{ "data": { "a": { "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", "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": 101, "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": "2026-10-02", "graded": true, "anchor": { "graded": true, "score": 65.5, "grade": "B", "agentReady": false, "rank": 291, "ranked": true, "rankOf": 842, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 67, "maintenance": 90, "payments": 40, "reliability": 53, "schema": 87, "security": 71, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": -2, "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, so -2 (https://github.com/langwatch/langwatch/security/advisories/GHSA-h25p-f8f6-2ccf)" ], "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 101 tools with no read-only or destructive annotations, and no rate limit for the platform API was found in the reviewed documentation.", "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 328 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 3.20.1 shipped on 2 October 2026, with 21 platform releases dated since 11 July in the repository changelog" ], "weaknesses": [ "The MCP server registers 101 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 two operations in the OpenAPI document declare a 429", "The status page shows Scenarios down for 9 hours 34 minutes on 8 September 2026 and trace processing degraded for 14 hours 44 minutes on 31 July", "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", "The audit log is Enterprise only and records neither sign-ins nor reads of traces" ], "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", "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 101 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": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.5 } ], "editorialScores": { "ergonomics": 67, "maintenance": 90, "payments": 40, "reliability": 53, "schema": 87, "security": 71, "transparency": 73 }, "provenanceScore": 77 }, "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": "2026-10-09", "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": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/langwatch.json", "live": { "slug": "langwatch", "probe": { "target": "https://app.langwatch.ai", "method": "get", "lastAt": "2026-10-09T11:46:32.095480858Z", "lastOk": true, "lastStatus": 200, "lastMs": 60, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 81, "p95ms24h": 135, "samples24h": 44, "samples30d": 44, "days": [ { "date": "2026-10-09", "probes": 44, "ok": 44 } ] }, "vendorStatus": { "page": "https://status.langwatch.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-09T07:58:07.342247188Z" }, "updatedAt": "2026-10-09T11:46:32.095480858Z" } }, "answer": "W\u0026B Weave scores 66.7 (B) on agent readiness against LangWatch's 65.5 (B), and leads in 2 of 7 scored categories. LangWatch leads on schema \u0026 documentation, security \u0026 auth and payments \u0026 pricing.", "b": { "slug": "wandb-weave", "name": "W\u0026B Weave", "vendor": "Weights \u0026 Biases (CoreWeave)", "vendorUrl": "https://wandb.ai", "kind": "http-api", "category": "agent-observability", "summary": "W\u0026B Weave is CoreWeave Forge's tracing and evaluation service for LLM applications and agents. It takes traces from Python and TypeScript SDKs or an OTLP endpoint and exposes them through a REST Service API.", "url": "https://www.anchorterminal.com/tools/wandb-weave", "markdownUrl": "https://www.anchorterminal.com/tools/wandb-weave.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/wandb-weave.