LIVE · AXIOS CALL GRAPH · CLICK ANY FUNCTION TO TRACE ITS BLAST RADIUS
Try:

Your agents break less code and burn fewer tokens.

Every function · every call between them · mapped in ~3 s · no LLM
$ npx -y @ghostlygawd/codeweb . ready · your repo in ~3 s
Free & MIT · v0.12.0 · runs on your machine · never executes your code
Callers found before an edit
GREP44%
CODEWEB74%
Agents break code they can't see
"What breaks if I change this?"
126×
Cheaper than grepping in rounds
Independent checks
490K+
0 disagreements
One graph, two interfaces

Built for the humans and the agents editing the code

codeweb computes one structural graph and serves it two ways, so you and the agents editing your code share the same map.

For humans

An interactive map

One self-contained HTML report — the dependency web, duplication, hotspots, and ranked, cycle-safe consolidation. No CDN, no network, opens straight from disk.

For agents

27 deterministic tools

Over MCP, your agents ask what already does this, what an edit breaks, and which fix is safe — before they write a line. No LLM in the analysis loop, so answers don't drift.

How it works

A four-stage deterministic pipeline

Parse-free extraction on the fast path for JavaScript, TypeScript, Python, Rust, Go, Java, C#, Ruby, PHP, Kotlin, and Swift, with an agent fallback for everything else.

01

extract

Parse-free atomic nodes + edges, per language.

02

cluster

Group nodes into semantic domains by call gravity.

03

overlap

Body-confirm cross-domain duplication and rank it.

04

render

A self-contained interactive map + 27 agent tools.

Where you point it

Your repo — and any repo you're considering

Map your own codebase

See the real dependency web, find where logic is duplicated, and get an ordered, cycle-safe plan to consolidate it.

Review before you adopt

Clone a third-party repo read-only, fully map it, and get an adoption review before you commit to depending on it. codeweb never runs the target.

Benchmarks

Every claim comes with its data

Tested against independent checkers. The failures are published alongside the wins.

126×

cheaper "what breaks if I change this?" answers — one codeweb call vs an agent grepping in rounds (measured).

0 disagreements

across ~490,000 checks of codeweb's answers against independent implementations: who calls what, what an edit breaks, where the cycles are.

44% → 74%

of a function's callers found by AI agents: grep vs codeweb, same context budget, better in all 5 runs (v0.9.0 pilot). Your agents break code they don't see.

For learners and experts alike

Approachable at the surface, deep when you need it

New to the codebase? Open the map, follow the foundations-first reading order, and see the domains at a glance. Shipping at scale? Wire the CI gate and drive the 27 MCP tools from your agents, on graphs of 16k+ symbols.

  • Beginners — one command, one map, plain-language findings.
  • Advanced — deterministic tools, fitness rules, sharded subgraphs, a PR gate.
codeweb interactive report: a force-directed domain graph of the axios codebase

The live report — a real map of axios (274 symbols, 8 domains). Open the interactive demo →

The point of all of it

Ship bigger changes with fewer surprises

You and your agents see the same map before any of you edits. You find the right code faster, and you break less of it. Every claim on this site is measured, and the failures are published too.

Want the changelog when capabilities land? Watch → Custom → Releases on GitHub — release notes are the only announce channel this tool has.