Causaly
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.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 36 cited facts, 4 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Persistent causal knowledge graph vendor fix
- Tier
- T1
- Created
- 2018 (founded 2018 by Yiannis Kiachopoulos and Artur Saudabayev; London UK) third-party fix
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Enterprise only vendor fix
- Funding
- Series B $60M (ICONIQ Growth) Jul 2023; total $93M third-party fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
Memory taxonomy
- storage
- graph
- retrieval
- graph-traversal
- persistence
- long-term
- update
- extraction
- unit
- fact
- governance
- inspectable
- conflict
- overwrite
When to use
Optimised for: research-workflow integration + provenance + claim grounding
Anti-fit: not for non-research / non-academic use cases
Pros & cons
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.
Claims & capabilities
500M facts, 70M directional relationships. Major pharma partners. Agentic layer launched early-access Mar 2025.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Managed-only
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- yes — Causaly capabilities exposed via MCP, A2A and APIs
- A2A
- no A2A protocol support advertised — vertical product, no A2A integration documented
- OpenTelemetry
- no OpenTelemetry integration advertised — vendor logs/observability not publicly documented
Compare Causaly with…
Alternatives to Causaly → 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.
- Inworld AI T1
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.
- 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.
- 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 (35 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 Persistent causal knowledge graph vendor
- What it does & what's distinct Agentic AI platform for life sciences: orchestrated scientific agents over a curated bio… vendor
- Claims / benefits 500M facts, 70M directional relationships. Major pharma partners. Agentic layer launched… vendor
- Modalities text vendor
- Created 2018 (founded 2018 by Yiannis Kiachopoulos and Artur Saudabayev; London UK) third-party
- Funding Series B $60M (ICONIQ Growth) Jul 2023; total $93M third-party
- Customers / scale Major pharma partners (not publicly named) vendor
- Pricing Enterprise only vendor
- Compliance SOC 2 Type II; GDPR-compliant vendor
- Deployment Managed-only vendor
- HQ UK third-party
- Founders / pedigree Artur Saudabayev (CTO) and Yiannis Kiachopoulos (CEO); met at Singularity University third-party
- Memory volume / scale 500M facts / 70M directional relationships (vendor claim) vendor
- Consistency strong consistency required for clinical record integrity vendor
- Versioning immutable audit log (HIPAA + 21 CFR Part 11 require audit trails) vendor
- Tombstoning audit-logged soft delete (regulatory retention requirement) vendor
- Schema evolution FHIR/HL7-aligned schema (clinical standard); minor versioning vendor
- Namespace primitives tenant-per-customer (BAA-scoped); patient-scoped within tenant vendor
- Contradiction handling always overwrite (last-write-wins) vendor
- Forgetting policy regulated retention (7+ years per HIPAA + state law); patient-requested deletion governe… vendor
- MCP support yes — Causaly capabilities exposed via MCP, A2A and APIs vendor
- Validated verticals research only (academia + R&D in pharma / biotech / scientific publishing) vendor
- Time to running <10min (hosted SaaS) to <1day (enterprise integration) vendor
- Anti-fit not for non-research / non-academic use cases vendor
- Optimised for research-workflow integration + provenance + claim grounding vendor
- Adjacent infrastructure self-contained SaaS; some integrate with reference managers vendor
- Pros Causal-biology graph extracted from full literature corpus is unique — most science-AI c… vendor
- Cons Biology / pharma scope; not general scientific search; subscription pricing. vendor
- Project & sources causaly.com vendor
- cost-pricing-model subscription vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product product 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)