{ "data": { "a": { "slug": "fone-me", "name": "fone.me", "vendor": "Fone", "vendorUrl": "https://www.fone.me", "kind": "platform", "category": "voice-agents", "summary": "fone.me is a hosted AI agent at a personal link that answers calls and messages for a person or small business over web chat, voice, WhatsApp, Telegram and a Premium number. Other agents reach it through keyless MCP and A2A.", "url": "https://www.anchorterminal.com/tools/fone-me", "markdownUrl": "https://www.anchorterminal.com/tools/fone-me.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/fone-me.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/fone-me.json", "dns": "fone-me.grade.anchorterminal.com", "license": "Proprietary hosted service. Terms of service at https://www.fone.me/terms, whose text draws by script and could not be read on 5 November 2026; no company is named on any page read. No source, SDK or package is published", "transports": [ "streamable-http" ], "remoteUrl": "https://www.fone.me/mcp", "packages": [], "auth": "none", "authNotes": "No credential for callers. llms.txt gives the MCP server at https://www.fone.me/mcp as Streamable HTTP with auth 'none', and the README of the GitHub repository spearisa/fone-me-mcp says 'public, like the links themselves'. The A2A agent cards read (demo and maxr) declare no securitySchemes or security. The search API at /api/agents/search takes a query with no key per llms.txt. Owners sign in with Apple, Google or email to set up an agent; no owner API key, scopes or tokens are documented.", "pricing": "freemium", "pricingNotes": "The agent, the first link and the website chat button are free. Premium is $9.99 a month (llms.txt and https://www.fone.me/alternatives/smith-ai) and adds the agent's own phone number, calling minutes and more links, with cancellation at any time; no page read gives the minute allowance, the number of links, the countries for numbers or the payment method. Outbound calls use Premium minutes and international calls use more minutes per minute. Callers and outside agents pay nothing (checked 2026-11-05).", "priceSummary": "$9.99 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in llms.txt, the guide pages read, the MCP repository README and server.json, or the two agent cards (checked 2026-11-05). The MCP server and A2A endpoints are free and keyless; Premium is a monthly subscription with no payment route stated.", "endpoints": [] }, "toolCount": 4, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-05" }, "docsUrl": "https://www.fone.me/llms.txt", "llmsTxt": "https://www.fone.me/llms.txt", "capabilities": [ "voice.agent", "voice.telephony", "voice.calls", "messaging.whatsapp", "messaging.inbound" ], "tags": [ "hosted", "official", "closed-source", "mcp", "remote-mcp", "no-auth", "keyless", "a2a", "llms-txt", "whatsapp", "telegram", "ios", "freemium", "free-tier", "no-status-page" ], "lastRelease": "2026-10-05", "graded": true, "anchor": { "graded": true, "score": 28.3, "grade": "F", "agentReady": false, "rank": 1429, "ranked": true, "rankOf": 1510, "categoryRank": 26, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 29, "maintenance": 23, "payments": 50, "reliability": 15, "schema": 31, "security": 30, "transparency": 23 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-05" }, "negative": 0, "verdict": "Any agent can find a fone.me link and message its owner's agent through a keyless MCP server or A2A, with no sign-up or cost, and owners see every conversation in one inbox. Tool schemas, rate limits and abuse controls for that open channel are unpublished, the terms and privacy policy draw by script, and no company is named.", "bestFor": "Agents acting for a person who need to reach a freelancer's, shop's or small business's own AI agent at its fone.me link to ask a question, request a booking or quote or leave a message, and owners who want an answering agent on a link, WhatsApp, Telegram and a $9.99 number without building one.", "strengths": [ "Keyless MCP server and per-link A2A endpoints let any agent find, look up and message a person's or business's agent without an account or payment", "Agent cards follow A2A 0.3.0 with skills, input and output modes and a JSON-RPC transport, readable at an address robots.txt allows", "Outbound calls disclose the agent and transcription, run only 8 am to 9 pm in the callee's time zone and stop permanently on a do-not-call request", "Owners see every call and chat with a transcript in one inbox, can take over at any time and approve what the agent will say before it calls", "Free agent, first link and website chat button, with Premium at $9.99 a month for a number and calling minutes" ], "weaknesses": [ "No tool arguments, input schemas, annotations, error shapes or rate limits are published for the MCP server or A2A endpoints", "message_agent and A2A reach any person's agent with no caller identity, and no spam, rate or abuse control for that channel is documented", "The terms, privacy policy, data-deletion page, FAQ and support page draw by script, and no company, address or country of incorporation is named on any page read", "No status page, changelog, security.txt, SLA or published minute allowance for Premium", "robots.txt disallows the /mcp, /api/ and /*/a2a paths that llms.txt advertises to agents" ], "agentNotes": [ "Connect to https://www.fone.me/mcp with no credentials; use find_agents or get_agent before message_agent so the message goes to the right person's link.", "Say who you are acting for in every message_agent call; the owner reads it in an inbox as a named conversation, and conversations continue across calls.", "Treat replies as the owner's agent speaking from what it was taught, not a commitment; the vendor says it asks its owner before agreeing to anything or spending money.", "Read a link's agent card at /{link}/.well-known/agent-card.json for its skills before using A2A message/send at /{link}/a2a.", "Don't send personal or payment details through message_agent; no retention or privacy terms for agent-to-agent messages could be read." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "F", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 28.3 } ], "editorialScores": { "ergonomics": 29, "maintenance": 23, "payments": 50, "reliability": 15, "schema": 31, "security": 30, "transparency": 13 }, "provenanceScore": 32, "checked": { "categories": { "ergonomics": "2026-11-05", "maintenance": "2026-11-05", "payments": "2026-11-05", "reliability": "2026-11-05", "schema": "2026-11-05", "security": "2026-11-05", "transparency": "2026-11-05" }, "last": "2026-11-05", "oldest": "2026-11-05", "stale": false, "staleAfterDays": 90 } }, "connect": { "config": { "mcpServers": { "fone.me": { "type": "http", "url": "https://www.fone.me/mcp" } } } }, "letme": { "capability": "https://letme.dev/voice.agent", "tool": "https://letme.dev/fone-me" }, "area": "voice", "unitPrices": [ { "item": "Premium", "unit": "month", "usd": 9.99, "note": "own fone.me number, calling minutes (allowance not published) and more links; the agent, first link and chat button are free" } ], "provenance": { "legalEntity": "", "domain": "fone.me", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.fone.me/terms", "privacy": "https://www.fone.me/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-05", "notes": [ "No legal entity is named on any page read. Page metadata gives the author and site name as 'Fone', and llms.txt gives San Francisco, CA, USA as a location. The terms, privacy policy and data-deletion page draw their text by script and showed only titles, so whether they name a company is unchecked, not absent.", "The README of github.com/spearisa/fone-me-mcp ends 'Operated by zwilio'. No fone.me page read names zwilio or links the repository, and three web searches found no company of that name, so it is not recorded as the legal entity.", "The MCP server, the search API and the A2A endpoints are on www.fone.me, the vendor's own domain. robots.txt disallows /mcp, /api/ and /*/a2a, so none was fetched; the agent cards it allows were read for two links.", "No status page or changelog found. /.well-known/security.txt answers with the app's HTML shell, recorded as none. /status failed to load.", "RDAP for fone.me, the Wayback Machine, the official MCP registry and the App Store listing (id 6759304762) were not read; each fetch needed an approval that did not come. firstReleased 2025-11-05 is the earliest sitemap lastmod (/sha_krux), a lower bound only, and falls one year to the day before the check, so the sitemap may cap its dates." ], "score": 32 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/fone-me.json", "live": { "slug": "fone-me", "probe": { "target": "https://www.fone.me/mcp", "method": "get", "lastAt": "2026-11-07T19:22:07.71997153Z", "lastOk": true, "lastStatus": 405, "lastMs": 357, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 215, "p95ms24h": 511, "samples24h": 210, "samples30d": 210, "days": [ { "date": "2026-11-06", "probes": 13, "ok": 13 }, { "date": "2026-11-07", "probes": 197, "ok": 197 } ] }, "securityTxt": { "url": "https://fone.me/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:59.997697627Z" }, "llmsTxt": { "url": "https://www.fone.me/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:32.136376991Z" }, "pages": [ { "url": "https://www.fone.me/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:28:42.001987885Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" }, { "url": "https://www.fone.me/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:28:44.174787172Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e3b0c44298fc" } ], "mcpTools": { "url": "https://www.fone.me/mcp", "checkedAt": "2026-11-07T01:44:39.315960369Z", "status": "ok", "note": "answered without the initialize handshake", "tools": [ { "name": "find_agents", "title": "Find people and businesses on fone.me", "description": "Search fone.me for people's and businesses' AI agents by what they do or offer (e.g. 