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/wandb-weave.json", "repo": "https://github.com/wandb/weave", "license": "Hosted service under the W\u0026B Master Service Agreement. The Weave SDKs and trace server source on GitHub are Apache-2.0, and the W\u0026B MCP server is MIT", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://trace.wandb.ai", "packages": [ { "registry": "pypi", "name": "weave" }, { "registry": "npm", "name": "weave" } ], "auth": "api-key", "authNotes": "A Forge API key, created by a signed-in user at forge.coreweave.com/settings after signing up at id.coreweave.com/signup. The Service API takes it as `Authorization: Bearer`, the OTLP endpoints as a `wandb-api-key` header or HTTP Basic with user `api`. Personal keys reach every organisation the user belongs to. Service account keys are limited to one team or one organisation. Keys carry no per-permission scopes, the secret is shown once, and deleting a key revokes it at once.", "pricing": "freemium", "pricingNotes": "Free is $0 a month with 1 GB of Weave data ingestion. Pro starts at $60 a month with 1.5 GB, a 30 day trial and further ingestion at $0.10 per MB, billed in arrears. Enterprise is quoted, with further ingestion listed at $0.20 per MB and volume discounts on annual commitments. Ingested bytes are counted once when stored. The pricing page doesn't say whether Free needs a card (checked 2026-10-08).", "priceSummary": "$60 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Weave docs, the OpenAPI document or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 623550, "pypiWeekly": 219442, "asOf": "2026-10-08" }, "docsUrl": "https://docs.coreweave.com/products/wandb/weave", "llmsTxt": "https://docs.coreweave.com/llms.txt", "openapi": "https://trace.wandb.ai/openapi.json", "capabilities": [ "obs.traces", "obs.evals", "obs.prompts", "obs.datasets" ], "tags": [ "hosted", "freemium", "open-source", "self-hosted", "mcp", "llms-txt", "openapi", "opentelemetry", "python", "typescript", "status-page", "soc2" ], "lastRelease": "2026-09-25", "graded": true, "anchor": { "graded": true, "score": 66.7, "grade": "B", "agentReady": false, "rank": 260, "ranked": true, "rankOf": 842, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 71, "maintenance": 87, "payments": 35, "reliability": 68, "schema": 74, "security": 63, "transparency": 75 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "The Service API at trace.wandb.ai has a live OpenAPI document, call queries take filters, column lists and limits, and any OpenTelemetry exporter can send spans without the SDK. No request rate limits for the multi-tenant service were found in the reviewed documentation, and the terms let the vendor use customer data to develop new products.", "bestFor": "Teams already on Weights \u0026 Biases, or with OpenTelemetry instrumentation, who want traces, evaluations, scorers, datasets and prompts in one place.", "strengths": [ "A live OpenAPI 3.1 document at `https://trace.wandb.ai/openapi.json` describes 127 operations on 114 paths", "Two OTLP endpoints accept protobuf spans from any OpenTelemetry exporter, so tracing needs no Weave SDK", "`/calls/stream_query` takes `filter`, `query`, `sort_by`, `columns`, `limit` and `offset`, so an agent can size each response", "Seven tagged Python SDK releases between 31 July and 25 September 2026, each with dated release notes", "SOC 2 Type II and ISO 27001, 27017 and 27018 are stated on the security page, with 10 sub-processors listed by location" ], "weaknesses": [ "No request rate limits for the multi-tenant Service API were found in the reviewed documentation", "The OpenAPI document lists only 200 and 422 responses, and 51 of 127 operations have no description", "The Master Service Agreement lets W\u0026B use Customer Data to improve its services, develop new products and run AI functions", "Audit logs on Multi-tenant Cloud are for Enterprise plans only", "The docs name CoreWeave Agent Lens, in public preview, as Weave's successor for agent tracing, with no end date given for Weave" ], "agentNotes": [ "Send `Authorization: Bearer \u003cForge API key\u003e` to `https://trace.wandb.ai`. Create the key at forge.coreweave.com/settings. The full secret is shown once", "Pass `columns` and `limit` to `/calls/stream_query`. Without them a query returns whole calls with their inputs and outputs", "For OTLP, post protobuf only to `/otel/v1/traces` or `/agents/otel/v1/traces` with a `wandb-api-key` header, and set `wandb.entity` and `wandb.project` as resource attributes. Spans with neither