Novaya-AI

Novgraph — Git skill for Claude Code

Git community

How to install Novgraph

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Novaya-AI/novgraph and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Novgraph does

A live knowledge graph of your codebase for coding agents: commit intent, co-change coupling, ranked blast radius, computed architecture - over MCP or the shell, at 78-99.74% token savings measured per answer. Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf, Cline, OpenCode. Python 3.11+.

Alternatives in Git

Cc Usage — by ryoppippi - Handy CLI tool for managing and analyzing Claude Code usage, based on analyzing local Claude Co 11.7k ★
Destructive Command Guard — The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by ag 869 ★
Self Reflect — Extract learnings from recent PR reviews, conversations, and session patterns to update the knowledge base 402 ★

README

novgraph

**A live knowledge graph of your codebase, queried by coding agents.**

[![PyPI](https://img.shields.io/pypi/v/novaya?label=pypi%20%C2%B7%20novaya)](https://pypi.org/project/novaya/) [![Python](https://img.shields.io/pypi/pyversions/novaya)](https://pypi.org/project/novaya/) [![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE) [![CI](https://github.com/Novaya-AI/novgraph/actions/workflows/ci.yml/badge.svg)](https://github.com/Novaya-AI/novgraph/actions/workflows/ci.yml)

Command-line client for **Novgraph**, a hosted **knowledge graph** of a git repository. The graph holds your files and symbols as nodes and their real relationships as typed edges, and coding agents query it over MCP or the shell for four things a file read cannot give them: the recorded intent behind each commit, files that change together without importing each other, ranked blast radius, and computed architecture.

**Token savings: 78% to 99.74% per answer**, measured against the cost of reading the files each answer cites — not modelled, not estimated from a benchmark.

This repository is the client only — auth, agent detection, MCP registration and request transport. Python 3.11+, standard library, **no dependencies, no engine**. Indexing, storage and retrieval run on Novaya's servers.

uv tool install novaya      # the PyPI package is `novaya`
novgraph install       # generate a key at https://app.trynovaya.com

`install` detects every supported agent on the machine, registers the MCP server, writes a pointer into each agent's instruction file, adds a `/novgraph` command, resolves which indexed codebase this checkout is, and verifies each step. `novgraph doctor` re-runs those checks with an exit code.

What problem it solves

A coding agent starts each session with no memory of the repository. To answer "what does this touch", it greps, opens files, and infers — spending tokens to rebuild a picture it loses at the end of the session. T