'dog walker', 'real estate agent in Miami', 'Spanish tutor'). Returns their fone.me links.", "inputSchema": { "properties": { "limit": { "description": "How many results (1-10). Default 5.", "type": "number" }, "query": { "description": "What you're looking for, in plain words.", "type": "string" } }, "required": [ "query" ], "type": "object" }, "annotations": { "openWorldHint": true, "readOnlyHint": true, "title": "Find people and businesses on fone.me" } }, { "name": "get_agent", "title": "Look up a fone.me agent", "description": "Get who is behind a fone.me link (e.g. fone.me/samspearin) and what their agent can help with, before messaging it.", "inputSchema": { "properties": { "link": { "description": "A fone.me link or name, e.g. 'fone.me/sam' or 'sam'.", "type": "string" } }, "required": [ "link" ], "type": "object" }, "annotations": { "openWorldHint": true, "readOnlyHint": true, "title": "Look up a fone.me agent" } }, { "name": "message_agent", "title": "Message a fone.me agent", "description": "Send a message to the AI agent at a fone.me link and get its reply — ask a question, request a booking or a quote, or leave a message for the person. The conversation continues across calls. Say who you're asking for in on_behalf_of.", "inputSchema": { "properties": { "link": { "description": "A fone.me link or name, e.g. 'fone.me/samspearin'.", "type": "string" }, "message": { "description": "What to say to the agent.", "type": "string" }, "on_behalf_of": { "description": "The name of the person you're asking for (shown to the owner).", "type": "string" } }, "required": [ "link", "message" ], "type": "object" }, "annotations": { "destructiveHint": false, "idempotentHint": false, "openWorldHint": true, "readOnlyHint": false, "title": "Message a fone.me agent" } }, { "name": "add_chat_to_website", "title": "Add an AI chat button to a website", "description": "Get the one-line code that puts a fone.me AI agent on a website: a chat button in the corner where visitors chat, call by voice, or continue on WhatsApp or Telegram, and the agent answers questions, takes messages and booking requests for the owner. Use it when someone building or editing a website (HTML, Next.js, React, WordPress, Shopify, Wix, Squarespace, Webflow, Framer) wants a chatbot, AI receptionist, live chat or contact widget. Free to start. Give the person's fone.me link if they have one.", "inputSchema": { "properties": { "link": { "description": "The site owner's fone.me link, e.g. 'fone.me/joes-plumbing' or 'joes-plumbing'. Leave out if they don't have one yet.", "type": "string" }, "site": { "description": "What the site is built with: html, nextjs, react, wordpress, shopify, wix, squarespace, webflow, framer. Default html.", "type": "string" } }, "type": "object" }, "annotations": { "openWorldHint": true, "readOnlyHint": true, "title": "Add an AI chat button to a website" } } ], "schemaTokens": 725, "changedAt": "2026-11-07T01:44:39.315960369Z", "check": { "checker": "anchor-check/1.0", "totalTokens": 725, "counts": { "error": 0, "note": 1, "warn": 1 }, "findings": [ { "rule": "TC18", "severity": "warn", "tool": "add_chat_to_website", "message": "readOnlyHint is true but the name says \"add\"", "fix": "If it changes anything, readOnlyHint must be false." }, { "rule": "TC24", "severity": "note", "message": "4 of 4 tools have no outputSchema", "fix": "Declare outputSchema for tools that return structured data, and return structuredContent that matches it." } ] } }, "updatedAt": "2026-11-07T19:22:07.71997153Z" } }, "answer": "Pipecat scores 65.2 (B) on agent readiness against fone.me's 28.3 (F), and leads in every scored category.", "b": { "slug": "pipecat", "name": "Pipecat", "vendor": "Daily", "vendorUrl": "https://www.pipecat.ai/", "kind": "framework", "category": "voice-agents", "summary": "Pipecat is Daily's open-source Python framework for real-time voice and multimodal agents, built as pipelines of transport, speech-to-text, LLM and text-to-speech services, with client SDKs and optional hosting on Pipecat Cloud.", "url": "https://www.anchorterminal.com/tools/pipecat", "markdownUrl": "https://www.anchorterminal.com/tools/pipecat.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/pipecat.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/pipecat.json", "dns": "pipecat.grade.anchorterminal.com", "repo": "https://github.com/pipecat-ai/pipecat", "license": "BSD-2-Clause for the framework. Pipecat Cloud is a hosted service under Daily's terms of service", "transports": [], "packages": [ { "registry": "pypi", "name": "pipecat-ai" }, { "registry": "npm", "name": "@pipecat-ai/client-js" } ], "auth": "none", "authNotes": "The framework has no account or key of its own and runs in the developer's process. Each service takes its provider's key, such as `DEEPGRAM_API_KEY` or `CARTESIA_API_KEY`, passed in code. Pipecat Cloud uses public and private API keys as bearer tokens, CLI login and email with a one-time code for the dashboard.", "pricing": "free", "pricingNotes": "Free under BSD-2-Clause, with no signup. The developer pays each model, speech and transport provider. Pipecat Cloud, if used, bills from $0.01 per active agent minute for agent-1x, with Daily PSTN at $0.018 a minute and 1:1 Daily WebRTC voice free (https://www.daily.co/pricing/pipecat-cloud/, read 17 October 2026).", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the framework source, the docs or the Pipecat Cloud pricing page (checked 17 October 2026).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 16314, "npmWeekly": 97617, "pypiWeekly": 302047, "asOf": "2026-10-17" }, "docsUrl": "https://docs.pipecat.ai", "llmsTxt": "https://docs.pipecat.ai/llms.txt", "capabilities": [ "voice.agent", "voice.pipeline", "voice.speech-to-speech", "voice.tools", "voice.telephony", "agent.mcp-client", "agent.multi-agent" ], "tags": [ "framework", "open-source", "self-hosted", "python", "free", "no-card", "bsd-2-clause", "llms-txt", "mcp-client", "pipeline", "speech-to-speech", "telephony", "webrtc", "no-telemetry" ], "lastRelease": "2026-10-28", "graded": true, "anchor": { "graded": true, "score": 65.2, "grade": "B", "agentReady": false, "rank": 428, "ranked": true, "rankOf": 1510, "categoryRank": 9, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 85, "payments": 60, "reliability": 68, "schema": 92, "security": 67, "transparency": 83 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -9, "negativeNotes": [ "2025-11-10 to 2026-06-17. Three published advisories, fixed and between four and eleven months old, so 1 point each. Remote code execution through `pickle.loads()` in the optional, deprecated LivekitFrameSerializer (GHSA-c2jg-5cp7-6wc7, CVE-2025-62373, critical, fixed in 0.0.94 on 10 November 2025, advisory published 23 April 2026), arbitrary file read through the development runner's `/files` endpoint (GHSA-3363-2ph6-35wh, high, fixed in 1.2.0 on 14 May 2026) and unauthenticated call control through the runner's telephony `/ws` endpoint (GHSA-j8cv-x86q-rj85, high, fixed in 1.4.0 on 17 June 2026). The moderate GHSA-hqm2-cfx2-2vgh of 15 October 2026 covers behaviour documented as by design and isn't deducted. https://osv.dev/vulnerability/GHSA-c2jg-5cp7-6wc7, https://osv.dev/vulnerability/GHSA-3363-2ph6-35wh, https://osv.dev/vulnerability/GHSA-j8cv-x86q-rj85", "-3, 26 August to 28 October 2026. pipecat-ai keeps shipping breaking changes in minor releases with no advance notice, while its changelog states semantic versioning. The changelog flags 16 in 1.8.0 (26 August), 4 in 1.9.0, 4 in 1.10.0, 6 in 1.13.0 (18 October, among them `get_llm_invocation_params()` turning async and `BackendOutput` losing `is_final`), 1 in 1.14.0 and 5 in 1.15.0 (28 October, among them several stop strategies now all having to agree before a user turn ends). Repeated breaks in the framework's own package fold into one term. https://github.com/pipecat-ai/pipecat/blob/main/CHANGELOG.md", "-3, 16 to 23 October 2026. 1.13.0 (18 October) fixed OpenAI-compatible provider services sending `OPENAI_API_KEY` to other providers when given no `api_key` (merged on 16 October) and error messages carrying API keys, tokens and signed URLs, and 1.14.0 (23 October) closed a gap in that masking. All three are under Security in the changelog, and OSV lists no advisory for them on 1 November. A credential sent to another provider, fixed and described with no advisory, takes its own term apart from the breaking changes, as terraform-mcp's redirectable bearer token and stackone's unadvised fixes did. https://github.com/pipecat-ai/pipecat/blob/main/CHANGELOG.md" ], "verdict": "A BSD-2-Clause Python framework with dozens of speech, model and transport integrations, an MCP client that filters tools and pins arguments, and nine releases in 90 days. It has no tool-approval step or prompt-injection guidance, and minor releases keep removing and renaming APIs although the changelog states semver.", "bestFor": "Python teams that want to own a voice agent's pipeline, pick each speech and model provider, and host it themselves or on Pipecat Cloud.", "strengths": [ "BSD-2-Clause framework, with 23 speech-to-text, 25 LLM, 31 text-to-speech and 6 speech-to-speech services listed in the README", "Nine releases in the 90 days to 1 November 2026, with a dated Keep a Changelog file and pull-request links", "`MCPClient` takes a tool allowlist, per-tool output filters and fixed arguments hidden from the model", "No telemetry found in the source. OpenTelemetry tracing is off by default and needs an exporter the developer supplies", "Since 1.13.0, OpenAI-compatible provider services require an explicit key, and error messages mask credentials" ], "weaknesses": [ "No tool-approval or confirmation step, and no prompt-injection guidance, for tools that act on a caller's speech", "Up to 1.12.0, OpenAI-compatible provider services sent `OPENAI_API_KEY` to other providers. Fixed in 1.13.0 on 18 October 2026, with no advisory", "Three high or critical advisories fixed since November 2025, in an optional serialiser and the development runner", "Breaking changes ship in minor releases, 16 flagged in 1.8.0 and 5 in 1.15.0, although the changelog says it follows semver", "The optional ai-coustics filter registers a Pipecat identifier with that vendor's SDK, which the docs don't mention" ], "agentNotes": [ "Upgrade to 1.13.0 or later and pass `api_key` explicitly to every OpenAI-compatible service such as Groq, Cerebras or OpenRouter. Earlier versions send `OPENAI_API_KEY` to that provider when no key is given", "Pass `tools_filter` to `MCPClient` so only the tools the call needs reach the model, and use `tools_arguments` for values the model must not choose", "Gate tools that book, pay or send in your own handler. Pipecat has no approval step, and a caller's speech goes straight to the model", "Keep the development runner on localhost. Its `/start`, `/daily` and dial-in webhook endpoints take requests from anyone by design", "Pin a minor version and read the warning-flagged entries in CHANGELOG.md before upgrading. 