Axon

The knowledge graph for your codebase — explore it visually, or let your AI agent query it.

Indexes any codebase into a structural knowledge graph — every dependency, call chain, cluster, and execution flow. Explore it through an interactive web dashboard with force-directed graph visualization, or expose it through MCP tools so AI agents get full structural understanding in every tool call.

$ axon analyze .

Walking files...               142 files found
Parsing code...                142/142
Tracing calls...               847 calls resolved
Analyzing types...             234 type relationships
Detecting communities...       8 clusters found
Detecting execution flows...   34 processes found
Finding dead code...           12 unreachable symbols
Analyzing git history...       18 coupled file pairs
Generating embeddings...       623 vectors stored

Done in 4.2s — 623 symbols, 1,847 edges, 8 clusters, 34 flows

Then explore your codebase visually:

axon ui                      # Opens interactive dashboard at localhost:8420

Three views, one command:

• Explorer — Interactive force-directed graph (Sigma.js + WebGL). Click any node to see its code, callers, callees, impact radius, and community. Community hull overlays show architectural clusters at a glance.
• Analysis — Health score, coupling heatmap, dead code report, inheritance tree, branch diff — your codebase health in one dashboard.
• Cypher Console — Write and run Cypher queries against the graph with syntax highlighting, presets, and history.

Plus: command palette (Cmd+K), keyboard shortcuts, flow trace animations, graph minimap, and SSE-powered live reload when watch mode is active.

---

The Problem

Your AI agent edits UserService.validate(). It doesn't know that 47 functions depend on that return type, 3 execution flows pass through it, and payment_handler.py changes alongside it 80% of the time.

Breaking changes ship.

This happens because AI agents work with flat text. They grep for callers, miss indirect ones, and have no understanding of how code is connected. Context windows are finite. LSPs don't expose call graphs. Grepping gives you strings, not structure.

The agent needs a knowledge graph — not more text.

---

How Axon Solves It

Most code intelligence tools give the agent raw files and hope it reads enough. Axon takes a different approach: precompute structure at index time so every tool call returns complete, actionable context.

A 12-phase pipeline runs once over your repo. After that:

• axon_impact("validate") returns all 47 affected symbols, grouped by depth (will break / may break / review), with confidence scores — in a single call
• axon_query("auth handler") returns hybrid-ranked results grouped by execution flow, not a flat list of name matches
• axon_context("UserService") returns callers, callees, type references, community membership, and dead code status — the full picture

Three benefits:

1. Reliability — the context is already in the tool response. No multi-step exploration that can miss code.
2. Token efficiency — one tool call instead of a 10-query search chain. Agents spend tokens on reasoning, not navigation.
3. Model democratization — even smaller models get full architectural clarity because the tools do the heavy lifting.