Inworld AI
Formerly an NPC character engine with named Long-Term Memory; now sells realtime voice models (TTS-2, STT-1, speech-to-speech) and OpenAI-compatible open-model inference. Character/NPC memory is no longer the headline product.
Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 39 cited facts, 10 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Long-term character memory + Character Brain vendor fix
- Tier
- T1
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Usage-based: TTS-2 $25/1M chars on demand ($10 Enterprise); TTS-2 Flash $15/1M; STT-1 $0.10/audio-hour; open LLMs from $0.07/1M input tokens vendor fix
- Funding
- $50M total $500M val Series A · 2023-08 third-party fix
- Freshness
- 2026-10-29 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
Memory taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- episode
- governance
- opaque
- conflict
- llm-arbitrate
When to use
Optimised for: character consistency + narrative continuity + low-latency
Anti-fit: not for non-character / non-narrative use cases
Pros & cons
Pros
Most adopted NPC AI platform — memory model handles personality, mood, relationship state in addition to conversation history.
Cons
Game-engine-tied integrations; production deployment requires game studio engineering effort.
Claims & capabilities
Unity, Unreal, NVIDIA ACE integrations. $120M raised (Lightspeed, KP, Founders Fund, M12, Samsung NEXT).
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
- no MCP support advertised — vertical product, no MCP server / client integration documented
- A2A
- no A2A protocol support advertised — vertical product, no A2A integration documented
- OpenTelemetry
- no OpenTelemetry integration advertised — vendor logs/observability not publicly documented
Compare Inworld AI with…
Alternatives to Inworld AI → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other vertical / domain-specific ai memory in the catalog, ranked by inbound references.
- NVIDIA ReMEmbR T3
Builds long-horizon memory by captioning video segments with VILA, storing captions with timestamps + 3D position coordinates in MilvusDB. At query time, LLM iterates retrieval across text, time, and position modalities. Deployed on Nova Carter robot (Jetson Orin).
- Abridge T1
Clinician-assist ambient documentation. Source mapping: every AI-generated summary element traced back to the source utterance. Audit-and-trust layer over episodic memory. Built on proprietary 1.5M+ medical-encounter dataset.
- ASAPP GenerativeAgent T1
Treats memory as first-class architecture. Captures the digital footprint of every interaction; retrieves preference and history at engagement time. Public example: airline knowing a frequent flyer wants aisle seats with her son — preference-aware, not just history-lookup.
- BenevolentAI T1
Taken private: merged into Osaka Holdings (renamed BenevolentAI S.A.) and delisted from Euronext Amsterdam 2025-03-13. Target identification / drug repurposing / mechanism tracing. 85+ data sources, petabyte-scale, rebuilt every few weeks. Wet-lab results re-enter the graph and shift downstream predictions — institutional experimental memory closing a feedback loop. As of Oct 2026 benevolent.com leads with Qor, powered by BenevolentAI, a life-science intelligence service for biopharma decision makers and consultancies. Qor (qor.one) is a continuously updated decision-intelligence service built on BenevolentAI's knowledge graph and reasoning methods: it tracks evidence on an asset or indication (competitive position, rival readouts, comparable deals), source-verifies each claim and flags when an earlier conclusion stops holding. It targets biotech teams and life-science consultancies.
- Causaly T1
Agentic AI platform for life sciences: orchestrated scientific agents over a curated biomedical knowledge graph (plus Bio Graph and Pipeline Graph), an evidence-retrieval system and an enterprise data fabric over literature, trials and patents.
- Character.ai T1
Chat Memories (user-defined facts), auto-memories for c.ai+ subscribers, pinned memories, in-context retention. Latest chat models PipSqueak 3 and ShortSqueak (Sep 2026). On 2026-10-12 the company announced a voluntary Chapter 11 process for a court-supervised sale of all or substantially all assets (sale expected late Nov/early Dec 2026); the platform keeps running meanwhile and would be wound down if no viable bid emerges.
Sources (38 cited facts, 10 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Long-term character memory + Character Brain vendor
- What it does & what's distinct Formerly an NPC character engine with named Long-Term Memory; now sells realtime voice m… vendor
- Claims / benefits Unity, Unreal, NVIDIA ACE integrations. $120M raised (Lightspeed, KP, Founders Fund, M12… vendor
- Modalities text vendor
- Created 2022-01 third-party
- Mindshare 10 jobs 9 HN · 1 press third-party
- Funding $50M total $500M val Series A · 2023-08 third-party
- Customers / scale 51-200 ppl Xbox, Ubisoft (NEO NPC prototype), NVIDIA, Kinetix, Shiseido vendor
- Pricing Usage-based: TTS-2 $25/1M chars on demand ($10 Enterprise); TTS-2 Flash $15/1M; STT-1 $0… vendor
- Compliance SOC 2 Type II; GDPR-compliant vendor
- Deployment Both vendor
- HQ US third-party
- Founders / pedigree Lightspeed / Kleiner Perkins / Disney Accelerator; co-founders Ilya Gelfenbeyn et al. third-party
- Memory volume / scale no scale claim vendor
- Versioning snapshots vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling LLM resolves and overwrites vendor
- Forgetting policy consolidation/summarization vendor
- Webhooks / events webhooks supported vendor
- Import / export JSON via Studio API vendor
- Validated verticals gaming (AAA + indie), interactive narrative, AI companions vendor
- Time to running <10min (SDK download / hosted API) vendor
- Anti-fit not for non-character / non-narrative use cases vendor
- Optimised for character consistency + narrative continuity + low-latency vendor
- Adjacent infrastructure requires game engine integration (Unity / Unreal); BYO LLM vendor
- Pros Most adopted NPC AI platform — memory model handles personality, mood, relationship stat… vendor
- Cons Game-engine-tied integrations; production deployment requires game studio engineering ef… vendor
- Project & sources inworld.ai vendor
- cost-input-usd-per-mtok 0 third-party
- cost-output-usd-per-mtok 0 third-party
- cost-tier free third-party
- cost-pricing-model free-tier third-party
- cost-last-verified 2026-06-29 third-party
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
Related systems
References (1)
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — now sells realtime voice models (TTS-2, STT-1, speech-to-speech) and OpenAI-compatible open-model inference.
Referenced by (3)
- LiveKit Agents integrates with — LiveKit Agents docs have a Inworld AI model plugin page. (verified 2026-10-29)
- Pipecat (Daily) integrates with — Pipecat docs have a Inworld AI service page. (verified 2026-10-29)
- Vapi integrates with — Vapi docs list Inworld AI as a provider/integration. (verified 2026-10-29)