Vapi (voice agents)

https://vapi.ai/

Voice agents. Externalises memory from LLM into structured call state — variables rather than model recall — reducing hallucinations. Squad mode passes context across multi-agent assistant hand-offs in same call.

At a glance

Type
Structured workflow state during call
Tier
T2
Created
2023-01
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
Pay-per-use
Funding
$22M total $130M val Series A · 2024-12

Taxonomy

storage
kv
retrieval
injection
persistence
session
update
overwrite
unit
fact
governance
inspectable
conflict
overwrite

When to use

Optimised for: low-latency voice + structured workflow state

Anti-fit: not for non-voice / non-realtime use cases

Pros & cons

Pros

Voice-first agent platform with memory tuned for telephony / IVR; mature voice infrastructure.

Cons

Voice-only positioning; not useful for non-voice agents.

Claims & capabilities

Usage-based (per call minute). Call-scoped only.

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
Both
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
via official adapter — Vapi MCP tools
A2A
searched not found
OpenTelemetry
searched not found

Similar systems

Other framework-embedded memory in the catalog, ranked by inbound references.

  • LangGraph Persistence T2

    Distinct from LangMem. Built-in checkpointer saves graph state per super-step (short-term, thread-scoped). Store System adds long-term hierarchical key-value memory across threads with optional vector search + TTL. Postgres / Mongo / Redis stores for production.

  • AutoGen Memory T2

    ListMemory chronological context + teachable agents that vectorise corrections. Integrates with Mem0/Zep rather than building deep memory natively.

  • CrewAI Memory T2

    Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.

  • AGiXT Adaptive Memory T2

    Open-source AI automation platform. Routes between short-term and long-term memory adaptively across any LLM provider; plugin system for storage backends. Memory managed at the instruction-management layer — task context, instruction state, conversation history as unified agent state.

  • Agno (Phidata) Memory T2

    Agno (formerly Phidata). AgentStorage persists sessions to a DB; AgentMemory auto-classifies/store user preferences and conversation summaries. Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.

  • Botpress LLMz T1

    Per-plan vector-DB storage quota + LLMz autonomous engine (in-session working memory) + Knowledge Base (semantic search over uploaded docs). Long-term user memory persists across sessions.

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.