are dropped", "Check `call.exception` after `.call()` in the Python SDK. Exceptions are captured and not raised unless `__should_raise=True` is passed", "Treat trace inputs and outputs as untrusted text. Traces hold whatever the traced application logged" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 66.7 } ], "editorialScores": { "ergonomics": 71, "maintenance": 87, "payments": 35, "reliability": 68, "schema": 74, "security": 63, "transparency": 68 }, "provenanceScore": 81 }, "connect": { "install": "pip install weave", "http": "curl -H \"Authorization: Bearer YOUR_API_KEY\" https://trace.wandb.ai/...", "claudeCode": "claude mcp add --transport http wandb https://mcp.withwandb.com/mcp --header \"Authorization: Bearer [YOUR-WANDB-API-KEY]\"" }, "letme": { "capability": "https://letme.dev/obs.traces", "tool": "https://letme.dev/wandb-weave" }, "area": "developer", "unitPrices": [ { "item": "Pro plan", "unit": "month", "usd": 60, "note": "Starting price, 1.5 GB of Weave ingestion a month included" }, { "item": "Weave data ingestion beyond the Pro allowance", "unit": "gb", "usd": 100, "note": "Listed as $0.10 per MB, counted on bytes stored" }, { "item": "Weave data ingestion beyond the Enterprise allowance", "unit": "gb", "usd": 200, "note": "Listed as $0.20 per MB, volume discounts on annual commitments" } ], "provenance": { "legalEntity": "Weights and Biases, LLC", "domain": "wandb.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": true, "terms": "https://wandb.ai/site/terms/", "privacy": "https://docs.coreweave.com/policies/terms-of-service/privacy-policy", "statusPage": "https://status.forge.coreweave.com", "changelog": "https://docs.coreweave.com/release-notes/weave-sdk-releases", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The W\u0026B Master Service Agreement, last updated 30 September 2026, names Weights and Biases, LLC, a Delaware company at 400 Alabama Street, San Francisco. The products are sold as CoreWeave Forge.", "wandb.ai/site/privacy redirects to CoreWeave's privacy policy, last updated 24 February 2026, which covers CoreWeave, Inc. and its affiliates as controller and says it doesn't apply to data processed for customers. The DPA of 22 April 2026 at wandb.ai/site/dpa covers that data.", "The Service API and OTLP endpoints run on trace.wandb.ai. The hosted MCP server runs on mcp.withwandb.com and the console on forge.coreweave.com.", "wandb.ai/.well-known/security.txt redirects to a Forge page that answers \"Invalid .well-known request\", and coreweave.com/.well-known/security.txt returns 404. The security page takes reports at security@coreweave.com.", "status.wandb.com, which the SLA cites, redirects to status.forge.coreweave.com.", "RDAP for wandb.ai gives a registration date of 2017-12-16." ], "score": 81 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/wandb-weave.json", "live": { "slug": "wandb-weave", "probe": { "target": "https://trace.wandb.ai", "method": "get", "lastAt": "2026-10-09T11:46:45.671898702Z", "lastOk": true, "lastStatus": 200, "lastMs": 156, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 144, "p95ms24h": 227, "samples24h": 44, "samples30d": 44, "days": [ { "date": "2026-10-09", "probes": 44, "ok": 44 } ] }, "vendorStatus": { "page": "https://status.forge.coreweave.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-09T11:41:15.82222577Z" }, "updatedAt": "2026-10-09T11:46:45.671898702Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Reasoning Engine B.V. (LangWatch)", "b": "Weights \u0026 Biases (CoreWeave)", "name": "Vendor" }, { "a": "https://app.langwatch.ai", "b": "https://trace.wandb.ai", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, SSE (legacy), stdio", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache 2.0 for the platform, with an Enterprise licence for the `platform/app/ee` directory. The SDKs and the MCP server are MIT", "b": "Hosted service under the W\u0026B Master Service Agreement. The Weave SDKs and trace server source on GitHub are Apache-2.0, and the W\u0026B MCP server is