Why does your agent open the wrong file when you ask a simple question?
Ask where you handle logins and your agent hunts for login.ts, misses the real file buried three folders deep, and hands you a confident answer about the wrong code. Nectar gives every file a plain-language description of what it actually does, so your agent finds code by meaning and stops guessing from names.
curl -fsSL https://get.theapiary.sh | sh Why can't my agent find code that isn't named after what it does?
Because it searches names and keywords, and real codebases hide login logic in a file called session-refresh.ts. Nectar reads each file and writes down what it does, so a search for logins lands on the right one even when the name never says so.
Do I have to change how I work?
No. Nectar runs quietly and keeps its descriptions current as files change, and the better answers surface right inside your assistant through Honeycomb's shared memory. You ask the same questions and get the right files back.
How does it match meaning instead of keywords?
The descriptions live on Deeplake, which searches by meaning, so 'anything about logins' finds the right file even when you would never have guessed its name or where it sits. It is the book index that actually read every chapter.
Will it keep up as the code moves?
Yes. Nectar re-reads files as they change, so a renamed or relocated file still gets found by what it does. Poorly named, buried, or freshly moved, your agent still lands on it.
How much time do your engineers lose because AI reads the wrong code?
Your developers' agents find code by file name, so in a real codebase they read the wrong files, answer confidently about the wrong thing, and hand the search back to the engineer. Nectar describes every file by what it does and stores that on Deeplake, so agents find the right code by meaning, once, for the whole team.
What does 'the agent read the wrong file' actually cost us?
Every wrong file is a wasted turn you pay for and a confident answer your engineer has to catch and correct. Nectar points agents at the files that actually matter, so they spend tokens on the right code the first time.
How does one engineer's understanding reach everyone?
Nectar's descriptions are a portable registry: build the understanding once and the whole team inherits it when they pull the project, with no re-indexing per person. A new hire's agent is useful on day one instead of week three.
Where does this live, and is it secure?
On Deeplake, reached only by the local daemon, with teams and projects isolated at the storage layer and secrets never exposed. The descriptions are versioned, so the map of your codebase is auditable, not a black box.
Why is meaning-based recall a moat, not a nice-to-have?
Deeplake matches on what code does, at scale, so agents find the right file even when nobody named it well, which is most real code. That accuracy compounds across every question every engineer asks, all day.
