Teams buildingon Graphify.

The data already lives in Rootly. The graph makes the structure visible. Sylvain Kalache, Rootly AI Labs

Named, and linked.

No asserted outcomes. Each one carries the post, the repository or the paper it came from.

• Rootly AI Labs

  Incident management · SRE

  Rootly turned its incident data (incidents, alerts, teams, services) into a queryable knowledge graph with Graphify.

  Read the postView the integration

• Superagent

  Security for AI-native developers

  Superagent (YC W24), the security layer for AI-native developers.

• HKUST KnowComp

  Research lab

  Published DeepRefine, an agent skill plus paper that refines Graphify knowledge graphs.

  View the skill

Numbers we did not run.

The people linked under each figure ran them, on their own codebases.

• 71.5×fewer tokens in one user's Claude Code and Graphify setup.lucasrosati/claude-code-memory-setup
• 79×fewer tokens on a 496K-token codebase, with zero vector database in the stack.Steve Scargall, MemVerge

How developers put it to work.

Practitioners writing about their own setups. We link and attribute; we never reproduce the piece.

• How Graphify Stopped My Team from Burning Thousands of Tokens Per Query

  DEV Community. A React Native tech lead on how the graph replaced sequential file-reading in Cursor for his team.

• Graphify + Claude Code: How I Cut Token Usage by 71x on a 50k-Line Codebase

  Medium. Wires Graphify into Claude Code with a PreToolUse hook and reports a 71× token drop on a 50k-line codebase.

• Cut Your Claude Token Consumption By 70x

  DEV Community. Why parsing code into queryable relationships beats re-reading files every session, with real token numbers.

• This Tool Fixes AI Coding at Scale with 70× Fewer Tokens (Graphify)

  Better Stack (YouTube). A walkthrough of how Graphify's on-device knowledge graph cuts token usage for coding agents at scale.