWatch | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 60 | 63 | LangWatch +3 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 60 | 87 | LangWatch +27 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 67 | Gauge CLI +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 55 | 71 | LangWatch +16 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 40 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 90 | LangWatch +8 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 53 | 76 | LangWatch +23 |\n| Negative events | ≤15 | 0 | -4 | |\n| **Total** | | **60.4 · C** | **65.6 · B** | |\n\n## Facts side by side\n\n| Fact | Gauge CLI | LangWatch |\n| --- | --- | --- |\n| Kind | cli | HTTP API |\n| Vendor | Gauge | Reasoning Engine B.V. (LangWatch) |\n| Hosted endpoint | no (local only) | `https://app.langwatch.ai` |\n| Transports | | HTTP, Streamable HTTP, SSE (legacy), stdio |\n| Auth | None | OAuth or key |\n| Pricing | Freemium | Freemium |\n| Price for evaluations | not published | $0.0546 per 1M tokens |\n| x402 | no | no |\n| Licence | MIT | Apache 2.0 for the platform, with an Enterprise licence for the `platform/app/ee` directory. The SDKs and the MCP server are MIT |\n| Tools exposed | none | 110 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-11-04 | 2026-10-30 |\n| Terms last updated | no document linked | 2026-09-22 |\n| Privacy policy last updated | no document linked | 2026-09-29 |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | yes |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | yes |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | none | 4.9k stars, 50k npm/wk, 87k PyPI/wk |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### Gauge CLI\n\nNo score change since it was listed.\n\n### LangWatch\n\n- no change on 1 November 2026: correction, negative event\n- +0.1 on 28 October 2026: new evidence\n\n## Verdicts\n\n**Gauge CLI.** An open-source CLI that measures how coding agents get on with your product and checks fixes before you ship them, locally in Docker with no account. It's young and pre-1.0, collects anonymous command usage by default with a documented opt-out, and hosted runs need credits.\n\n**LangWatch.** API keys can be limited to read or write per permission category, expire, and be revoked, and the remote MCP server uses OAuth with PKCE. The MCP server registers 110 tools with no read-only or destructive annotations, no platform API rate limit was found, and the hosted server dropped its documented SSE transport in the 21 October release without notice.\n\n## Before you call either\n\n### Gauge CLI\n\n1. npm install -g @withgauge/cli, then gauge local runtime pull and gauge init --local in the project\n2. Run gauge install-skill so your coding agent finds the CLI's own instructions\n3. Set GAUGE_TELEMETRY_DISABLED=1 in CI if you don't want command usage collected\n4. Rebuild and pack an npm CLI or SDK before rerunning, so test sessions get the new tarball\n5. Keep .gauge/ private; it holds measurements and analyses\n\n### LangWatch\n\n1. Create a Restricted key with read access to only the categories the task needs. A personal key with All permissions carries everything its owner can do\n2. Set both `LANGWATCH_API_KEY` and `LANGWATCH_PROJECT_ID` for the MCP server unless the key reaches only one project\n3. Connect remote MCP clients to `https://app.langwatch.ai/mcp` over Streamable HTTP. The older SSE transport was retired on 15 October 2026\n4. Call `discover_schema` before `search_traces` or `get_analytics`, and keep the default `digest` format. `json` returns the full raw trace\n5. Allowlist MCP tools in the client. All 110 load by default, among them `platform_create_api_key` and the delete tools\n6. Follow `next_cursor` until it is null on list endpoints. A full page does not mean more rows exist\n\n## Questions\n\n### Which is better for AI agents, Gauge CLI or LangWatch?\n\nLangWatch scores 65.6 (B) on agent readiness against Gauge CLI's 60.4 (C), and leads in 5 of 7 scored categories. Gauge CLI leads on agent ergonomics.\n\n### Can an agent call Gauge CLI and LangWatch without installing anything?\n\nNo hosted endpoint is listed for Gauge CLI. LangWatch has a hosted endpoint at https://app.langwatch.ai.\n\n### Are Gauge CLI and LangWatch open source?\n\nYes. Gauge CLI is open source (MIT). LangWatch is open source (Apache 2.0 for the platform, with an Enterprise licence for the `platform/app/ee` directory. The SDKs and the MCP server are MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gauge-cli-vs-langwatch.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gauge-cli-vs-langwatch.