Launching today

Kivgraph

Launching today

Semantic code navigation for AI coding agents

1 follower

Semantic code navigation for AI coding agents

1 follower

Visit website

Kivgraph gives Claude Code, Codex, and other AI coding agents a local semantic graph of symbols, dependencies, and cross-repository relationships. It answers structural code questions with less context than grep and file reading.

Free

Launch tags:Developer Tools•Artificial Intelligence•GitHub

Launch Team

Wispr Flow: Dictation That Works EverywhereStop typing. Start speaking. 4x faster.

Promoted

Maker

📌

I built Kivgraph after watching my coding agent spend dozens of searches and file reads answering questions like “where is this used?” and “what breaks if I change it?” The benchmark that convinced me to keep working on it covered 37 repositories and 29 questions. Kivgraph and grep + reading both got 28/29 exact answers, but the graph used 36k tokens versus 268k. That is about 7.4× less context overall. The tradeoff is important: grep was cheaper on 5 questions, so Kivgraph is not a replacement for ordinary search. It is for structural, cross-repository questions where reconstructing relationships is expensive. Kivgraph is Apache-2.0, runs locally over stdio, needs no API key, and currently supports Go, TypeScript, Rust, Python, and Dart. I’m excited to hear where this approach is useful and where it is not.

Report

12h ago

Forum Threads

p/kivgraph

•

12h ago

268k tokens to understand 37 repos. Kivgraph did it in 36k.

I m building Kivgraph, a local semantic code graph for AI coding agents. It maps symbols, dependencies, and cross-repository relationships so an agent can answer structural questions like where is this used? or what breaks if I change it? without repeatedly reading the same files.

In my benchmark, Kivgraph and grep + reading reached 28/29 exact answers, while the graph used 36k tokens versus 268k. Grep was still cheaper for some simple searches, so I see this as a complement rather than a replacement.

The launch is scheduled for tomorrow. I d love to hear: what codebase questions make your agent burn the most context, and what would you want a tool like this to expose?

View all