Platform
ContextMemoryTrustIntelligence
Products
ChatExplorerToolkit
System
SpecificationsDocumentationSecurity
Solutions
Change ProgrammesTechnology OptimisationFinancial ReportingSales OptimisationKnowledge Bases
Company
CareersResourcesContact
Request a demo
Platform · Toolkit

Build on a model that knows your organisation.

Engineers, data scientists and AI agents all work against the same live model, each in the language or protocol that suits them, with temporal parameters built into every call.

Request a demo Documentation
↳ For engineers ↳ For data scientists ↳ For AI agents
For engineers

Load your data, then build on it

Ingest from what you already run, then query the model from the language or API that suits the job. Temporal parameters are built into every call.

Getting your data in

Batch

Bulk ingestion

Load any Arrow-compatible tabular data: CSV, Parquet, Pandas, DuckDB and more. Completely unordered, because Pometry merges all history chronologically.

Streaming

Real-time events

Webhook and event-stream connectors for continuous updates. Changes are reflected immediately and preserved in the temporal history.

Building on the model

Python

Data science native

Native Python bindings for analytics workflows. Integrates directly with pandas, NumPy and your existing ML tooling.

Rust

Systems-level access

Direct bindings to the core. Zero-overhead integration for performance-critical applications and embedded deployments.

GraphQL

Flexible queries

Query exactly the fields you need. Supports deep traversal, relationship filtering and temporal windowing in a single request.

For data scientists

Fifty algorithms, all temporal

Run any of them against a historical snapshot or a window down to the millisecond, compare output across periods, or extend the library with your own implementations in Rust or Python.

Temporal PageRank Community Detection Anomaly Detection Temporal Shortest Path k-Core Decomposition Betweenness Centrality Louvain (temporal) Weakly Connected Components Link Prediction Node Embedding Temporal Density Flow Analysis Temporal Motifs Clustering Coefficient HITS (temporal) Change Point Detection Motif Detection Label Propagation Foremost Path Temporal Ego Network Strongly Connected Components Graph Similarity Bipartite Projection Dependency Chain Reachability Triangle Count Fastest Path Temporal Degree Centrality Temporal Closeness Centrality Temporal PageRank Community Detection Anomaly Detection Temporal Shortest Path k-Core Decomposition Betweenness Centrality Louvain (temporal) Weakly Connected Components Link Prediction Node Embedding Temporal Density Flow Analysis Temporal Motifs Clustering Coefficient HITS (temporal) Change Point Detection Motif Detection Label Propagation Foremost Path Temporal Ego Network Strongly Connected Components Graph Similarity Bipartite Projection Dependency Chain Reachability Triangle Count Fastest Path Temporal Degree Centrality Temporal Closeness Centrality
Temporal PageRank Community Detection Anomaly Detection Temporal Shortest Path k-Core Decomposition Betweenness Centrality Louvain (temporal) Weakly Connected Components Link Prediction Node Embedding Temporal Density Flow Analysis Temporal Motifs Clustering Coefficient HITS (temporal) Change Point Detection Motif Detection Label Propagation Foremost Path Temporal Ego Network Strongly Connected Components Graph Similarity Bipartite Projection Dependency Chain Reachability Triangle Count Fastest Path Temporal Degree Centrality Temporal Closeness Centrality Temporal PageRank Community Detection Anomaly Detection Temporal Shortest Path k-Core Decomposition Betweenness Centrality Louvain (temporal) Weakly Connected Components Link Prediction Node Embedding Temporal Density Flow Analysis Temporal Motifs Clustering Coefficient HITS (temporal) Change Point Detection Motif Detection Label Propagation Foremost Path Temporal Ego Network Strongly Connected Components Graph Similarity Bipartite Projection Dependency Chain Reachability Triangle Count Fastest Path Temporal Degree Centrality Temporal Closeness Centrality
For AI agents

Your organisation, as a tool call

Register the MCP server and any agent that speaks the Model Context Protocol can traverse relationships, filter by time and cite what it found. Claude, GPT, Gemini, Llama or your internal deployment.

agent → pometry MCP connected
✓ neighbours(entity: "Atlas Migration", at: "2026-03-14") 128 nodes
✓ shortest_path(from: "Payments", to: "Core Banking") 4 hops
✓ history(node: "LOAN-000008", between: [Q1, Q3]) 42 events
✓ subgraph(labels: ["team"], window: "90d") 17 teams
✓ recall(query: "who signed off the schema change") 3 decisions

Experience Pometry in action
with a live demo.

Find out how you can close your visibility gap with unique, institutional intelligence.

Request a demo Talk to the team