Awesome papers about machine learning (deep learning) on dynamic (temporal) graphs (networks / knowledge graphs).

Distributed Temporal Graph Analytics with Apache Flink

Advances on machine learning of dynamic (temporal) graphs, covering the reading list of recent top academic conferences.

privacy-first context graph engine for AI agents and human teams.

the 1st place of WSDM 2022 Challenge (Temporal Link Prediction)

Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter + Gemini Flash → Neo4j (via Graphiti). 12 MCP tools, hierarchical clusters, two-regime confidence decay.

Source code for paper "Towards Efficient Simulation-based Constrained Temporal Graph Pattern Matching"

Experiments Using Knowledge and Temporal Graphs

Real-time global intelligence platform — OSINT monitoring + multi-agent predictive simulation in Gleam/OTP

A curated list of graph datasets of various types, including plaingraphs, attributed graphs, bipartite graphs, text-attributed graphs, multi-modal graphs, temporal graphs, etc.

Privacy-aware activity tracking system with semantic search, temporal graphs, and ML-based context prediction

Temporal graph model on DOM

RAPTOR (Round-bAsed Public Transit Optimized Router) TypeScript implementation

Unified Parallel Semantic Log Parsing based on Causal Graph Construction for Attack Attribution

Shared context substrate for AI agents. Retrieval that learns what's useful. Runs local or cloud.

GGames is a Python package that provides functions to study games on graphs that can be either static or time-varying.

Local-first temporal knowledge graph memory for AI agents. Runs with Ollama — no API keys required. Single Go binary + SQLite. Hybrid search, MCP server, REST API, interactive TUI.

Temporal GraphRAG: dynamic ontology induction for causal memory compression in long-horizon LLM agents. Achieves 1.0 causal recall with 95–98% graph compression across 10K–30K session corpora.

Starter template for building LangGraph agents with real long-term memory using OpenMemory’s temporal graph.

This is a ready-to-go application to convert the LDBC FinBench dataset to a Gradoop TPGM graph.