MIT", "name": "Licence" }, { "a": "101", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-02", "b": "2026-09-25", "name": "Last release" }, { "a": "2026-09-22", "b": "2026-09-30", "name": "Terms last updated" }, { "a": "2026-09-29", "b": "2026-02-24", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "4.9k stars, 50k npm/wk, 87k PyPI/wk", "b": "624k npm/wk, 219k PyPI/wk", "name": "Popularity" } ], "faq": [ { "answer": "W\u0026B Weave scores 66.7 (B) on agent readiness against LangWatch's 65.5 (B), and leads in 2 of 7 scored categories. LangWatch leads on schema \u0026 documentation, security \u0026 auth and payments \u0026 pricing.", "question": "Which is better for AI agents, LangWatch or W\u0026B Weave?" }, { "answer": "LangWatch takes an API key or an OAuth sign-in. W\u0026B Weave needs an API key.", "question": "Do LangWatch and W\u0026B Weave need an API key?" }, { "answer": "Yes. LangWatch has a hosted endpoint at https://app.langwatch.ai and W\u0026B Weave at https://trace.wandb.ai.", "question": "Can an agent call LangWatch and W\u0026B Weave without installing anything?" }, { "answer": "Yes. 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). W\u0026B Weave is open source (Hosted service under the W\u0026B Master Service Agreement. The Weave SDKs and trace server source on GitHub are Apache-2.0, and the W\u0026B MCP server is MIT).", "question": "Are LangWatch and W\u0026B Weave open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 87 against 74", "Security \u0026 auth, 71 against 63", "Payments \u0026 pricing, 40 against 35" ], "also": [ "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 101 tools, deletes and key creation among them, with no toolsets and no `readOnlyHint` or `destructiveHint` annotations in the source" }, { "aheadOn": [ "Reliability, 68 against 53" ], "also": null, "goodFor": "Teams already on Weights \u0026 Biases, or with OpenTelemetry instrumentation, who want traces, evaluations, scorers, datasets and prompts in one place.", "slug": "wandb-weave", "watchFor": "No request rate limits for the multi-tenant Service API were found in the reviewed documentation" } ], "job": { "capability": "obs.traces", "name": "Obs traces" }, "others": [ { "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/arize-phoenix-vs-wandb-weave.json", "title": "Arize Phoenix vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/arize-phoenix-vs-wandb-weave" }, { "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/baserun-vs-wandb-weave.json", "title": "Baserun vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/baserun-vs-wandb-weave" }, { "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/braintrust-vs-wandb-weave.json", "title": "Braintrust API + MCP vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/braintrust-vs-wandb-weave" }, { "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/galileo-vs-wandb-weave.json", "title": "Galileo API + MCP vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/galileo-vs-wandb-weave" }, { "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/helicone-vs-wandb-weave.json", "title": "Helicone AI Gateway + MCP vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/helicone-vs-wandb-weave" }, { "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/honeyhive-vs-wandb-weave.json", "title": "HoneyHive vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/honeyhive-vs-wandb-weave" }, { "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/laminar-vs-wandb-weave.json", "title": "Laminar API + MCP vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/laminar-vs-wandb-weave" }, { "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/langfuse-vs-wandb-weave.json", "title": "Langfuse API + MCP vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/langfuse-vs-wandb-weave" }, { "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/langsmith-vs-wandb-weave.json", "title": "LangSmith API + MCP vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/langsmith-vs-wandb-weave" }, { "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-respan.json", "title": "LangWatch