Context for coding agents

Give coding agents full change context.

Glaux shows hidden coupling, surfaces files an agent would miss, and explains what to verify before a change lands.

src/core/browser.tsHIGH RISK84% confidenceunstable
{ }What The Agent Sees
changeRisk:high
reviewFirst:dispatcher.ts, fetcher.ts, errors.ts
primaryDrivers:hidden_coupling, high_centrality
suggestedChecks:cross-module-regression
Files You Should Review First3 hidden · 1 expected
hidden
src/core/dispatcher.ts
Co-changed 7× · no import path found
hidden
src/network/fetcher.ts
Co-changed 5× · no import path found
expected
src/core/page.ts
Import edge · frequently co-changed

The Problem

Agents edit code without knowing what they're missing.

A coding agent reads the file it was asked to change. It misses the files that have always changed alongside it. It doesn't know this file is a coordination point for three other modules. It makes the edit. The PR surprises the reviewer.

01

Edits one file

The agent reads the file it was asked to change and nothing else.

02

Misses hidden dependencies

Three other files always change with this one. No import connects them. The agent doesn't know.

03

Causes follow-up fixes

The change lands. Review catches the missing updates. The cycle repeats.

The Solution

Before an agent edits a file, Glaux tells it what it's missing.

One MCP call returns a decision-ready briefing: risk verdict, hidden coupling, files to read first, and verification hints. The agent gets full context before touching anything.

01

Select a file

Agent picks the file it's about to change.

02

Get risk verdict

Glaux returns a risk level and confidence score instantly.

03

See missing files

Hidden coupling, expected partners, dormant dependencies — all surfaced.

04

Verify the right areas

Deterministic check types: cross-module regression, downstream callers.

Why It Works

Three graphs. One context block.

Glaux combines git history, structural dependencies, and semantic understanding into a single context layer. No single source of truth reveals what all three together do.

Git graph

What changes together

Co-change patterns across thousands of commits reveal behavioral coupling that no import graph captures.

Static graph

What depends on what

Tree-sitter static analysis resolves imports, symbol calls, and inheritance across the whole repo.

Semantic graph

What the code means

Community detection clusters files into logical modules. PageRank surfaces which files are structural hubs.

Glaux

Turns all three into one decision-ready context block for the agent.

What It Produces

Real product language, not raw metrics.

Glaux doesn't return centrality scores and pagerank. It returns decisions.

Files You Should Review First

most actionable

Hidden coupling: files that co-change with no import path. Expected partners. Dormant dependencies.

Why This File Is Risky

explains the risk

Primary drivers with evidence: hidden coupling, top 4% centrality, 94% paired change rate.

What To Verify

actionable checks

Deterministic check types: cross-module regression, downstream callers, paired-file review.

Change Pattern

behavioral context

How often this file changes, whether it ever changes alone, its paired change rate.

What The Agent Sees

full transparency

The exact context block Glaux delivers via MCP: changeRisk, reviewFirst, primaryDrivers, suggestedCheckTypes.

Risk Verdict

decision-first

High / medium / low with confidence score. One line tells the agent how carefully to proceed.

Built for coding agents

Glaux makes coding agents safer on complex repos.

Any agent that speaks MCP gets full change context automatically. No prompt engineering. No manual documentation. One tool call.

Claude CodeCursorCodexWindsurfCustom agents

Also available as a REST API for custom integrations, dashboards, and CI pipelines.

Early Access

Give your agents full change context.

Want to see Glaux running on your repo? Reach out and we'll get you set up.

Drop us a line

Tell us about your repo and we'll get you set up.

hello@glaux.dev