1.15.0 changed how several user turn stop strategies combine" ], "metrics": { "kind": "library", "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": 65.2 } ], "editorialScores": { "ergonomics": 72, "maintenance": 85, "payments": 60, "reliability": 68, "schema": 92, "security": 67, "transparency": 85 }, "provenanceScore": 80, "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": "pip install pipecat-ai # or: uv tool install \"pipecat-ai[cli]\" \u0026\u0026 pipecat init" }, "letme": { "capability": "https://letme.dev/voice.agent", "tool": "https://letme.dev/pipecat" }, "sameCompany": [ "pipecat-phonellm" ], "area": "voice", "unitPrices": [ { "item": "Pipecat Cloud agent-1x (0.5 vCPU, 1 GB)", "unit": "call-minute", "usd": 0.01, "note": "per active agent minute, reserved agents $0.0005 a minute" }, { "item": "Pipecat Cloud agent-2x (1 vCPU, 2 GB)", "unit": "call-minute", "usd": 0.02, "note": "per active agent minute, reserved agents $0.001 a minute" }, { "item": "Pipecat Cloud agent-3x (1.5 vCPU, 3 GB)", "unit": "call-minute", "usd": 0.03, "note": "per active agent minute, reserved agents $0.0015 a minute" }, { "item": "Daily WebRTC voice and video", "unit": "call-minute", "usd": 0.004, "note": "per participant minute, 1:1 voice sessions on Pipecat Cloud free" }, { "item": "Daily PSTN dial-in or dial-out", "unit": "call-minute", "usd": 0.018, "note": "SIP included, SIP alone $0.003 to $0.02 a minute" }, { "item": "SIP REFER call transfer", "unit": "tx", "usd": 0.2, "note": "per transfer event" }, { "item": "Audio recording", "unit": "audio-minute", "usd": 0.005, "note": "storage $0.003 a minute" } ], "provenance": { "legalEntity": "Daily", "domain": "pipecat.ai", "domainRegistered": "2024-05-01", "endpointOnVendorDomain": null, "terms": "https://www.daily.co/legal/terms-of-service/", "privacy": "https://www.daily.co/legal/privacy/", "statusPage": "https://status.pipecat.daily.co", "changelog": "https://github.com/pipecat-ai/pipecat/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "LICENSE reads 'Copyright (c) 2024–2026, Daily'. The terms of service (last updated 31 March 2025) say Daily and name Pipecat Cloud and Daily's open-source frameworks among its services. The DPA (last updated 1 May 2025) names the company 'Daily, Co.' at 548 Market St., San Francisco.", "RDAP gives pipecat.ai a registration date of 1 May 2024. The docs are at docs.pipecat.ai and the code under GitHub's pipecat-ai organisation.", "security.txt returns 404 on www.pipecat.ai, docs.pipecat.ai and www.daily.co. SECURITY.md and the Pipecat Cloud security guide route reports to an email address at Daily, which the guide says is acknowledged within a week. Daily publishes a responsible disclosure policy with no bounty.", "The privacy policy is effective 6 January 2025. The sub-processor list is dated 1 September 2026.", "The status page covers Pipecat Cloud, not the framework.", "WebFetch refused docs.pipecat.ai and github.com, so docs.pipecat.ai, www.daily.co, status.pipecat.daily.co, developers.cloudflare.com, huggingface.co, pypi.org, api.osv.dev, pypistats.org, repos.ecosyste.ms, issues.ecosyste.ms, the npm registry, the MCP registry and rdap.org were read with curl after their robots.txt. GitHub's own pages answered 403 through the session's proxy." ], "score": 80 }, "requirements": { "setupChecked": true, "complianceChecked": true, "card": "unknown", "freeTier": true, "minutes": 20, "credential": "api-key", "hosting": [ "self-hosted" ], "euResidency": "unknown", "trainsOnData": "no", "zeroRetention": "unknown", "dpa": true, "selfHost": "yes" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/pipecat.json", "live": { "slug": "pipecat", "vendorStatus": { "page": "https://status.pipecat.daily.co", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T19:23:16.830139271Z" }, "versions": [ { "registry": "github", "name": "pipecat-ai/pipecat", "version": "v1.15.0", "released": "2026-10-29", "seenAt": "2026-11-06T23:56:17.95033308Z" }, { "registry": "npm", "name": "@pipecat-ai/client-js", "version": "1.16.0", "seenAt": "2026-11-06T23:56:17.115559884Z" }, { "registry": "pypi", "name": "pipecat-ai", "version": "1.15.0", "released": "2026-10-29", "seenAt": "2026-11-06T23:56:16.870846918Z" } ], "githubStars": 17101, "npmWeekly": 129192, "pypiWeekly": 374140, "securityTxt": { "url": "https://pipecat.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:00:50.311611328Z" }, "llmsTxt": { "url": "https://docs.pipecat.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:38.227872926Z" }, "domain": { "domain": "pipecat.ai", "registered": "2024-05-01", "source": "https://rdap.identitydigital.services/rdap/domain/pipecat.ai", "checkedAt": "2026-11-01T14:20:09.941363148Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/pipecat-ai/pipecat/main/CHANGELOG.md", "kind": "deprecations", "status": 304, "checkedAt": "2026-11-07T14:22:55.571520023Z", "changedAt": "2026-10-30T05:50:02.946504107Z", "fingerprint": "13e9874e9ea5" }, { "url": "https://www.daily.co/pricing/pipecat-cloud/", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:27:45.084757238Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "06f32f71f3dd" } ], "github": { "repo": "pipecat-ai/pipecat", "checkedAt": "2026-11-02T09:16:35.354291053Z", "stars": 16992, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T03:32:17Z", "openIssues": 142, "openPRs": 371, "issuesOpened90d": 199, "issuesClosed90d": 141, "prsMerged90d": 676, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-30T18:11:51Z" }, "advisories": [ { "ghsa": "GHSA-hqm2-cfx2-2vgh", "cve": "CVE-2026-102682", "severity": "medium", "published": "2026-09-29T17:39:30Z" }, { "ghsa": "GHSA-j8cv-x86q-rj85", "cve": "CVE-2026-54695", "severity": "high", "published": "2026-06-17T14:39:37Z" }, { "ghsa": "GHSA-3363-2ph6-35wh", "cve": "CVE-2026-44716", "severity": "high", "published": "2026-05-15T02:17:30Z" }, { "ghsa": "GHSA-c2jg-5cp7-6wc7", "cve": "CVE-2025-62373", "severity": "critical", "published": "2026-04-23T12:55:15Z" } ], "replies": { "sampled": 25, "unanswered": 20, "medianDays": 0 } }, "updatedAt": "2026-11-07T19:23:16.830139271Z" } }, "edges": [ { "by": 62, "category": "maintenance", "leads": "pipecat", "name": "Maintenance \u0026 community", "reasons": { "a": "Closed service. The newest dated change to the agent surface found is the MCP repository github.com/spearisa/fone-me-mcp, created 5 October 2026 with server.json version 1.0.0, 31 days ago (20). The comparison page marked 'Checked October 28, 2026' and the profile lastmods in the sitemap are content, not releases. No changelog, release notes or three dated changes in 90 days (0 of 20). The support page and FAQ draw by script and no support email, forum or community channel was found; responsiveness unchecked (3 of 15). server.json names the server me.fone.www/agents, a namespace that needs proof of the domain, but the official MCP registry could not be read, so presence is scored absent (0 of 15). No package, public code or CI (0 of 10). 20+0+3+0+0 = 23.", "b": "pipecat-ai 1.15.0, dated 28 October 2026 in the changelog and tagged that day, 4 days before the check (30). Nine releases in the 90 days to 1 November, 1.8.0 on 26 August to 1.15.0 (20). Issue and pull-request reply times couldn't be read, since GitHub's pages answer 403, and the 17 October figures came from a third-party copy of GitHub data, now struck. The clone shows 151 pull requests from outside forks merged in the 90 days to 1 November, fixes that cite the issues they close, and a needs-repro workflow that labels issues (13 of 25, was 15). The Python framework and the JavaScript client (`@pipecat-ai/client-js` 1.16.0, tagged 28 October) are current, with client SDKs in six languages (15). CI, coverage, a licence check, a uv lockfile and trusted publishing to PyPI are configured. Dependabot was added on 23 October, for the pinned GitHub Actions only, and a passing main wasn't confirmed (7 of 10). 30 + 20 + 13 + 15 + 7 = 85." }, "scores": { "a": 23, "b": 85 } }, { "by": 61, "category": "schema", "leads": "pipecat", "name": "Schema \u0026 documentation", "reasons": { "a": "MCP reading, since the MCP server is what an outside agent calls. No tool arguments or input schemas are published in llms.txt, the guide pages or the GitHub README, and robots.txt disallows /mcp, so no session was opened and tools/list was not read. Per-link A2A agent cards are machine-readable JSON (protocol 0.3.0, JSONRPC, input and output modes, skills with examples) and server.json names the remote, but neither types the MCP tools (8 of 25). llms.txt is a real document for agents covering the MCP server, A2A, the search API and the widget (10). Each tool has a one-line purpose in llms.txt and the README, and the how-it-works page states what the agent will and won't do; nothing says when not to use a tool (6 of 20). No typed inputs, enums, constraints or required fields published (0 of 15). Example prompts in the README, per-skill examples in agent cards and widget code for eight site builders; no error response is documented (4 of 15). server.json and the agent cards carry version 1.0.0 and the cards a protocol version; no changelog (3 of 15). 