Vapi (voice agents)
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.
Active · Verified 2026-10-28 · fresh as of 2026-10-28 · 47 cited facts, 4 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- Structured workflow state during call vendor fix
- Tier
- T2
- Section
- Framework-embedded memory
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Pay-as-you-go $0.05/min Vapi hosting with $5 free credit; Core $29/mo; Pro 10% of the hosting fee ($999/mo minimum); Premier custom vendor fix
- Funding
- $22M total $130M val Series A · 2024-12 vendor fix
- Freshness
- 2026-10-28 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
- SDK languages
- csharp, go, java, python, rest, ruby, typescript vendor fix
- Protocols
- mcp-client vendor fix
- Compliance
- hipaa, pci-dss vendor fix
Memory 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
Alternatives to Vapi (voice agents) → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other framework-embedded memory in the catalog, ranked by inbound references.
- Spring AI ChatMemory T3
Wraps conversation memory behind an Advisor abstraction. MessageWindowChatMemory default 20-msg sliding window (preserves system messages); pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j). Memory injected as cross-cutting concern at the ChatClient level.
- Flowise Memory T1
Discontinued: Flowise (acquired by Workday, Aug 2025) was sunset in 2026 — code freeze 2026-07-29, GitHub repo archived 2026-08-13, end of life 2026-08-31. Was a visual LangChain canvas with LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary Buffer) backed by an internal chat_message DB table; Buffer Window kept the last K interactions, Summary Buffer compressed older turns while keeping recent ones verbatim.
- 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
AutoGen's memory layer: ListMemory chronological context plus teachable agents that vectorise corrections; integrates with Mem0/Zep rather than building deep memory natively. Microsoft AutoGen is in maintenance mode (community managed, bug and security fixes only), and Microsoft points new projects to Microsoft Agent Framework.
- CrewAI Memory T2
Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
- Hermes Agent memory (Nous Research) T3
Nous Research's open-source self-improving agent keeps an agent-curated MEMORY.md/USER.md notebook injected at session start, full-text (FTS5) search over past sessions that returns raw messages without LLM summarisation, and optional Honcho user modelling. one of the most-starred agent projects of 2026.
Sources (46 cited facts, 4 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Structured workflow state during call vendor
- What it does & what's distinct Voice agents. Externalises memory from LLM into structured call state — variables rather… vendor
- Claims / benefits Usage-based (per call minute). Call-scoped only. vendor
- Modalities voice + text vendor
- Created 2023-01 vendor
- Mindshare 2 press ~50 (small star jobs vendor
- Funding $22M total $130M val Series A · 2024-12 vendor
- Customers / scale $8M ARR 51-200 ppl No named customers disclosed, ~30 per early tracking third-party
- Pricing Pay-as-you-go $0.05/min Vapi hosting with $5 free credit; Core $29/mo; Pro 10% of the ho… vendor
- Compliance SOC 2 Type II; HIPAA (hipaaEnabled flag; only HIPAA-compliant services used when enabled… vendor
- Data handling PHI processed but not stored when HIPAA mode enabled; PCI-compliant masking of payment d… vendor
- Deployment Both vendor
- HQ US third-party
- Founders / pedigree Vapi AI (Nikhil Gupta & Jordan Dearsley, co-founders; YC W23) third-party
- Memory volume / scale no scale claim — state lives in call variables vendor
- Schema evolution free-form / no schema vendor
- Contradiction handling always overwrite (last-write-wins) vendor
- Forgetting policy TTL-based vendor
- MCP support via official adapter — Vapi MCP tools vendor
- Webhooks / events webhooks supported (server URL events) vendor
- Import / export JSON via REST; webhook events; call recordings export vendor
- Integration count 0 vendor
- Orchestration multi-agent supervisor vendor
- Programmatic control declarative config + REST vendor
- Pricing specifics per-API-call: pay-per-use per call minute vendor
- Agent abstraction multi-agent supervisor (Squad mode) vendor
- Memory primitives key-value (call state variables) vendor
- LLM lock multi-vendor vendor
- Runtimes declarative cross-language vendor
- Session handling sticky session (call-scoped only) vendor
- Validated verticals voice agents (telephony, scheduling, support) vendor
- Time to running <10min (hosted SaaS) vendor
- Anti-fit not for non-voice / non-realtime use cases vendor
- Optimised for low-latency voice + structured workflow state vendor
- Adjacent infrastructure BYO LLM + STT/TTS providers (or use Vapi defaults) vendor
- Pros Voice-first agent platform with memory tuned for telephony / IVR; mature voice infrastru… vendor
- Cons Voice-only positioning; not useful for non-voice agents. vendor
- Project & sources vapi.ai vendor
- adoption-accelerator yc-w21 third-party
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- compliance-certifications hipaa,pci-dss vendor
- sdk-languages csharp,go,java,python,rest,ruby,typescript vendor
- protocol-support mcp-client vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-28
- Pricing “Pay-per-use” → “Pay-as-you-go $0.05/min Vapi hosting with $5 free credit; Core $29/mo; Pro 10% of the hosting fee ($999/mo minimum); Premier custom” source
- 2026-10-23
- Compliance “SOC 2 Type II; HIPAA (hipaaEnabled flag; only HIPAA-compliant services used when enabled); PCI DSS (pciEnabled flag…” → “SOC 2 Type II; HIPAA (hipaaEnabled flag; only HIPAA-compliant services used when enabled); PCI DSS” source