CAD for code.
Deterministic search & edit tools for coding agents — delivered via MCP.
Today's tools are fast, flexible, and great at finding text.
But code isn't text.
It has structure, syntax, relationships, and meaning.
Text tools see none of it — so agents loop, re-check, and hope it compiles.
Code is Data.
pandō builds a map of your code — giving agents the ability to search and edit by meaning, not just text.
Imagine a 1,000-page novel. Your protagonist is George.
Halfway through, you decide he's now Camellia.
You need to update every reference — and change nothing else.
Trivial find & replace. Both tools get it right.
Which one is George and which Alpha?
Did we catch all relations, like friend or coworker?
Structure, not Strings.
Exact
Correct Syntax
Code generated by the agent is syntactically valid (compiler-checked before commit)
Deterministic AST
Transformations validate against the Abstract Syntax Tree before commit.
Safer
Semantic Undo
Every edit gets a snapshot. Rollback from anything.
Atomic Transactions
Edits apply atomically. Either the whole graph updates, or nothing does.
Faster
10–100×
Text tools require LLM verification for every match. pandō edits the reference graph directly. No uploads, no inference.
Local Execution
pandō talks to your local disk, not the LLM. Most searches take milliseconds — just a database query.
Leaner
Token Savings
Achieves >100× token compression for some operations (e.g. rename costs the same for one or a thousand references)
O(n) → O(1) Cost
Token cost is O(n) (n = references) using text tools (for some ops). pandō is O(1): just the operation params + symbol name.
Tighter
Reduced Exposure
Some operations send no code at all to the LLM — just the intent of the transform.
Scalable Codemods
Operations like FMR require O(1) input, generate O(1) output, and modify arbitrary code volume.
Vibe Freely.
Architect Precisely.
Free VS Code extension. One install, zero config — runs alongside your stack.
Free for personal use · Organization at $999/year/dev