8+10+6+0+4+3 = 31.", "b": "Framework reading. Typed Python (py.typed) with an API reference page per service, transport, frame type and utility (25). llms.txt, Markdown copies of each page and llms-full.txt (4.7 MB on 1 November) (10). Guides say when to reach for Flows, multiple LLM agents or a single pipeline, and the error-handling page says which failures are worth retrying. The OpenTelemetry reference now gives `PipelineWorker` defaults of `enable_tracing` False and `enable_turn_tracking` True, matching the 1.15.0 source, so the mismatch the 17 October check found is gone (16 of 20, was 14). Pydantic `Settings` classes per service, a provider-neutral `FunctionSchema`, and an `ErrorCategory` enum (12 of 15). Example folders from function calling and MCP to telephony, and documented error categories and Pipecat Cloud error codes (14 of 15). Dated changelog with pull-request links, towncrier fragments and a migration guide to 1.0 (15). 25 + 10 + 16 + 12 + 14 + 15 = 92." }, "scores": { "a": 31, "b": 92 } }, { "by": 60, "category": "transparency", "leads": "pipecat", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service. Terms of service exist at /terms but draw by script, so their content, governing law and the company they name are unchecked; no company, address or country of incorporation appears on any page read, llms.txt says San Francisco, and the MCP repository has no licence (5 of 30). Data handling was read only from guide pages, which say only the owner sees their calls and messages, calls are transcribed and callers told so, and private categories are withheld. The privacy policy and data-deletion page draw by script, so no retention period, recording statement, DPA or AI-training statement was read (8 of 30). No deprecation policy or dated notices (0). No subprocessors, telephony, model or hosting providers or data locations are named on any page read; the demo agent card's icon is served from Cloudinary (0 of 20). 5+8+0+0 = 13.", "b": "BSD-2-Clause (30). The framework keeps no data. Daily's privacy policy (6 January 2025) keeps personal data while an account is open, the Pipecat Cloud security guide says session data is removed when a session ends, logs are stored by default and administrative API calls are kept a year, and Daily publishes a DPA (1 May 2025) and a sub-processor list (1 September 2026), per the 17 October check. Control-plane data is in the US whatever the agent's region (24 of 30). The changelog has Deprecated sections in most releases, and recent entries name removal in 2.0.0, with a migration guide to 1.0, but no dated removal windows (13 of 20). No telemetry found, and tracing is opt-in, which the OpenTelemetry reference now states too. The optional ai-coustics filter still registers a Pipecat identifier with that vendor's SDK in 1.15.0, which the docs don't mention (18 of 20, was 16). 30 + 24 + 13 + 18 = 85." }, "scores": { "a": 23, "b": 83 } }, { "by": 53, "category": "reliability", "leads": "pipecat", "name": "Reliability", "reasons": { "a": "Hosted reading, for the MCP server and A2A endpoints and the service behind them. No status page is linked from llms.txt, the home page or any guide page read, and https://www.fone.me/status failed to load (0). No readable incident history, so the floor (5). No request rate limit for the MCP server, the search API or A2A is published; the only limits are on the agent's own outbound calls (8 am to 9 pm in the callee's time zone, 'limited per day' with no number), which are not request limits (0 of 15). No 429, overload or retry guidance and no idempotency key for message_agent or message/send (0 of 15). No SLA (0). Nothing on the MCP server, the agent cards or llms.txt is marked beta or preview, and the MCP repository's server.json is version 1.0.0 (10). 0+5+0+0+0+10 = 15.", "b": "Local-software reading of the framework. pipecat-ai installs from PyPI with Python 3.11 or later declared (1.15.0's pyproject), and a compatibility workflow builds it on 3.11 to 3.14 (20). A public tests workflow runs pytest (406 Python files under tests/ in 1.15.0), on pushes to main and on pull requests, with coverage and licence-check jobs, but GitHub's Actions pages weren't readable on 17 October or 1 November, so a green main is not confirmed (15 of 25). The issue tracker couldn't be read, since GitHub's pages answer 403. The 17 October reading of open issues came from a third-party copy of GitHub data, which we no longer use, so it is struck. The clone shows 3,539 commits in the 90 days to 1 November, fixes that cite the issues they close (#6162 on 15 October, #6256 on 20 October, #6410 from an outside contributor on 28 October) and 151 merged pull requests from outside forks, so 8 of 25 on that evidence alone (was 12). Keep a Changelog with dates, semver stated and breaking changes flagged with a warning sign, but minor releases keep carrying them, 16 flagged in 1.8.0, 4 in 1.9.0, 4 in 1.10.0, 6 in 1.13.0, 1 in 1.14.0 and 5 in 1.15.0 (10 of 15). 1.15.0, classed Production/Stable (15). 20 + 15 + 8 + 10 + 15 = 68." }, "scores": { "a": 15, "b": 68 } }, { "by": 43, "category": "ergonomics", "leads": "pipecat", "name": "Agent ergonomics", "reasons": { "a": "MCP reading. Four tools named in llms.txt, a small set, but their definitions were not read, so short of full marks (18 of 25). find_agents searches by what someone does and the search API takes a query; no limit, paging or output-size controls are documented (3 of 20). No error codes or messages documented for the MCP server, the search API or A2A (0 of 20). No readOnlyHint or destructiveHint seen and no idempotency key; the three lookups are read-only by name and description, while message_agent writes to a real person's inbox and continues the conversation across calls (2 of 20). No credentials, no configuration beyond the URL, and few stated inputs; no SDK in any language (6 of 15). 18+3+0+2+6 = 29.", "b": "Framework reading. `MCPClient` registers an MCP server's tools with the LLM, with `tools_filter` to allow only named tools and `tools_arguments` to fix values and hide them from the schema. The repository's streamable HTTP MCP example is about 130 lines of code, most of it the voice pipeline rather than the tool wiring (20 of 25). `tools_output_filters` trims tool results, and context summarisation and Flows context strategies limit what the model sees (15 of 20). Errors carry a category that marks permanent failures, services expose `is_usable`, `ProcessorUnusablePolicy` decides whether a bot ends, and MCP failures return to the model as text (17 of 20). Function calls cancel on interruption by default, with per-tool timeouts and opt-in asynchronous or model-cancellable calls, but there is no idempotency guidance for tools with side effects (10 of 20). A bot needs a transport, speech-to-text, LLM, text-to-speech, VAD and context aggregators wired by hand, which `pipecat init` scaffolds. Server code is Python only, with client SDKs in six languages (10 of 15)." }, "scores": { "a": 29, "b": 72 } }, { "by": 37, "category": "security", "leads": "pipecat", "name": "Security \u0026 auth", "reasons": { "a": "No credential exists for callers. llms.txt gives auth 'none', the README says the server is 'public, like the links themselves', and the two agent cards read declare no security scheme. There is nothing to leak or rotate, but fone.me and an owner can tell callers apart only by the name they give ('Maria via ChatGPT' in the README) and by traffic, and no caller identity or verification is documented (10 of 30). Three of four MCP tools are lookups; message_agent and A2A message/send reach any owner's agent. On the owner's side the vendor says the agent asks before agreeing to anything or spending money, the owner approves what it will say before a call, outbound calls run only 8 am to 9 pm local, pause when reported and stop permanently on request, and the owner can take over any chat. No read-only mode and no confirmation on the caller's side (8 of 20). message_agent returns text generated from what the owner taught the agent, and every agent on the platform reads messages from anyone; the only guidance is the how-it-works statement that the agent keeps relationship status, health, money and address private, with no documented prompt-injection or spam handling for the open channel, and the call-screening page says it does not promise to block calls (4 of 15). Owners see every call and chat with a transcript in one inbox; nothing is logged for the calling agent (8 of 15). /.well-known/security.txt answers with the app shell, and no disclosure policy, bug bounty or certification appears on any page read (0 of 20). 10+8+4+8+0 = 30.", "b": "Framework reading, as for the frameworks category. We found no telemetry in the source, and tracing is off by default and needs an exporter the developer supplies. The two credential flaws the 17 October check found on 1.12.0 are fixed in released versions. 