Palantir Ontology
https://www.palantir.com/docs/foundry/ontology/overview
Proprietary operational ontology — semantic objects + kinetic actions wired to microservices. Not open-standards KG; closed platform.
Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 44 cited facts, 4 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- Operational digital twin vendor fix
- Tier
- T1
- Section
- Knowledge-graph platforms
- 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
- $2.46B total over 18 rounds; IPO 2020 NYSE:PLTR third-party fix
- Freshness
- 2026-10-29 fix
- Layer
- model-infra repo fix
- Licensing
- commercial vendor fix
- SDK languages
- java, python, typescript vendor fix
- Protocols
- mcp-server vendor fix
- Compliance
- fedramp, gdpr, iso27001, iso27017, iso27018, soc2-type2, soc3 vendor fix
When to use
Optimised for: relationship modeling + reasoning + governance over pure vector
Anti-fit: not for purely-vector or simple-RAG use cases (graph adds setup cost)
Pros & cons
Pros
Most aggressive enterprise data ontology + agent fusion in production; backed by deep enterprise consulting muscle.
Cons
Vendor lock-in is total; pricing is enterprise-tier; minimal applicability outside large enterprise / government deployments.
Claims & capabilities
Q3 2025 U.S. commercial revenue +121% YoY driven by AIP adoption; BP saved $1B via optimized oil/gas operations; Fortune 100 CPG firm projected $100M savings in year 1; CAZ Investments processed 100x more leads at 90% time reduction; AIP Bootcamps as primary onboarding
Technical surface
- API surface
- REST (Foundry platform APIs), Ontology SDK: TypeScript, Python, Java; WebSocket Ontology subscriptions
- Backend storage
- searched not found
- Deployment
- Both
- Embedding model
- searched not found
- Multi-tenancy
- Foundry tenant per customer with strong ACL classification; zero-trust architecture; dedicated FedRAMP High enclave for federal workloads
- MCP
- yes — Ontology MCP (exposes Ontology to external agents) and Palantir MCP (palantir/palantir-mcp)
- A2A
- no Google A2A (Agent2Agent) integration documented as of 2026-05.
- OpenTelemetry
- no first-party OpenTelemetry exporter documented; standard logs/metrics typically available.
Alternatives to Palantir Ontology → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other knowledge-graph platforms in the catalog, ranked by inbound references.
- Neo4j T1
Property graph DB with Cypher; native vector search; Aura Agent + MCP server for graph-as-memory. $100M GenAI investment in 2025.
- Amazon Neptune Analytics T1
Vector index on graph nodes queryable via openCypher. Mem0 integration GA 2025; Cognee integration for agentic RAG. Combines semantic recall with multi-hop traversal in one managed service.
- FalkorDB T2
Native GraphRAG SDK. Graph-memory backend for Mem0; MCP server via Graphiti integration; context graphs for long-term agent memory.
- ArangoDB T1
HybridGraphRAG combines vector search, graph traversal, full-text in one AQL query. ArangoGraphML for ML pipelines; LangChain integration. The company now brands itself Arango (Arango Contextual Data Platform unifying graph, vector, document and search), with ArangoDB as its database.
- Kuzu T2
Embedded property-graph database (Cypher) with a built-in vector index and full-text search, widely used as an embedded store for agent memory and GraphRAG. The kuzudb/kuzu repository was archived on 2025-10-10 after Apple acquired the company; 0.11.3 is the final release and earlier releases remain usable.
- Memgraph T2
In-memory GraphRAG engine. Memgraph 3.0 adds native vector search alongside graph traversal. LangChain toolkit.
Sources (43 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 Operational digital twin vendor
- What it does & what's distinct Proprietary operational ontology — semantic objects + kinetic actions wired to microserv… vendor
- Claims / benefits Q3 2025 U.S. commercial revenue +121% YoY driven by AIP adoption; BP saved $1B via optim… third-party
- Modalities text vendor
- Created 2003 third-party
- Mindshare Public NYSE-listed (PLTR); strong dev/practitioner presence among Fortune 500 + governme… vendor
- Funding $2.46B total over 18 rounds; IPO 2020 NYSE:PLTR third-party
- Customers / scale Public company — thousands of enterprise/govt customers; revenue $3B+ FY2024 vendor
- Pricing Enterprise only vendor
- Compliance SOC 2 Type II; ISO 27001; FedRAMP High; HIPAA; GDPR-compliant vendor
- Data handling Never trains on customer data vendor
- Deployment Both vendor
- HQ US vendor
- Founders / pedigree Peter Thiel, Alex Karp, Joe Lonsdale, Stephen Cohen, Nathan Gettings; Alex Karp is CEO third-party
- Memory volume / scale internal — undisclosed vendor
- Performance No public benchmark; Palantir publishes customer case studies (Airbus, Merck) describing… vendor
- API surface REST (Foundry platform APIs), Ontology SDK: TypeScript, Python, Java; WebSocket Ontology… vendor
- Multi-tenancy Foundry tenant per customer with strong ACL classification; zero-trust architecture; ded… vendor
- Encryption TLS 1.2+ in transit, AES-256/AES-128 at rest with full-disk + application-level encrypti… vendor
- Tombstoning soft-delete only vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling always overwrite (last-write-wins) vendor
- MCP support yes — Ontology MCP (exposes Ontology to external agents) and Palantir MCP (palantir/pala… vendor
- Webhooks / events webhooks supported (Foundry events) vendor
- Import / export Foundry export (proprietary); SQL vendor
- Validated verticals financial-services, healthcare, legal, government, internal IT, KM vendor
- Time to running <1hr (Docker / managed cloud) to <1week (enterprise procurement) vendor
- Anti-fit not for purely-vector or simple-RAG use cases (graph adds setup cost) vendor
- Optimised for relationship modeling + reasoning + governance over pure vector vendor
- Adjacent infrastructure BYO LLM; bundled graph store; some require additional vector index vendor
- Pros Most aggressive enterprise data ontology + agent fusion in production; backed by deep en… vendor
- Cons Vendor lock-in is total; pricing is enterprise-tier; minimal applicability outside large… vendor
- Project & sources Palantir Ontology 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 platform vendor
- taxonomy-three-layer-rollup model-infra repo
- compliance-certifications fedramp,gdpr,iso27001,iso27017,iso27018,soc2-type2,soc3 vendor
- sdk-languages java,python,typescript vendor
- protocol-support mcp-server vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)