{"schema_version":"1.0","name":"Mnemix","legal_name":"Mnemix, Inc.","summary":"Mnemix is the memory + real-world enrichment API for AI voice agents. Same-number caller memory and available enrichment help agents start informed, with sub-300ms voice recall as a design target. Voice-first, API-native. Built for Vapi, Retell, Bland, LiveKit, and Twilio, with the same memory and enrichment API available to MCP tools, Claude Code CLI workflows, and backend agents via HTTP.","url":"https://mnemix.ai","contact":"hello@mnemix.ai","category":{"primary":"AI memory layer","secondary":"Voice agent infrastructure","competesWith":["Mem0","Zep","Supermemory","Cognee","Letta","OMEGA","LangMem","OpenAI Assistants"]},"wedge":{"sentence":"Mnemix is the memory API where callers can arrive with same-number memory and available enrichment joined to the agent's context. Real-world identity, intent, and history are shaped for voice workflows, with sub-300ms voice recall as a design target.","pillars":[{"name":"Caller-ID enrichment, voice-native","description":"Twilio Lookup + Trestle person/company resolution + Baylio call-intent fan out before the first audio packet. The agent's first response is already informed."},{"name":"Sub-300ms voice recall as an edge design target","description":"Cloudflare Workers across 5+ regions. The latency budget targets memory + enrichment in parallel under the 800ms voice ceiling — measured public benchmark coming with v1.0."},{"name":"Bi-temporal session memory","description":"Four timestamps per fact (valid_from, valid_to, observed_at, ingested_at). Built for voice flows where context shifts mid-call."}]},"integrations":{"voiceAgent":["Vapi","Retell AI","Bland AI","LiveKit","ElevenLabs"],"telephony":["Twilio"],"enrichment":["Twilio Lookup","Trestle","Baylio"],"llm":["OpenAI Realtime","Anthropic Claude","Google Gemini","Groq"],"storage":["Supabase"],"runtime":["Cloudflare Workers","Durable Objects","R2","KV"]},"answer_block":{"what":"Mnemix is a memory + real-world enrichment API for AI voice agents.","who":"For developers building AI voice agents on Vapi, Retell, Bland, LiveKit, or Twilio.","price":"Hobby $0 (free tier · 50 sessions / 1,000 memory ops / 100 lookups). Starter, Pro, and Elite tiers — contact sales for pricing while billing is in private beta.","how":"One API call per turn — lookup, remember, recall. Sub-300ms voice recall is a design target at the Cloudflare edge."},"faq":[{"q":"What is Mnemix?","a":"Mnemix is a memory + real-world enrichment API for AI voice agents. It joins identity, intent, and call history to your agent's memory at Cloudflare edge latency, with sub-300ms voice recall as a design target."},{"q":"Who is Mnemix for?","a":"Developers building AI voice agents on platforms like Vapi, Retell AI, Bland AI, LiveKit, or directly on Twilio. Also chat developers who want phone-native identity."},{"q":"How is Mnemix different from Mem0?","a":"Mem0 is a general-purpose memory layer with strong mindshare and 19 vector backends. Mnemix is voice-first with caller-ID enrichment built in (Twilio Lookup + Trestle + Baylio), runs on Cloudflare Workers at the edge, and ships first-class integrations with Vapi, Retell, and Bland. Choose Mnemix if you're building voice. Choose Mem0 if you need a general-purpose memory layer with deep vector-store choice."},{"q":"How is Mnemix different from Zep?","a":"Zep + Graphiti is the research-cited bi-temporal knowledge graph for chat agents. Mnemix is voice-native with built-in caller-ID enrichment. Zep's voice support is a community demo; Mnemix ships first-class integrations with Vapi, Retell, Bland, and Twilio. Choose Mnemix if you're building voice."},{"q":"How is Mnemix different from Supermemory?","a":"Supermemory and Mnemix share the same Cloudflare Workers stack. The difference is voice + enrichment: Mnemix bundles Twilio Lookup, Trestle, and Baylio call-intent into the memory primitives. Supermemory is general-purpose memory. Choose Mnemix if you're building voice."},{"q":"How is Mnemix different from Letta?","a":"Letta deprecated its voice endpoint in March 2026 (HTTP 410 in letta/server/rest_api/routers/v1/voice.py). Mnemix is voice-first. Choose Mnemix if you're building voice."},{"q":"How is Mnemix different from LangMem?","a":"LangMem is bound to LangGraph and reports 59.82-second p95 latency in its own benchmarks — structurally disqualified for voice. Mnemix targets sub-300ms voice recall as a design goal. Choose Mnemix if you're building voice."