1.13.0 (18 October) makes the services for OpenAI-compatible providers raise an error when given no key instead of falling back to `OPENAI_API_KEY`, and masks API keys, tokens and signed URLs in error messages, and 1.14.0 (23 October) closes a gap in that masking (30 of 30, was 20). No tool-approval or confirmation primitive. `tools_filter` allowlists MCP tools and `tools_arguments` pins values the model cannot change (8 of 20). A caller's speech and MCP tool results go to the model, and we found no prompt-injection guidance in the docs, re-searched in llms-full.txt on 1 November (3 of 15). OpenTelemetry spans per service and tool call, with `FunctionCallObserver` and `LLMLogObserver` for per-call visibility (15). SECURITY.md routes reports to an email address at Daily, and GitHub advisories are published with CVEs and fixed versions, four since April 2026 (OSV, re-read on 1 November, lists no new one). The `OPENAI_API_KEY` fix shipped without an advisory. No security.txt or bug bounty. Daily states SOC 2 Type 2, which isn't scored for a framework (11 of 20). 30 + 8 + 3 + 15 + 11 = 67." }, "scores": { "a": 30, "b": 67 } } ], "facts": [ { "a": "Platform", "b": "Agent framework", "name": "Kind" }, { "a": "Fone", "b": "Daily", "name": "Vendor" }, { "a": "https://www.fone.me/mcp", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "Streamable HTTP", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Freemium", "b": "Free", "name": "Pricing" }, { "a": "not published", "b": "$0.01 per minute of call", "name": "Price for voice agents" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary hosted service. Terms of service at https://www.fone.me/terms, whose text draws by script and could not be read on 5 November 2026; no company is named on any page read. No source, SDK or package is published", "b": "BSD-2-Clause for the framework. Pipecat Cloud is a hosted service under Daily's terms of service", "name": "Licence" }, { "a": "4", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-05", "b": "2026-10-28", "name": "Last release" }, { "a": "couldn't be read", "b": "2025-03-31", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "2025-01-06", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "16k stars, 98k npm/wk, 302k PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Pipecat scores 65.2 (B) on agent readiness against fone.me's 28.3 (F), and leads in every scored category.", "question": "Which is better for AI agents, fone.me or Pipecat?" }, { "answer": "No open-source release is listed for fone.me. Pipecat is open source (BSD-2-Clause for the framework. Pipecat Cloud is a hosted service under Daily's terms of service).", "question": "Are fone.me and Pipecat open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "A hosted endpoint, with nothing to install", "No incidents deducted, where Pipecat loses 9 points for them" ], "goodFor": "Agents acting for a person who need to reach a freelancer's, shop's or small business's own AI agent at its fone.me link to ask a question, request a booking or quote or leave a message, and owners who want an answering agent on a link, WhatsApp, Telegram and a $9.99 number without building one.", "slug": "fone-me", "watchFor": "No tool arguments, input schemas, annotations, error shapes or rate limits are published for the MCP server or A2A endpoints" }, { "aheadOn": [ "Reliability, 68 against 15", "Schema \u0026 documentation, 92 against 31", "Agent ergonomics, 72 against 29", "Security \u0026 auth, 67 against 30", "Payments \u0026 pricing, 60 against 50", "Maintenance \u0026 community, 85 against 23", "Transparency \u0026 trust, 83 against 23" ], "also": [ "Free to start without a card", "Open source" ], "goodFor": "Python teams that want to own a voice agent's pipeline, pick each speech and model provider, and host it themselves or on Pipecat Cloud.", "slug": "pipecat", "watchFor": "No tool-approval or confirmation step, and no prompt-injection guidance, for tools that act on a caller's speech" } ], "history": { "fone-me": null, "pipecat": [ { "causes": [ "security", "product", "correction", "event" ], "date": "2026-11-01", "delta": -3.8, "from": 69, "fromGrade": "B", "to": 65.2, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.1, "from": 69.1, "fromGrade": "B", "to": 69, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 68.9, "fromGrade": "B", "to": 69.1, "toGrade": "B" } ] }, "job": { "capability": "voice.agent", "name": "Voice agents" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-fone-me.json", "title": "Amazon Nova 2 Sonic vs fone.me", "url": "https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-fone-me" }, { "json": "https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-pipecat.json", "title": "Amazon Nova 2 Sonic vs Pipecat", "url": "https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-fone-me.json", "title": "AssemblyAI Voice Agent API vs fone.me", "url": "https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-fone-me" }, { "json": "https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-pipecat.json", "title": "AssemblyAI Voice Agent API vs Pipecat", "url": "https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/bland-ai-vs-fone-me.json", "title": "Bland AI API + MCP vs fone.me", "url": "https://www.anchorterminal.com/compare/bland-ai-vs-fone-me" }, { "json": "https://www.anchorterminal.com/compare/bland-ai-vs-pipecat.json", "title": "Bland AI API + MCP vs Pipecat", "url": "https://www.anchorterminal.com/compare/bland-ai-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/bolna-vs-fone-me.json", "title": "Bolna API + MCP vs fone.me", "url": "https://www.anchorterminal.com/compare/bolna-vs-fone-me" }, { "json": "https://www.anchorterminal.com/compare/bolna-vs-pipecat.json", "title": "Bolna API + MCP vs Pipecat", "url": "https://www.anchorterminal.com/compare/bolna-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-fone-me.json", "title": "Deepgram Voice Agent API vs fone.me", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-fone-me" }, { "json": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-pipecat.json", "title": "Deepgram Voice Agent API vs Pipecat", "url": "https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-fone-me.json", "title": "ElevenLabs Agents API + MCP vs fone.me", "url": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-fone-me" }, { "json": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-pipecat.json", "title": "ElevenLabs Agents API + MCP vs Pipecat", "url": "https://www.anchorterminal.com/compare/elevenlabs-agents-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-gemini-live.json", "title": "fone.me vs Gemini Live API", "url": "https://www.anchorterminal.com/compare/fone-me-vs-gemini-live" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-gpt-live.json", "title": "fone.me vs GPT-Live", "url": "https://www.anchorterminal.com/compare/fone-me-vs-gpt-live" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-harmony-ai.json", "title": "fone.me vs Harmony.ai", "url": "https://www.anchorterminal.com/compare/fone-me-vs-harmony-ai" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-hume-evi.json", "title": "fone.me vs Hume EVI (Empathic Voice Interface)", "url": "https://www.anchorterminal.com/compare/fone-me-vs-hume-evi" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-inworld-realtime.json", "title": "fone.me vs Inworld Realtime API", "url": "https://www.anchorterminal.com/compare/fone-me-vs-inworld-realtime" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-livekit-agents.json", "title": "fone.me vs LiveKit Agents", "url": "https://www.anchorterminal.com/compare/fone-me-vs-livekit-agents" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-openai-realtime.json", "title": "fone.me vs OpenAI Realtime API", "url": "https://www.anchorterminal.com/compare/fone-me-vs-openai-realtime" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-placecall.json", "title": "fone.me vs PlaceCall", "url": "https://www.anchorterminal.com/compare/fone-me-vs-placecall" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-retell-ai.json", "title": "fone.me vs Retell AI API + MCP", "url": "https://www.anchorterminal.com/compare/fone-me-vs-retell-ai" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-rime-prism.json", "title": "fone.me vs Rime Prism", "url": "https://www.anchorterminal.com/compare/fone-me-vs-rime-prism" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-synthflow.json", "title": "fone.me vs Synthflow API + MCP", "url": "https://www.anchorterminal.com/compare/fone-me-vs-synthflow" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-ultravox.json", "title": "fone.me vs Ultravox Realtime API", "url": "https://www.anchorterminal.com/compare/fone-me-vs-ultravox" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-vaani-voice.json", "title": "fone.me vs Vaani Developer Platform", "url": "https://www.anchorterminal.com/compare/fone-me-vs-vaani-voice" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-vapi.json", "title": "fone.me vs Vapi API + MCP", "url": "https://www.anchorterminal.com/compare/fone-me-vs-vapi" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-vocily.json", "title": "fone.me vs Vocily AI", "url": "https://www.anchorterminal.com/compare/fone-me-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/fone-me-vs-vogent.json", "title": "fone.me vs Vogent API", "url": "https://www.anchorterminal.com/compare/fone-me-vs-vogent" }, { "json": "https://www.anchorterminal.com/compare/gemini-live-vs-pipecat.json", "title": "Gemini Live API vs Pipecat", "url": "https://www.anchorterminal.com/compare/gemini-live-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/harmony-ai-vs-pipecat.json", "title": "Harmony.ai vs Pipecat", "url": "https://www.anchorterminal.com/compare/harmony-ai-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/hume-evi-vs-pipecat.json", "title": "Hume EVI (Empathic Voice Interface) vs Pipecat", "url": "https://www.anchorterminal.com/compare/hume-evi-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat.json", "title": "Inworld Realtime API vs Pipecat", "url": "https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/livekit-agents-vs-pipecat.json", "title": "LiveKit Agents vs Pipecat", "url": "https://www.anchorterminal.com/compare/livekit-agents-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/openai-realtime-vs-pipecat.json", "title": "OpenAI