Composure
Code Graph

Understand your codebase instantly

The code graph indexes every function, import, and dependency. When you change something, it knows exactly what else might break — in under 5 seconds.

30x

Fewer tokens

vs Explore agents for discovery

9x

Faster

<5 seconds vs 45+ seconds

0

Blind spots

Finds systems agents miss

15s

To build

Full graph from scratch

Discovery is the hidden cost of AI coding

Explore agents burn tokens

Each Explore agent spawns with ~20K tokens of overhead. Three agents for a single feature = 60K tokens before any code is written.

Agents miss systems

Pattern-based file search misses code that doesn't match expected naming. In one test, agents missed 8 existing systems that the graph found instantly.

45+ seconds per discovery

Multiple agents searching in parallel still takes 45+ seconds and produces 9,000 words of context. Graph queries return in milliseconds.

One graph. Every answer.

Composure parses your codebase with tree-sitter AST analysis across 8 languages. Every function, class, type, import, and test relationship is indexed in a SQLite database. Query it instantly — callers, dependencies, blast radius, entity scope — all without spawning a single agent.

terminal
$semantic_search_nodes({ query: "auth" })$→ Found 12 nodes: AuthProvider, useAuth, login(), ...$get_impact_radius({ changed_files: ["src/lib/auth.ts"] })$→ 3 files direct, 7 indirect, 2 untested$query_graph({ pattern: "callers_of", target: "handleLogin" })$→ 12 callers across 8 files$Total: 3 queries, ~500 words, <5 seconds$(vs 3 agents, ~9,000 words, 45+ seconds)

How it works

1

Build the graph

Run /composure:initialize or /composure:build-graph. Parses all source files with tree-sitter, indexes entities and relationships into a SQLite database.

2

Query instead of exploring

Use semantic_search_nodes, get_impact_radius, query_graph, and entity_scope to find code instantly. No agent spawning needed.

3

Auto-updates on every edit

The PostToolUse hook incrementally updates the graph after every file write. It's always current — no manual rebuild needed.

4

Cross-project intelligence

With multi-project scope, query across 15+ codebases simultaneously. Find shared patterns, detect version drift, build templates from real data.

Ready to try it?

Free for personal use. Takes 2 minutes to install.