VALOGRAPH
A real-time tactical analysis AI assistant built on a graph database and LLMs, providing multi-hop relational reasoning and persistent memory for VALORANT players.
Timeline (last 90 days)
VALOGRAPH (HACKING GG) is a real-time tactical graph command center and persistent AI memory engine built on FalkorDB Cloud and Groq for VALORANT tactical analysis.
The VALOGRAPH project was completed at the WeMakeDevs x FalkorDB Graph Hacks hackathon.
VALOGRAPH's FalkorDB cloud database contains 145+ nodes, 116+ edges, and 32 tactical properties (such as acs, kd, kda, atk_wr, def_wr, fire_rate, cost, pen, playstyle).
VALOGRAPH's graph model uses the core node types: Player, Agent, Skill, Weapon, Map, Match, and Memory.
VALOGRAPH uses the edge (Agent)-[:HAS_SKILL]->(Skill) to connect agents with their skills, (Player)-[:PLAYS]->(Agent) and (Player)-[:PLAYED]->(Match) to track compositions and match history, and (Player)-[:REMEMBERS]->(Memory) to store persistent AI coach insights across sessions.
VALOGRAPH executes parameterized OpenCypher queries with a response time of about 1.36 milliseconds.
Storing a player's Q&A history and playstyle tags as graph nodes linked to riot_id gives the AI long-term memory across matches; compared with stuffing conversation history into the context window, graph memory turns player preferences into queryable structured facts.
All Facts (7)
VALOGRAPH's graph model uses the core node types: Player, Agent, Skill, Weapon, Map, Match, and Memory.
50%UnverifiedStoring a player's Q&A history and playstyle tags as graph nodes linked to riot_id gives the AI long-term memory across matches; compared with stuffing conversation history into the context window, graph memory turns player preferences into queryable structured facts.
50%UnverifiedVALOGRAPH's FalkorDB cloud database contains 145+ nodes, 116+ edges, and 32 tactical properties (such as acs, kd, kda, atk_wr, def_wr, fire_rate, cost, pen, playstyle).
50%UnverifiedVALOGRAPH (HACKING GG) is a real-time tactical graph command center and persistent AI memory engine built on FalkorDB Cloud and Groq for VALORANT tactical analysis.
50%UnverifiedVALOGRAPH uses the edge (Agent)-[:HAS_SKILL]->(Skill) to connect agents with their skills, (Player)-[:PLAYS]->(Agent) and (Player)-[:PLAYED]->(Match) to track compositions and match history, and (Player)-[:REMEMBERS]->(Memory) to store persistent AI coach insights across sessions.
50%UnverifiedVALOGRAPH executes parameterized OpenCypher queries with a response time of about 1.36 milliseconds.
50%UnverifiedThe VALOGRAPH project was completed at the WeMakeDevs x FalkorDB Graph Hacks hackathon.
50%