vs Respan API + MCP", "url": "https://www.anchorterminal.com/compare/langwatch-vs-respan" }, { "json": "https://www.anchorterminal.com/compare/prefactor-vs-wandb-weave.json", "title": "Prefactor vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/prefactor-vs-wandb-weave" }, { "json": "https://www.anchorterminal.com/compare/respan-vs-wandb-weave.json", "title": "Respan API + MCP vs W\u0026B Weave", "url": "https://www.anchorterminal.com/compare/respan-vs-wandb-weave" } ], "scores": [ { "by": 15, "edge": "wandb-weave", "key": "reliability", "langwatch": 53, "name": "Reliability", "wandb-weave": 68, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 13, "edge": "langwatch", "key": "schema", "langwatch": 87, "name": "Schema \u0026 documentation", "wandb-weave": 74, "weight": 13 }, { "by": 4, "edge": "wandb-weave", "key": "ergonomics", "langwatch": 67, "name": "Agent ergonomics", "wandb-weave": 71, "weight": 13 }, { "by": 8, "edge": "langwatch", "key": "security", "langwatch": 71, "name": "Security \u0026 auth", "wandb-weave": 63, "weight": 14 }, { "by": 5, "edge": "langwatch", "key": "payments", "langwatch": 40, "name": "Payments \u0026 pricing", "wandb-weave": 35, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 3, "edge": "langwatch", "key": "maintenance", "langwatch": 90, "name": "Maintenance \u0026 community", "wandb-weave": 87, "weight": 7 }, { "by": 0, "edge": "", "key": "transparency", "langwatch": 75, "name": "Transparency \u0026 trust", "wandb-weave": 75, "weight": 7 } ], "summary": "W\u0026B Weave scores 66.7 (B) on agent readiness against LangWatch's 65.5 (B), and leads in 2 of 7 scored categories. LangWatch leads on schema \u0026 documentation, security \u0026 auth and payments \u0026 pricing. Both do obs traces.", "verdicts": { "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 101 tools with no read-only or destructive annotations, and no rate limit for the platform API was found in the reviewed documentation.", "wandb-weave": "The Service API at trace.wandb.ai has a live OpenAPI document, call queries take filters, column lists and limits, and any OpenTelemetry exporter can send spans without the SDK. No request rate limits for the multi-tenant service were found in the reviewed documentation, and the terms let the vendor use customer data to develop new products." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave", "json": "https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave.md", "slim": "https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave.min.md" }, "markdown": "W\u0026B Weave scores 66.7 (B) on agent readiness against LangWatch's 65.5 (B), and leads in 2 of 7 scored categories. LangWatch leads on schema \u0026 documentation, security \u0026 auth and payments \u0026 pricing. Both do obs traces.\n\n- LangWatch: grade B, 65.5/100, rank #291 of 842. Markdown https://www.anchorterminal.com/tools/langwatch.md · JSON https://www.anchorterminal.com/api/v1/tools/langwatch.json\n- W\u0026B Weave: grade B, 66.7/100, rank #260 of 842. Markdown https://www.anchorterminal.com/tools/wandb-weave.md · JSON https://www.anchorterminal.com/api/v1/tools/wandb-weave.json\n\n## Which one, for what\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 74\n- Security \u0026 auth, 71 against 63\n- Payments \u0026 pricing, 40 against 35\n\nAlso in its favour:\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: The MCP server registers 101 tools, deletes and key creation among them, with no toolsets and no `readOnlyHint` or `destructiveHint` annotations in the source\n\n### W\u0026B Weave (B)\n\nGood for: Teams already on Weights \u0026 Biases, or with OpenTelemetry instrumentation, who want traces, evaluations, scorers, datasets and prompts in one place.