Causaly vs Inworld AI
Causaly vs Inworld AI: side-by-side comparison of two vertical / domain-specific ai memory systems — architecture, taxonomy, license, pricing, MCP/A2A support, and direct edges.
Cost & capability
| Causaly | Inworld AI | |
|---|---|---|
| Capability band | competent | competent |
| Capability composite | 57 | 55 |
| Cost tier | — | free |
| $/Mtok input | — | 0 |
| $/Mtok output | — | 0 |
| Use cases | Analytical Summarization, Long Running Session | Memory Augmented Chat, Long Running Session, Latency Sensitive |
Where they differ (10)
Rows where both sides have data and the values disagree — the shortlist of dimensions that actually distinguish these two systems.
| Causaly | Inworld AI | |
|---|---|---|
| Capability composite | 57 | 55 |
| Use cases | Analytical Summarization, Long Running Session | Memory Augmented Chat, Long Running Session, Latency Sensitive |
| Type | Persistent causal knowledge graph | Long-term character memory + Character Brain |
| Created | 2018 (founded 2018 by Yiannis Kiachopoulos and Artur Saudabayev; London UK) | 2022-01 |
| Pricing | Enterprise only | 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 |
| Funding | Series B $60M (ICONIQ Growth) Jul 2023; total $93M | $50M total $500M val Series A · 2023-08 |
| Deployment | Managed-only | Both |
| MCP | yes — Causaly capabilities exposed via MCP, A2A and APIs | no MCP support advertised — vertical product, no MCP server / client integration documented |
| Optimised for | research-workflow integration + provenance + claim grounding | character consistency + narrative continuity + low-latency |
| Anti-fit | not for non-research / non-academic use cases | not for non-character / non-narrative use cases |
At a glance
| Causaly | Inworld AI | |
|---|---|---|
| Section | Vertical / domain-specific AI memory | Vertical / domain-specific AI memory |
| Tier | T1 | T1 |
| Type | Persistent causal knowledge graph | Long-term character memory + Character Brain |
| Created | 2018 (founded 2018 by Yiannis Kiachopoulos and Artur Saudabayev; London UK) | 2022-01 |
| Pricing | Enterprise only | 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 |
| Funding | Series B $60M (ICONIQ Growth) Jul 2023; total $93M | $50M total $500M val Series A · 2023-08 |
| Backend storage | searched not found | searched not found |
| Deployment | Managed-only | Both |
| API surface | searched not found | searched not found |
| Embedding | searched not found | searched not found |
| Multi-tenancy | searched not found | searched not found |
| MCP | yes — Causaly capabilities exposed via MCP, A2A and APIs | no MCP support advertised — vertical product, no MCP server / client integration documented |
| A2A | no A2A protocol support advertised — vertical product, no A2A integration documented | no A2A protocol support advertised — vertical product, no A2A integration documented |
| OpenTelemetry | no OpenTelemetry integration advertised — vendor logs/observability not publicly documented | no OpenTelemetry integration advertised — vendor logs/observability not publicly documented |
| Optimised for | research-workflow integration + provenance + claim grounding | character consistency + narrative continuity + low-latency |
| Anti-fit | not for non-research / non-academic use cases | not for non-character / non-narrative use cases |
Taxonomy
| Axis | Causaly | Inworld AI |
|---|---|---|
| storage | graph | vector |
| retrieval | graph-traversal | similarity |
| persistence | long-term | long-term |
| update | extraction | extraction |
| unit | fact | episode |
| governance | inspectable | opaque |
| conflict | overwrite | llm-arbitrate |
Pros & cons
Causaly
Pros: Causal-biology graph extracted from full literature corpus is unique — most science-AI competitors retrieve documents rather than causal links.
Cons: Biology / pharma scope; not general scientific search; subscription pricing.
Inworld AI
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.