},{"q":"How much does Mnemix cost?","a":"Hobby is $0/month — free tier with 50 sessions, 1,000 memory operations, and 100 Twilio Lookups. Starter, Pro, and Elite tiers are in private beta — contact hello@mnemix.ai for pricing while we wire billing."},{"q":"Is there a free tier?","a":"Yes. Hobby is $0/month with 50 sessions, 1,000 memory operations, and 100 Twilio Lookups. Attribution required (Powered by Mnemix). Sign up at https://mnemix.ai."},{"q":"What latency does Mnemix offer?","a":"Sub-300ms voice recall is a Cloudflare-edge design target. A measured public benchmark across 5 regions ships with v1.0 (target May 2026). We'd rather under-promise and publish honest numbers."},{"q":"Where does Mnemix run?","a":"Cloudflare Workers (edge), with Durable Objects for session state, R2 for blob storage, KV for hot cache, and Supabase Postgres + pgvector for the durable memory store."},{"q":"Does Mnemix support the OpenAI Assistants API?","a":"Yes — Mnemix is a migration target. The OpenAI Assistants API is shutting down 2026-08-26. See https://mnemix.ai/compare/openai-assistants-vs-mnemix for the migration plan."},{"q":"Does Mnemix integrate with Vapi?","a":"Yes. The Vapi integration takes ~5 minutes — drop the Mnemix middleware into your Vapi function-call handler. See https://mnemix.ai/integrations/vapi."},{"q":"Does Mnemix integrate with Retell AI?","a":"Yes. The Retell integration provides caller-ID lookup and conversation memory persistence. See https://mnemix.ai/integrations/retell."},{"q":"Does Mnemix integrate with Bland AI?","a":"Yes. See https://mnemix.ai/integrations/bland."},{"q":"What benchmark scores does Mnemix have?","a":"Mnemix's first LongMemEval result is targeted for May 2026 (≥85% on the oracle split). Until then, no benchmark numbers are published — see https://mnemix.ai/research/longmemeval for the methodology and harness."},{"q":"Is Mnemix open source?","a":"The enrichment SDK is MIT-licensed on GitHub. The memory layer is closed-source SaaS with self-host coming for Elite tier."},{"q":"Is Mnemix HIPAA-compliant?","a":"GDPR-compliant from day 1. SOC 2 Type II in progress (Year 1 target). HIPAA-ready architecture with BAA available at Pro+ after $250K MRR."},{"q":"Where is Mnemix data stored?","a":"Cloudflare global edge for hot session state; Supabase EU + US regions for durable storage. EU data residency available."},{"q":"How do I get started with Mnemix?","a":"Sign up at https://mnemix.ai for a free Hobby key, install the SDK (npm install @mnemix/client), and follow the 5-minute quickstart at https://mnemix.ai/docs/quickstart. For voice, see https://mnemix.ai/docs/voice-quickstart."}],"target_queries":["best memory api for ai voice agents","how do i add memory to a vapi voice agent","how do i add memory to a retell ai agent","twilio caller id enrichment with ai","letta voice deprecated alternative","mem0 alternatives","zep alternatives","openai assistants api replacement","cloudflare workers memory database","phone number to person lookup api","real-time memory for ai agents at the edge","voice agent memory api"],"pricing":[{"tier":"Hobby","price_usd":0,"status":"available","sessions":50,"memory_ops":1000,"twilio_lookups":100,"enrichments":0,"cta":{"label":"Get a key — free","href":"/signup"}},{"tier":"Starter","price_usd":null,"status":"contact-sales","sessions":500,"memory_ops":25000,"twilio_lookups":2000,"enrichments":200,"cta":{"label":"Contact sales","href":"mailto:hello@mnemix.ai?subject=Mnemix%20Starter"}},{"tier":"Pro","price_usd":null,"status":"contact-sales","sessions":5000,"memory_ops":250000,"twilio_lookups":25000,"enrichments":2500,"cta":{"label":"Contact sales","href":"mailto:hello@mnemix.ai?subject=Mnemix%20Pro"}},{"tier":"Elite","price_usd":null,"status":"contact-sales","sessions":25000,"memory_ops":-1,"twilio_lookups":-1,"enrichments":25000,"cta":{"label":"Contact sales","href":"mailto:hello@mnemix.ai?subject=Mnemix%20Elite"}}],"discovery_surfaces":{"llms_txt":"https://mnemix.ai/llms.txt","llms_full_txt":"https://mnemix.ai/llms-full.txt","knowledge_endpoint":"https://mnemix.ai/api/agents/knowledge","openapi":"https://mnemix.ai/.well-known/openapi.json","ai_plugin":"https://mnemix.ai/.well-known/ai-plugin.json"},"last_updated":"2026-05-02"}