\n\nAhead on:\n- Reliability, 68 against 53\n\nWatch for: No request rate limits for the multi-tenant Service API were found in the reviewed documentation\n\n\n## Score by category\n\n| Category | Weight | LangWatch | W\u0026B Weave | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 53 | 68 | W\u0026B Weave +15 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 87 | 74 | LangWatch +13 |\n| Agent ergonomics | 13% (16.2 this run) | 67 | 71 | W\u0026B Weave +4 |\n| Security \u0026 auth | 14% (17.5 this run) | 71 | 63 | LangWatch +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 35 | LangWatch +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 90 | 87 | LangWatch +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 75 | 75 | even |\n| Negative events | ≤15 | -2 | 0 | |\n| **Total** | | **65.5 · B** | **66.7 · B** | |\n\n## Facts side by side\n\n| Fact | LangWatch | W\u0026B Weave |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Reasoning Engine B.V. (LangWatch) | Weights \u0026 Biases (CoreWeave) |\n| Hosted endpoint | `https://app.langwatch.ai` | `https://trace.wandb.ai` |\n| Transports | HTTP, Streamable HTTP, SSE (legacy), stdio | HTTP, Streamable HTTP |\n| Auth | OAuth or key | API key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | Apache 2.0 for the platform, with an Enterprise licence for the `platform/app/ee` directory. The SDKs and the MCP server are MIT | Hosted service under the W\u0026B Master Service Agreement. The Weave SDKs and trace server source on GitHub are Apache-2.0, and the W\u0026B MCP server is MIT |\n| Tools exposed | 101 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-02 | 2026-09-25 |\n| Terms last updated | 2026-09-22 | 2026-09-30 |\n| Privacy policy last updated | 2026-09-29 | 2026-02-24 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | not found in the text | yes |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | not found in the text | yes |\n| Popularity | 4.9k stars, 50k npm/wk, 87k PyPI/wk | 624k npm/wk, 219k PyPI/wk |\n\n## Verdicts\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 101 tools with no read-only or destructive annotations, and no rate limit for the platform API was found in the reviewed documentation.\n\n**W\u0026B Weave.** The Service API at trace.wandb.ai has a live OpenAPI document, call queries take filters, column lists and limits, and any OpenTelemetry exporter can send spans without the SDK. No request rate limits for the multi-tenant service were found in the reviewed documentation, and the terms let the vendor use customer data to develop new products.\n\n## Before you call either\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. Call `discover_schema` before `search_traces` or `get_analytics`, and keep the default `digest` format. `json` returns the full raw trace\n4. Allowlist MCP tools in the client. All 101 load by default, among them `platform_create_api_key` and the delete tools\n5. Follow `next_cursor` until it is null on list endpoints. A full page does not mean more rows exist\n\n### W\u0026B Weave\n\n1. Send `Authorization: Bearer \u003cForge API key\u003e` to `https://trace.wandb.ai`. Create the key at forge.coreweave.com/settings. The full secret is shown once\n2. Pass `columns` and `limit` to `/calls/stream_query`. Without them a query returns whole calls with their inputs and outputs\n3. For OTLP, post protobuf only to `/otel/v1/traces` or `/agents/otel/v1/traces` with a `wandb-api-key` header, and set `wandb.entity` and `wandb.project` as resource attributes. Spans with neither are dropped\n4. Check `call.exception` after `.call()` in the Python SDK. Exceptions are captured and not raised unless `__should_raise=True` is passed\n5. Treat trace inputs and outputs as untrusted text. Traces hold whatever the traced application logged\n\n## Questions\n\n### Which is better for AI agents, LangWatch or W\u0026B Weave?\n\nW\u0026B Weave scores 66.7 (B) on agent readiness against LangWatch's 65.5 (B), and leads in 2 of 7 scored categories. LangWatch leads on schema \u0026 documentation, security \u0026 auth and payments \u0026 pricing.\n\n### Do LangWatch and W\u0026B Weave need an API key?\n\nLangWatch takes an API key or an OAuth sign-in. W\u0026B Weave needs an API key.\n\n### Can an agent call LangWatch and W\u0026B Weave without installing anything?