Supermodel CLI · Early Adopter Pricing

Your AI agents shouldn't be reading files to understand your code.

Supermodel maps every file, function, and call relationship in your repo and writes .graph files next to your source. Agents read them automatically — 40%+ fewer tokens, no prompt changes.

Read the docs
$ curl -fsSL https://supermodeltools.com/install | sh
CLI

One command. Persistent context.

↓ 40%+ token reduction

Every time an agent needs to understand your codebase, it reads files — in a large repo, that's thousands of tokens per task just for orientation. Run supermodel once and it writes .graph files next to every source file. Any agent that can read files picks them up automatically. No configuration.

"In a monorepo spanning TypeScript, Python, and Go, an agent asked to trace a data flow was reading 47 files to orient itself. With Supermodel, it reads the .graph file — same answer, 40%+ fewer tokens."

supermodel — zsh
$ curl -fsSL https://supermodeltools.com/install | sh
 
$ cd your-repo && supermodel
 
Analyzed 1,247 files
Wrote .graph files next to every source file
Watching for changes...
 
# your agent now reads .graph files automatically
# via grep and cat — no config needed
Cross-language IR

Seven languages. One graph.

TypeScript JavaScript Python Go Rust Java Ruby

Your agent thinks in files. Your codebase thinks in dependencies. Supermodel normalizes every language into one dependency graph — so cross-language edits don't break, and your agent knows exactly which files to touch.

"'Add a created_at field to the user model' — a one-liner data change that touches 11 files across 4 languages. The graph tells your agent exactly which ones."

supermodel — dependency graph
$ supermodel blast-radius models/user.py
 
models/user.py (Python)
  ├─ serializers/user.py
  ├─ handlers/user_grpc.go
  ├─ src/types/user.ts
  ├─ src/api/users.ts
  ├─ src/hooks/useUser.ts
  └─ + 6 more
 
11 files across 3 languages
  Python × 2  •  Go × 1  •  TS × 8
Dead code detection

Know what's safe to change.

Static linters read files. Supermodel reads your codebase as a graph of what calls what, across every language. When your agent needs to remove a function or rename a type, it has ground truth — not guesses.

Detection accuracy
Supermodel 94% F1

Static analysis 52% F1
Cost per analysis run
Supermodel $1.40

Claude Opus alone $219

"Deleting a 'dead' utility caused a silent runtime failure three services away. The call graph caught it before the PR."

Integration

One command. Drop it anywhere.

Install the CLI and your codebase gets a persistent graph. Any agent that reads files can use it — no config, no workflow changes, no new tools to learn.

CLI

Run supermodel in your repo. It writes .graph files next to every source file and watches for changes. Any agent reads them automatically via grep and cat.

TypeScript / Python SDK

Full API access via typed SDK. Integrate graph queries directly into your agent workflows.

REST API

Language-agnostic HTTP API. Use from CI, scripts, or any custom agent.

$ curl -fsSL https://supermodeltools.com/install | sh $ cd your-repo && supermodel .graph files written next to every source file Watching for changes

Questions

How is this different than a knowledge graph memory system?

Memory systems rely on agents subjectively selecting what to remember. A code graph is an external structural model of your system, like a blueprint or a map. It's incrementally updated as code changes, accurate because it's derived directly from your source, and useful across agents and sessions without asking any agent to decide what was worth remembering.

Do you store my code?

No. We process your code to build the graph and then immediately remove it. Your source code is not retained after processing. What we keep is the structural graph: function signatures, call relationships, dependency edges, domain classifications, and metadata.

Do you train on my code?

No. Because your source code is removed immediately after processing, it is never available to train on. We only retain the structural graph, not the code itself.

What languages does Supermodel support?

TypeScript, JavaScript, Python, Java, Go, Ruby, C++, Kotlin, Swift, Rust (experimental), Elixir (experimental), and more. 10+ languages, one API.

How does the graph stay up to date as my code changes?

The graph updates incrementally. Each file change triggers a partial update, only re-processing changed files and their affected relationships, not a full rebuild. Agents always query an accurate model of the current state of your code.

How do I integrate Supermodel with my AI agent?

Install our CLI. It drops map files next to your code. Any agent that reads files can use them. Full docs at docs.supermodeltools.com.

What's the difference between Supermodel and static analysis tools?

Static analysis tools are built for specific checks at a point in time. Supermodel builds a persistent, queryable multi-layer graph combining call relationships, dependency edges, domain classifications, and parse structure. The graph is designed to be queried by agents at runtime, stays current as code changes, and works across languages and repositories.

Are you GDPR/ITAR compliant?

If your business needs special compliance, send us a message at [email protected].