Realtime API vs Pipecat", "url": "https://www.anchorterminal.com/compare/openai-realtime-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-placecall.json", "title": "Pipecat vs PlaceCall", "url": "https://www.anchorterminal.com/compare/pipecat-vs-placecall" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-retell-ai.json", "title": "Pipecat vs Retell AI API + MCP", "url": "https://www.anchorterminal.com/compare/pipecat-vs-retell-ai" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-rime-prism.json", "title": "Pipecat vs Rime Prism", "url": "https://www.anchorterminal.com/compare/pipecat-vs-rime-prism" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-synthflow.json", "title": "Pipecat vs Synthflow API + MCP", "url": "https://www.anchorterminal.com/compare/pipecat-vs-synthflow" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-ultravox.json", "title": "Pipecat vs Ultravox Realtime API", "url": "https://www.anchorterminal.com/compare/pipecat-vs-ultravox" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-vaani-voice.json", "title": "Pipecat vs Vaani Developer Platform", "url": "https://www.anchorterminal.com/compare/pipecat-vs-vaani-voice" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-vapi.json", "title": "Pipecat vs Vapi API + MCP", "url": "https://www.anchorterminal.com/compare/pipecat-vs-vapi" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-vocily.json", "title": "Pipecat vs Vocily AI", "url": "https://www.anchorterminal.com/compare/pipecat-vs-vocily" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-vogent.json", "title": "Pipecat vs Vogent API", "url": "https://www.anchorterminal.com/compare/pipecat-vs-vogent" }, { "json": "https://www.anchorterminal.com/compare/cuelight-vs-pipecat.json", "title": "CueLight vs Pipecat", "url": "https://www.anchorterminal.com/compare/cuelight-vs-pipecat" }, { "json": "https://www.anchorterminal.com/compare/pipecat-vs-pipecat-phonellm.json", "title": "Pipecat vs Pipecat PhoneLLM", "url": "https://www.anchorterminal.com/compare/pipecat-vs-pipecat-phonellm" }, { "json": "https://www.anchorterminal.com/compare/gpt-live-vs-pipecat.json", "title": "GPT-Live vs Pipecat", "url": "https://www.anchorterminal.com/compare/gpt-live-vs-pipecat" } ], "panel": null, "scores": [ { "by": 53, "edge": "pipecat", "fone-me": 15, "key": "reliability", "name": "Reliability", "pipecat": 68, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 61, "edge": "pipecat", "fone-me": 31, "key": "schema", "name": "Schema \u0026 documentation", "pipecat": 92, "weight": 13 }, { "by": 43, "edge": "pipecat", "fone-me": 29, "key": "ergonomics", "name": "Agent ergonomics", "pipecat": 72, "weight": 13 }, { "by": 37, "edge": "pipecat", "fone-me": 30, "key": "security", "name": "Security \u0026 auth", "pipecat": 67, "weight": 14 }, { "by": 10, "edge": "pipecat", "fone-me": 50, "key": "payments", "name": "Payments \u0026 pricing", "pipecat": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 62, "edge": "pipecat", "fone-me": 23, "key": "maintenance", "name": "Maintenance \u0026 community", "pipecat": 85, "weight": 7 }, { "by": 60, "edge": "pipecat", "fone-me": 23, "key": "transparency", "name": "Transparency \u0026 trust", "pipecat": 83, "weight": 7 } ], "summary": "Pipecat scores 65.2 (B) on agent readiness against fone.me's 28.3 (F), and leads in every scored category. Both do voice agents.", "tasks": null, "tutorials": [], "verdicts": { "fone-me": "Any agent can find a fone.me link and message its owner's agent through a keyless MCP server or A2A, with no sign-up or cost, and owners see every conversation in one inbox. Tool schemas, rate limits and abuse controls for that open channel are unpublished, the terms and privacy policy draw by script, and no company is named.", "pipecat": "A BSD-2-Clause Python framework with dozens of speech, model and transport integrations, an MCP client that filters tools and pins arguments, and nine releases in 90 days. It has no tool-approval step or prompt-injection guidance, and minor releases keep removing and renaming APIs although the changelog states semver." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/fone-me-vs-pipecat", "json": "https://www.anchorterminal.com/compare/fone-me-vs-pipecat.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/fone-me-vs-pipecat.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/fone-me-vs-pipecat.min.md" }, "markdown": "Pipecat scores 65.2 (B) on agent readiness against fone.me's 28.3 (F), and leads in every scored category. Both do voice agents.\n\n- fone.me: grade F, 28.3/100, rank #1429 of 1510. Markdown https://www.anchorterminal.com/tools/fone-me.md · JSON https://www.anchorterminal.com/api/v1/tools/fone-me.json\n- Pipecat: grade B, 65.2/100, rank #428 of 1510. Markdown https://www.anchorterminal.com/tools/pipecat.md · JSON https://www.anchorterminal.com/api/v1/tools/pipecat.json\n- Best conversational voice-agent APIs: https://www.anchorterminal.com/best/voice-agents/index.md\n- All 518 voice agents comparisons: https://www.anchorterminal.com/compare/voice-agents/index.md\n\n## Which one, for what\n\n### fone.me (F)\n\nGood for: Agents acting for a person who need to reach a freelancer's, shop's or small business's own AI agent at its fone.me link to ask a question, request a booking or quote or leave a message, and owners who want an answering agent on a link, WhatsApp, Telegram and a $9.99 number without building one.\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- No incidents deducted, where Pipecat loses 9 points for them\n\nWatch for: No tool arguments, input schemas, annotations, error shapes or rate limits are published for the MCP server or A2A endpoints\n\n### Pipecat (B)\n\nGood for: Python teams that want to own a voice agent's pipeline, pick each speech and model provider, and host it themselves or on Pipecat Cloud.\n\nAhead on:\n- Reliability, 68 against 15\n- Schema \u0026 documentation, 92 against 31\n- Agent ergonomics, 72 against 29\n- Security \u0026 auth, 67 against 30\n- Payments \u0026 pricing, 60 against 50\n- Maintenance \u0026 community, 85 against 23\n- Transparency \u0026 trust, 83 against 23\n\nAlso in its favour:\n- Free to start without a card\n- Open source\n\nWatch for: No tool-approval or confirmation step, and no prompt-injection guidance, for tools that act on a caller's speech\n\n\n## Why the edge\n\n### Maintenance \u0026 community: Pipecat +62\n\n- fone.me (23): Closed service. The newest dated change to the agent surface found is the MCP repository github.com/spearisa/fone-me-mcp, created 5 October 2026 with server.json version 1.0.0, 31 days ago (20). The comparison page marked 'Checked October 28, 2026' and the profile lastmods in the sitemap are content, not releases. No changelog, release notes or three dated changes in 90 days (0 of 20). The support page and FAQ draw by script and no support email, forum or community channel was found; responsiveness unchecked (3 of 15). server.json names the server me.fone.www/agents, a namespace that needs proof of the domain, but the official MCP registry could not be read, so presence is scored absent (0 of 15). No package, public code or CI (0 of 10). 20+0+3+0+0 = 23.\n- Pipecat (85): pipecat-ai 1.15.0, dated 28 October 2026 in the changelog and tagged that day, 4 days before the check (30). Nine releases in the 90 days to 1 November, 1.8.0 on 26 August to 1.15.0 (20). Issue and pull-request reply times couldn't be read, since GitHub's pages answer 403, and the 17 October figures came from a third-party copy of GitHub data, now struck. The clone shows 151 pull requests from outside forks merged in the 90 days to 1 November, fixes that cite the issues they close, and a needs-repro workflow that labels issues (13 of 25, was 15). The Python framework and the JavaScript client (`@pipecat-ai/client-js` 1.16.0, tagged 28 October) are current, with client SDKs in six languages (15). CI, coverage, a licence check, a uv lockfile and trusted publishing to PyPI are configured. Dependabot was added on 23 October, for the pinned GitHub Actions only, and a passing main wasn't confirmed (7 of 10). 30 + 20 + 13 + 15 + 7 = 85.\n\n### Schema \u0026 documentation: Pipecat +61\n\n- fone.me (31): MCP reading, since the MCP server is what an outside agent calls. No tool arguments or input schemas are published in llms.txt, the guide pages or the GitHub README, and robots.txt disallows /mcp, so no session was opened and tools/list was not read. Per-link A2A agent cards are machine-readable JSON (protocol 0.3.0, JSONRPC, input and output modes, skills with examples) and server.json names the remote, but neither types the MCP tools (8 of 25). llms.txt is a real document for agents covering the MCP server, A2A, the search API and the widget (10). Each tool has a one-line purpose in llms.txt and the README, and the how-it-works page states what the agent will and won't do; nothing says when not to use a tool (6 of 20). No typed inputs, enums, constraints or required fields published (0 of 15). Example prompts in the README, per-skill examples in agent cards and widget code for eight site builders; no error response is documented (4 of 15). server.json and the agent cards carry version 1.0.0 and the cards a protocol version; no changelog (3 of 15). 8+10+6+0+4+3 = 31.\n- Pipecat (92): Framework reading. Typed Python (py.typed) with an API reference page per service, transport, frame type and utility (25). llms.txt, Markdown copies of each page and llms-full.txt (4.7 MB on 1 November) (10). Guides say when to reach for Flows, multiple LLM agents or a single pipeline, and the error-handling page says which failures are worth retrying. The OpenTelemetry reference now gives `PipelineWorker` defaults of `enable_tracing` False and `enable_turn_tracking` True, matching the 1.15.0 source, so the mismatch the 17 October check found is gone (16 of 20, was 14). Pydantic `Settings` classes per service, a provider-neutral `FunctionSchema`, and an `ErrorCategory` enum (12 of 15). Example folders from function calling and MCP to telephony, and documented error categories and Pipecat Cloud error codes (14 of 15). Dated changelog with pull-request links, towncrier fragments and a migration guide to 1.0 (15). 