DOCS Manual · IDE plugins

Your AI assistant burns tokens reading files. This makes it stop.

Cheburnexus indexes your project at compiler level — the same understanding a compiler has, not text search — and serves your LLM exactly the code it needs.

TypeScript / JavaScript · Python · Java

Why it makes your AI better

Without Cheburnexus
you --> LLM --> read file --> grep --> read file --> read file --> grep ...
            |__ context filling up with raw text __|
                                                   --> answer
With Cheburnexus
you --> LLM --> Cheburnexus --> structured facts --> answer
                (compiler-level index)

Wasted context is not just cost — it is worse answers. A model that spent its window on boilerplate has less room left to think about your actual problem.

Cheburnexus hands it a structured project instead: classes, call graphs, dependencies, cycles, entry points — resolved by a real compiler front-end, not guessed from patterns. Language models are dramatically better at reasoning over structure than over raw file dumps.

Every response reports how many tokens it saved you; the Cheburnexus panel keeps the total.

Using it

Ask your assistant normally — but point the model at Cheburnexus. It works for far more than search.

{{ u.title }}
“{{ u.prompt }}”
{{ u.note }}

After you change code, ask the assistant to reanalyze so the index reflects the latest source.

If the model forgets

Language models are probabilistic — yours may drift back to reading files by hand, especially in a long session. That is normal, and you fix it in one line:

“Use Cheburnexus for this, not file reads.”

Worth saying once at the start of a session, and again whenever you notice it grepping.

To make it stick permanently, put the instruction in your assistant's project rules file:

{{ ruleFileName }} · project root 
Always use Cheburnexus tools to explore this codebase before reading files directly.
Prefer get_summary, find_class and who_calls over reading or grepping files.

What it gives the model

{{ c }}

Crucially, it answers precisely or stays silent — it reports facts it can prove, never guesses.

If a signal is unknown, it says unknown rather than inventing an answer for your model to trust.

Setup

On first run the extension downloads the analysis engine — one time, verified by checksum. It is not bundled in the extension, so the download is not instant; progress is shown in the status bar.

After that it registers the engine as an MCP server automatically, injecting your project folder — there is nothing to configure. Open your project and ask.

The Cheburnexus panel in the activity bar shows your plan, engine status, and token savings.

Step-by-step install guide

License

Cheburnexus runs at Free limits with no key. Paid plans: place your claims.json license file in the path shown in the status panel, then restart the IDE.

The key is stored securely in the OS secret store. Enforcement is soft today.

Privacy

All analysis runs locally on your machine. Your code is never uploaded anywhere.

Troubleshooting

Engine not installed

Use the Engine node in the Cheburnexus panel to (re)download it.

Tools not visible

Ensure the engine finished downloading, then restart the window so the MCP server registers.

Plan still shows Free

Check claims.json sits at the exact path in the status panel, then restart the IDE.

Answers look stale

Ask the assistant to reanalyze — the index reflects the source as of the last analysis.

Still stuck? [email protected] — we answer with facts, not guesses.