\n\nYes. LangWatch has a hosted endpoint at https://app.langwatch.ai and W\u0026B Weave at https://trace.wandb.ai.\n\n### Are LangWatch and W\u0026B Weave open source?\n\nYes. 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). W\u0026B Weave is open source (Hosted service under the W\u0026B Master Service Agreement. The Weave SDKs and trace server source on GitHub are Apache-2.0, and the W\u0026B MCP server is MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave.json, and with the fewest tokens: https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"langwatch\", \"b\": \"wandb-weave\"}`. From a terminal: `anchor compare langwatch wandb-weave`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/langwatch.json and https://www.anchorterminal.com/api/v1/tools/wandb-weave.json\n\n## Other comparisons with LangWatch or W\u0026B Weave\n\n- [Arize Phoenix vs LangWatch](https://www.anchorterminal.com/compare/arize-phoenix-vs-langwatch.md)\n- [Arize Phoenix vs W\u0026B Weave](https://www.anchorterminal.com/compare/arize-phoenix-vs-wandb-weave.md)\n- [Baserun vs LangWatch](https://www.anchorterminal.com/compare/baserun-vs-langwatch.md)\n- [Baserun vs W\u0026B Weave](https://www.anchorterminal.com/compare/baserun-vs-wandb-weave.md)\n- [Braintrust API + MCP vs LangWatch](https://www.anchorterminal.com/compare/braintrust-vs-langwatch.md)\n- [Braintrust API + MCP vs W\u0026B Weave](https://www.anchorterminal.com/compare/braintrust-vs-wandb-weave.md)\n- [Galileo API + MCP vs LangWatch](https://www.anchorterminal.com/compare/galileo-vs-langwatch.md)\n- [Galileo API + MCP vs W\u0026B Weave](https://www.anchorterminal.com/compare/galileo-vs-wandb-weave.md)\n- [Helicone AI Gateway + MCP vs LangWatch](https://www.anchorterminal.com/compare/helicone-vs-langwatch.md)\n- [Helicone AI Gateway + MCP vs W\u0026B Weave](https://www.anchorterminal.com/compare/helicone-vs-wandb-weave.md)\n- [HoneyHive vs LangWatch](https://www.anchorterminal.com/compare/honeyhive-vs-langwatch.md)\n- [HoneyHive vs W\u0026B Weave](https://www.anchorterminal.com/compare/honeyhive-vs-wandb-weave.md)\n- [Laminar API + MCP vs LangWatch](https://www.anchorterminal.com/compare/laminar-vs-langwatch.md)\n- [Laminar API + MCP vs W\u0026B Weave](https://www.anchorterminal.com/compare/laminar-vs-wandb-weave.md)\n- [Langfuse API + MCP vs LangWatch](https://www.anchorterminal.com/compare/langfuse-vs-langwatch.md)\n- [Langfuse API + MCP vs W\u0026B Weave](https://www.anchorterminal.com/compare/langfuse-vs-wandb-weave.md)\n- [LangSmith API + MCP vs LangWatch](https://www.anchorterminal.com/compare/langsmith-vs-langwatch.md)\n- [LangSmith API + MCP vs W\u0026B Weave](https://www.anchorterminal.com/compare/langsmith-vs-wandb-weave.md)\n- [LangWatch vs Prefactor](https://www.anchorterminal.com/compare/langwatch-vs-prefactor.md)\n- [LangWatch vs Respan API + MCP](https://www.anchorterminal.com/compare/langwatch-vs-respan.md)\n- [Prefactor vs W\u0026B Weave](https://www.anchorterminal.com/compare/prefactor-vs-wandb-weave.md)\n- [Respan API + MCP vs W\u0026B Weave](https://www.anchorterminal.com/compare/respan-vs-wandb-weave.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "LangWatch vs W\u0026B Weave", "url": "" } ], "description": "W\u0026B Weave scores 66.7 (B) on agent readiness against LangWatch's 65.5 (B), and leads in 2 of 7 scored categories. LangWatch leads on schema \u0026 documentation, security \u0026 auth and payments \u0026 pricing. Both do obs traces. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "LangWatch B 65.5", "W\u0026B Weave B 66.7", "scores" ], "h1": "LangWatch vs W\u0026B Weave", "image": "https://www.anchorterminal.com/assets/og/compare-langwatch-vs-wandb-weave.png", "path": "/compare/langwatch-vs-wandb-weave", "published": "2026-10-01", "section": "tools", "title": "LangWatch vs W\u0026B Weave for AI agents, B 65.5 vs B 66.7", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/langwatch-vs-wandb-weave" }, "tokens": { "markdown": 2600, "slim": 730 }, "version": 1 }