25 + 10 + 16 + 12 + 14 + 15 = 92.\n\n### Transparency \u0026 trust: Pipecat +60\n\n- fone.me (23): Closed service. Terms of service exist at /terms but draw by script, so their content, governing law and the company they name are unchecked; no company, address or country of incorporation appears on any page read, llms.txt says San Francisco, and the MCP repository has no licence (5 of 30). Data handling was read only from guide pages, which say only the owner sees their calls and messages, calls are transcribed and callers told so, and private categories are withheld. The privacy policy and data-deletion page draw by script, so no retention period, recording statement, DPA or AI-training statement was read (8 of 30). No deprecation policy or dated notices (0). No subprocessors, telephony, model or hosting providers or data locations are named on any page read; the demo agent card's icon is served from Cloudinary (0 of 20). 5+8+0+0 = 13.\n- Pipecat (83): BSD-2-Clause (30). The framework keeps no data. Daily's privacy policy (6 January 2025) keeps personal data while an account is open, the Pipecat Cloud security guide says session data is removed when a session ends, logs are stored by default and administrative API calls are kept a year, and Daily publishes a DPA (1 May 2025) and a sub-processor list (1 September 2026), per the 17 October check. Control-plane data is in the US whatever the agent's region (24 of 30). The changelog has Deprecated sections in most releases, and recent entries name removal in 2.0.0, with a migration guide to 1.0, but no dated removal windows (13 of 20). No telemetry found, and tracing is opt-in, which the OpenTelemetry reference now states too. The optional ai-coustics filter still registers a Pipecat identifier with that vendor's SDK in 1.15.0, which the docs don't mention (18 of 20, was 16). 30 + 24 + 13 + 18 = 85.\n\n### Reliability: Pipecat +53\n\n- fone.me (15): Hosted reading, for the MCP server and A2A endpoints and the service behind them. No status page is linked from llms.txt, the home page or any guide page read, and https://www.fone.me/status failed to load (0). No readable incident history, so the floor (5). No request rate limit for the MCP server, the search API or A2A is published; the only limits are on the agent's own outbound calls (8 am to 9 pm in the callee's time zone, 'limited per day' with no number), which are not request limits (0 of 15). No 429, overload or retry guidance and no idempotency key for message_agent or message/send (0 of 15). No SLA (0). Nothing on the MCP server, the agent cards or llms.txt is marked beta or preview, and the MCP repository's server.json is version 1.0.0 (10). 0+5+0+0+0+10 = 15.\n- Pipecat (68): Local-software reading of the framework. pipecat-ai installs from PyPI with Python 3.11 or later declared (1.15.0's pyproject), and a compatibility workflow builds it on 3.11 to 3.14 (20). A public tests workflow runs pytest (406 Python files under tests/ in 1.15.0), on pushes to main and on pull requests, with coverage and licence-check jobs, but GitHub's Actions pages weren't readable on 17 October or 1 November, so a green main is not confirmed (15 of 25). The issue tracker couldn't be read, since GitHub's pages answer 403. The 17 October reading of open issues came from a third-party copy of GitHub data, which we no longer use, so it is struck. The clone shows 3,539 commits in the 90 days to 1 November, fixes that cite the issues they close (#6162 on 15 October, #6256 on 20 October, #6410 from an outside contributor on 28 October) and 151 merged pull requests from outside forks, so 8 of 25 on that evidence alone (was 12). Keep a Changelog with dates, semver stated and breaking changes flagged with a warning sign, but minor releases keep carrying them, 16 flagged in 1.8.0, 4 in 1.9.0, 4 in 1.10.0, 6 in 1.13.0, 1 in 1.14.0 and 5 in 1.15.0 (10 of 15). 1.15.0, classed Production/Stable (15). 20 + 15 + 8 + 10 + 15 = 68.\n\n### Agent ergonomics: Pipecat +43\n\n- fone.me (29): MCP reading. Four tools named in llms.txt, a small set, but their definitions were not read, so short of full marks (18 of 25). find_agents searches by what someone does and the search API takes a query; no limit, paging or output-size controls are documented (3 of 20). No error codes or messages documented for the MCP server, the search API or A2A (0 of 20). No readOnlyHint or destructiveHint seen and no idempotency key; the three lookups are read-only by name and description, while message_agent writes to a real person's inbox and continues the conversation across calls (2 of 20). No credentials, no configuration beyond the URL, and few stated inputs; no SDK in any language (6 of 15). 18+3+0+2+6 = 29.\n- Pipecat (72): Framework reading. `MCPClient` registers an MCP server's tools with the LLM, with `tools_filter` to allow only named tools and `tools_arguments` to fix values and hide them from the schema. The repository's streamable HTTP MCP example is about 130 lines of code, most of it the voice pipeline rather than the tool wiring (20 of 25). `tools_output_filters` trims tool results, and context summarisation and Flows context strategies limit what the model sees (15 of 20). Errors carry a category that marks permanent failures, services expose `is_usable`, `ProcessorUnusablePolicy` decides whether a bot ends, and MCP failures return to the model as text (17 of 20). Function calls cancel on interruption by default, with per-tool timeouts and opt-in asynchronous or model-cancellable calls, but there is no idempotency guidance for tools with side effects (10 of 20). A bot needs a transport, speech-to-text, LLM, text-to-speech, VAD and context aggregators wired by hand, which `pipecat init` scaffolds. Server code is Python only, with client SDKs in six languages (10 of 15).\n\n### Security \u0026 auth: Pipecat +37\n\n- fone.me (30): No credential exists for callers. llms.txt gives auth 'none', the README says the server is 'public, like the links themselves', and the two agent cards read declare no security scheme. There is nothing to leak or rotate, but fone.me and an owner can tell callers apart only by the name they give ('Maria via ChatGPT' in the README) and by traffic, and no caller identity or verification is documented (10 of 30). Three of four MCP tools are lookups; message_agent and A2A message/send reach any owner's agent. On the owner's side the vendor says the agent asks before agreeing to anything or spending money, the owner approves what it will say before a call, outbound calls run only 8 am to 9 pm local, pause when reported and stop permanently on request, and the owner can take over any chat. No read-only mode and no confirmation on the caller's side (8 of 20). message_agent returns text generated from what the owner taught the agent, and every agent on the platform reads messages from anyone; the only guidance is the how-it-works statement that the agent keeps relationship status, health, money and address private, with no documented prompt-injection or spam handling for the open channel, and the call-screening page says it does not promise to block calls (4 of 15). Owners see every call and chat with a transcript in one inbox; nothing is logged for the calling agent (8 of 15). /.well-known/security.txt answers with the app shell, and no disclosure policy, bug bounty or certification appears on any page read (0 of 20). 10+8+4+8+0 = 30.\n- Pipecat (67): Framework reading, as for the frameworks category. We found no telemetry in the source, and tracing is off by default and needs an exporter the developer supplies. The two credential flaws the 17 October check found on 1.12.0 are fixed in released versions. 1.13.0 (18 October) makes the services for OpenAI-compatible providers raise an error when given no key instead of falling back to `OPENAI_API_KEY`, and masks API keys, tokens and signed URLs in error messages, and 1.14.0 (23 October) closes a gap in that masking (30 of 30, was 20). No tool-approval or confirmation primitive. `tools_filter` allowlists MCP tools and `tools_arguments` pins values the model cannot change (8 of 20). A caller's speech and MCP tool results go to the model, and we found no prompt-injection guidance in the docs, re-searched in llms-full.txt on 1 November (3 of 15). OpenTelemetry spans per service and tool call, with `FunctionCallObserver` and `LLMLogObserver` for per-call visibility (15). SECURITY.md routes reports to an email address at Daily, and GitHub advisories are published with CVEs and fixed versions, four since April 2026 (OSV, re-read on 1 November, lists no new one). The `OPENAI_API_KEY` fix shipped without an advisory. No security.txt or bug bounty. Daily states SOC 2 Type 2, which isn't scored for a framework (11 of 20). 30 + 8 + 3 + 15 + 11 = 67.