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gauge-cli\", \"b\": \"langwatch\"}`. From a terminal: `anchor compare gauge-cli langwatch`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gauge-cli.json and https://www.anchorterminal.com/api/v1/tools/langwatch.json\n\n## Other comparisons with Gauge CLI or LangWatch\n\n- [Agent Tree vs LangWatch](https://www.anchorterminal.com/compare/agent-tree-vs-langwatch.md)\n- [agents-tree vs LangWatch](https://www.anchorterminal.com/compare/agents-tree-vs-langwatch.md)\n- [Arize Phoenix vs LangWatch](https://www.anchorterminal.com/compare/arize-phoenix-vs-langwatch.md)\n- [Baserun vs LangWatch](https://www.anchorterminal.com/compare/baserun-vs-langwatch.md)\n- [BotGauge vs LangWatch](https://www.anchorterminal.com/compare/botgauge-vs-langwatch.md)\n- [Braintrust API + MCP vs LangWatch](https://www.anchorterminal.com/compare/braintrust-vs-langwatch.md)\n- [Galileo API + MCP vs LangWatch](https://www.anchorterminal.com/compare/galileo-vs-langwatch.md)\n- [Helicone AI Gateway + MCP vs LangWatch](https://www.anchorterminal.com/compare/helicone-vs-langwatch.md)\n- [HoneyHive vs LangWatch](https://www.anchorterminal.com/compare/honeyhive-vs-langwatch.md)\n- [Laminar API + MCP vs LangWatch](https://www.anchorterminal.com/compare/laminar-vs-langwatch.md)\n- [Langfuse API + MCP vs LangWatch](https://www.anchorterminal.com/compare/langfuse-vs-langwatch.md)\n- [LangSmith API + MCP vs LangWatch](https://www.anchorterminal.com/compare/langsmith-vs-langwatch.md)\n- [LangWatch vs MLflow Tracing](https://www.anchorterminal.com/compare/langwatch-vs-mlflow-tracing.md)\n- [LangWatch vs Navige](https://www.anchorterminal.com/compare/langwatch-vs-navige.md)\n- [LangWatch vs Opik API + MCP](https://www.anchorterminal.com/compare/langwatch-vs-opik.md)\n- [LangWatch vs Overmind](https://www.anchorterminal.com/compare/langwatch-vs-overmind.md)\n- [LangWatch vs Prefactor](https://www.anchorterminal.com/compare/langwatch-vs-prefactor.md)\n- [LangWatch vs Pydantic Logfire](https://www.anchorterminal.com/compare/langwatch-vs-pydantic-logfire.md)\n- [LangWatch vs Respan API + MCP](https://www.anchorterminal.com/compare/langwatch-vs-respan.md)\n- [LangWatch vs W\u0026B Weave](https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave.md)\n- [Arize Phoenix vs Gauge CLI](https://www.anchorterminal.com/compare/arize-phoenix-vs-gauge-cli.md)\n- [Baserun vs Gauge CLI](https://www.anchorterminal.com/compare/baserun-vs-gauge-cli.md)\n- [BotGauge vs Gauge CLI](https://www.anchorterminal.com/compare/botgauge-vs-gauge-cli.md)\n- [Braintrust API + MCP vs Gauge CLI](https://www.anchorterminal.com/compare/braintrust-vs-gauge-cli.md)\n- [DeepEval vs Gauge CLI](https://www.anchorterminal.com/compare/deepeval-vs-gauge-cli.md)\n- [DeepEval vs LangWatch](https://www.anchorterminal.com/compare/deepeval-vs-langwatch.md)\n- [Galileo API + MCP vs Gauge CLI](https://www.anchorterminal.com/compare/galileo-vs-gauge-cli.md)\n- [Gauge CLI vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-helicone.md)\n- [Gauge CLI vs HoneyHive](https://www.anchorterminal.com/compare/gauge-cli-vs-honeyhive.md)\n- [Gauge CLI vs Laminar API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-laminar.md)\n- [Gauge CLI vs Langfuse API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-langfuse.md)\n- [Gauge CLI vs LangSmith API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-langsmith.md)\n- [Gauge CLI vs MLflow Tracing](https://www.anchorterminal.com/compare/gauge-cli-vs-mlflow-tracing.md)\n- [Gauge CLI vs Opik API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-opik.md)\n- [Gauge CLI vs Overmind](https://www.anchorterminal.com/compare/gauge-cli-vs-overmind.md)\n- [Gauge CLI vs Prefactor](https://www.anchorterminal.com/compare/gauge-cli-vs-prefactor.md)\n- [Gauge CLI vs Pydantic Logfire](https://www.anchorterminal.com/compare/gauge-cli-vs-pydantic-logfire.md)\n- [Gauge CLI vs Respan API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-respan.md)\n- [Gauge CLI vs W\u0026B Weave](https://www.anchorterminal.com/compare/gauge-cli-vs-wandb-weave.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": "Gauge CLI vs LangWatch", "url": "" } ], "description": "LangWatch scores 65.6 (B) to Gauge CLI's 60.4 (C) for evaluations. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Gauge CLI C 60.4", "LangWatch B 65.6", "scores" ], "h1": "Gauge CLI vs LangWatch", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/gauge-cli-vs-langwatch", "published": "2026-10-01", "section": "tools", "title": "Gauge CLI vs LangWatch for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-06", "url": "https://www.anchorterminal.com/compare/gauge-cli-vs-langwatch" }, "tokens": { "markdown": 4600, "slim": 2430 }, "version": 1 }