Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/timepoint-ai/timepoint-clockchain/llms.txt

Use this file to discover all available pages before exploring further.

​
Welcome to Timepoint Clockchain

Timepoint Clockchain is a PostgreSQL-backed directed graph of historical moments — a temporal causal graph for AI agents that reason about causality across time. Each node carries dialog, entity states, provenance, and confidence, addressed by a canonical spatiotemporal URL.
Why this exists — AI agents that reason about causality across time currently rely on web search (noisy, unstructured), knowledge graphs (no temporal dimension), or hallucination. The Clockchain is a structured alternative: every node carries dialog, entity states, provenance, and confidence, addressed by a canonical spatiotemporal URL, in a format (TDF) designed for machine consumption.

​
What is Clockchain?

The graph accumulates two layers of rendered reality:
  • Rendered Past — historical events rendered by Flash with full causal structure, entity states, dialog, and source grounding
  • Rendered Future — simulation outputs from Pro, scored for convergence, stored as TDF records
Each new event with causal edges tightens the Bayesian prior — fewer plausible things could have happened in the gaps — approaching asymptotic coverage of any historical period.
The name is conceptual. This is PostgreSQL, not a blockchain.

​
Key Features

Canonical URLs

Every moment has a unique spatiotemporal address with 8 segments encoding when and where

Typed Edges

Causal, contemporaneous, spatial, and thematic relationships between moments

Autonomous Growth

LLM-driven workers expand the graph 24/7 by generating related events

TDF Interoperability

All nodes exportable as TDF records for cross-service data interchange

​
How It Works

The Clockchain serves as the central accumulation point for the Timepoint AI suite:
  1. Flash renders historical scenes with full causal structure
  2. Pro generates temporal simulations scored for convergence
  3. Expander autonomously grows the graph by finding frontier nodes and generating related events
  4. Each addition strengthens the Bayesian prior for better future renderings

​
Core Architecture

The Clockchain is built on:
  • PostgreSQL database with two tables: nodes and edges
  • FastAPI service with RESTful endpoints
  • Four autonomous workers (Renderer, Expander, Judge, Daily)
  • Canonical URL system for spatiotemporal addressing
  • Auto-linking for temporal, spatial, and thematic edges

​
Use Cases

  • Temporal reasoning for AI agents that need to understand causality
  • Historical knowledge graph with full spatiotemporal grounding
  • Simulation validation through causal convergence
  • Browse and discovery of historical moments via REST API
  • Content generation with Flash scene renderer integration

​
Next Steps

Quickstart

Get up and running with Clockchain in minutes

Core Concepts

Understand the graph architecture and data model

API Reference

Explore the complete API documentation

Timepoint Suite

Learn about the full Timepoint AI ecosystem

Build docs developers (and LLMs) love

Get started for freeTalk to us