\n\n## Score by category\n\n| Category | Weight | fone.me | Pipecat | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 15 | 68 | Pipecat +53 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 31 | 92 | Pipecat +61 |\n| Agent ergonomics | 13% (16.2 this run) | 29 | 72 | Pipecat +43 |\n| Security \u0026 auth | 14% (17.5 this run) | 30 | 67 | Pipecat +37 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 50 | 60 | Pipecat +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 23 | 85 | Pipecat +62 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 23 | 83 | Pipecat +60 |\n| Negative events | ≤15 | 0 | -9 | |\n| **Total** | | **28.3 · F** | **65.2 · B** | |\n\n## Facts side by side\n\n| Fact | fone.me | Pipecat |\n| --- | --- | --- |\n| Kind | Platform | Agent framework |\n| Vendor | Fone | Daily |\n| Hosted endpoint | `https://www.fone.me/mcp` | no (local only) |\n| Transports | Streamable HTTP | |\n| Auth | None | None |\n| Pricing | Freemium | Free |\n| Price for voice agents | not published | $0.01 per minute of call |\n| x402 | no | no |\n| Licence | Proprietary hosted service. Terms of service at https://www.fone.me/terms, whose text draws by script and could not be read on 5 November 2026; no company is named on any page read. No source, SDK or package is published | BSD-2-Clause for the framework. Pipecat Cloud is a hosted service under Daily's terms of service |\n| Tools exposed | 4 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-05 | 2026-10-28 |\n| Terms last updated | couldn't be read | 2025-03-31 |\n| Privacy policy last updated | couldn't be read | 2025-01-06 |\n| Customer content may train models | couldn't be read | not found in the text |\n| Terms restrict automated access | couldn't be read | not found in the text |\n| Terms restrict benchmarking | couldn't be read | not found in the text |\n| Terms or service can change without notice | couldn't be read | not found in the text |\n| Arbitration or class-action waiver | couldn't be read | not found in the text |\n| Popularity | none | 16k stars, 98k npm/wk, 302k PyPI/wk |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### fone.me\n\nNo score change since it was listed.\n\n### Pipecat\n\n- -3.8 on 1 November 2026: security, product, correction, negative event\n- -0.1 on 30 October 2026: checklist\n- +0.2 on 27 October 2026: checklist\n\n## Verdicts\n\n**fone.me.** Any agent can find a fone.me link and message its owner's agent through a keyless MCP server or A2A, with no sign-up or cost, and owners see every conversation in one inbox. Tool schemas, rate limits and abuse controls for that open channel are unpublished, the terms and privacy policy draw by script, and no company is named.\n\n**Pipecat.** A BSD-2-Clause Python framework with dozens of speech, model and transport integrations, an MCP client that filters tools and pins arguments, and nine releases in 90 days. It has no tool-approval step or prompt-injection guidance, and minor releases keep removing and renaming APIs although the changelog states semver.\n\n## Before you call either\n\n### fone.me\n\n1. Connect to https://www.fone.me/mcp with no credentials; use find_agents or get_agent before message_agent so the message goes to the right person's link.\n2. Say who you are acting for in every message_agent call; the owner reads it in an inbox as a named conversation, and conversations continue across calls.\n3. Treat replies as the owner's agent speaking from what it was taught, not a commitment; the vendor says it asks its owner before agreeing to anything or spending money.\n4. Read a link's agent card at /{link}/.well-known/agent-card.json for its skills before using A2A message/send at /{link}/a2a.\n5. Don't send personal or payment details through message_agent; no retention or privacy terms for agent-to-agent messages could be read.\n\n### Pipecat\n\n1. Upgrade to 1.13.0 or later and pass `api_key` explicitly to every OpenAI-compatible service such as Groq, Cerebras or OpenRouter. Earlier versions send `OPENAI_API_KEY` to that provider when no key is given\n2. Pass `tools_filter` to `MCPClient` so only the tools the call needs reach the model, and use `tools_arguments` for values the model must not choose\n3. Gate tools that book, pay or send in your own handler. Pipecat has no approval step, and a caller's speech goes straight to the model\n4. Keep the development runner on localhost. Its `/start`, `/daily` and dial-in webhook endpoints take requests from anyone by design\n5. Pin a minor version and read the warning-flagged entries in CHANGELOG.md before upgrading. 1.15.0 changed how several user turn stop strategies combine\n\n## Questions\n\n### Which is better for AI agents, fone.me or Pipecat?\n\nPipecat scores 65.2 (B) on agent readiness against fone.me's 28.3 (F), and leads in every scored category.\n\n### Are fone.me and Pipecat open source?\n\nNo open-source release is listed for fone.me. Pipecat is open source (BSD-2-Clause for the framework. Pipecat Cloud is a hosted service under Daily's terms of service).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/fone-me-vs-pipecat.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fone-me-vs-pipecat.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"fone-me\", \"b\": \"pipecat\"}`. From a terminal: `anchor compare fone-me pipecat`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fone-me.json and https://www.anchorterminal.com/api/v1/tools/pipecat.json\n\n## Other comparisons with fone.me or Pipecat\n\n- [Amazon Nova 2 Sonic vs fone.me](https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-fone-me.md)\n- [Amazon Nova 2 Sonic vs Pipecat](https://www.anchorterminal.com/compare/amazon-nova-sonic-vs-pipecat.md)\n- [AssemblyAI Voice Agent API vs fone.me](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-fone-me.md)\n- [AssemblyAI Voice Agent API vs Pipecat](https://www.anchorterminal.com/compare/assemblyai-voice-agent-vs-pipecat.md)\n- [Bland AI API + MCP vs fone.me](https://www.anchorterminal.com/compare/bland-ai-vs-fone-me.md)\n- [Bland AI API + MCP vs Pipecat](https://www.anchorterminal.com/compare/bland-ai-vs-pipecat.md)\n- [Bolna API + MCP vs fone.me](https://www.anchorterminal.com/compare/bolna-vs-fone-me.md)\n- [Bolna API + MCP vs Pipecat](https://www.anchorterminal.com/compare/bolna-vs-pipecat.md)\n- [Deepgram Voice Agent API vs fone.me](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-fone-me.md)\n- [Deepgram Voice Agent API vs Pipecat](https://www.anchorterminal.com/compare/deepgram-voice-agent-vs-pipecat.md)\n- [ElevenLabs Agents API + MCP vs fone.me](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-fone-me.md)\n- [ElevenLabs Agents API + MCP vs Pipecat](https://www.anchorterminal.com/compare/elevenlabs-agents-vs-pipecat.md)\n- [fone.me vs Gemini Live API](https://www.anchorterminal.com/compare/fone-me-vs-gemini-live.md)\n- [fone.me vs GPT-Live](https://www.anchorterminal.com/compare/fone-me-vs-gpt-live.md)\n- [fone.me vs Harmony.ai](https://www.anchorterminal.com/compare/fone-me-vs-harmony-ai.md)\n- [fone.me vs Hume EVI (Empathic Voice Interface)](https://www.anchorterminal.com/compare/fone-me-vs-hume-evi.md)\n- [fone.me vs Inworld Realtime API](https://www.anchorterminal.com/compare/fone-me-vs-inworld-realtime.md)\n- [fone.me vs LiveKit Agents](https://www.anchorterminal.com/compare/fone-me-vs-livekit-agents.md)\n- [fone.me vs OpenAI Realtime API](https://www.anchorterminal.com/compare/fone-me-vs-openai-realtime.md)\n- [fone.me vs PlaceCall](https://www.anchorterminal.com/compare/fone-me-vs-placecall.md)\n- [fone.me vs Retell AI API + MCP](https://www.anchorterminal.com/compare/fone-me-vs-retell-ai.md)\n- [fone.me vs Rime Prism](https://www.anchorterminal.com/compare/fone-me-vs-rime-prism.md)\n- [fone.me vs Synthflow API + MCP](https://www.anchorterminal.com/compare/fone-me-vs-synthflow.md)\n- [fone.me vs Ultravox Realtime API](https://www.anchorterminal.com/compare/fone-me-vs-ultravox.md)\n- [fone.me vs Vaani Developer Platform](https://www.anchorterminal.com/compare/fone-me-vs-vaani-voice.md)\n- [fone.me vs Vapi API + MCP](https://www.anchorterminal.com/compare/fone-me-vs-vapi.md)\n- [fone.me vs Vocily AI](https://www.anchorterminal.com/compare/fone-me-vs-vocily.md)\n- [fone.me vs Vogent API](https://www.anchorterminal.com/compare/fone-me-vs-vogent.md)\n- [Gemini Live API vs Pipecat](https://www.anchorterminal.com/compare/gemini-live-vs-pipecat.md)\n- [Harmony.ai vs Pipecat](https://www.anchorterminal.com/compare/harmony-ai-vs-pipecat.md)\n- [Hume EVI (Empathic Voice Interface) vs Pipecat](https://www.anchorterminal.com/compare/hume-evi-vs-pipecat.md)\n- [Inworld Realtime API vs Pipecat](https://www.anchorterminal.com/compare/inworld-realtime-vs-pipecat.md)\n- [LiveKit Agents vs Pipecat](https://www.anchorterminal.com/compare/livekit-agents-vs-pipecat.md)\n- [OpenAI Realtime API vs Pipecat](https://www.anchorterminal.com/compare/openai-realtime-vs-pipecat.md)\n- [Pipecat vs PlaceCall](https://www.anchorterminal.com/compare/pipecat-vs-placecall.md)\n- [Pipecat vs Retell AI API + MCP](https://www.anchorterminal.com/compare/pipecat-vs-retell-ai.md)\n- [Pipecat vs Rime Prism](https://www.anchorterminal.com/compare/pipecat-vs-rime-prism.md)\n- [Pipecat vs Synthflow API + MCP](https://www.anchorterminal.com/compare/pipecat-vs-synthflow.md)\n- [Pipecat vs Ultravox Realtime API](https://www.anchorterminal.com/compare/pipecat-vs-ultravox.md)\n- [Pipecat vs Vaani Developer Platform](https://www.anchorterminal.com/compare/pipecat-vs-vaani-voice.md)\n- [Pipecat vs Vapi API + MCP](https://www.anchorterminal.com/compare/pipecat-vs-vapi.md)\n- [Pipecat vs Vocily AI](https://www.anchorterminal.com/compare/pipecat-vs-vocily.md)\n- [Pipecat vs Vogent API](https://www.anchorterminal.com/compare/pipecat-vs-vogent.md)\n- [CueLight vs Pipecat](https://www.anchorterminal.com/compare/cuelight-vs-pipecat.md)\n- [Pipecat vs Pipecat PhoneLLM](https://www.anchorterminal.com/compare/pipecat-vs-pipecat-phonellm.md)\n- [GPT-Live vs Pipecat](https://www.anchorterminal.com/compare/gpt-live-vs-pipecat.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "fone.me vs Pipecat", "url": "" } ], "description": "Pipecat scores 65.2 (B) to fone.me's 28.3 (F) for voice agents. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "fone.me F 28.3", "Pipecat B 65.2", "scores" ], "h1": "fone.me vs Pipecat", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/fone-me-vs-pipecat", "published": "2026-10-01", "section": "tools", "title": "fone.me vs Pipecat for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/fone-me-vs-pipecat" }, "tokens": { "markdown": 6400, "slim": 4030 }, "version": 1 }