Chat with Your Code
Chat with Your Code turns a repository into a queryable knowledge surface. Ask 'where is auth handled?' or 'what does this script do?' and get answers grounded in your actual files.
What it is
Folder-scoped LLM chat with file-citation grounding and per-session persistence.
Why it's useful
Removes the cold-start cost of reading an unfamiliar codebase; pairs nicely with static analysis findings.
How Decoder implements it
Folder-scoped chat sessions persist across logins; answers cite the files used; tone and proficiency hydrate from your profile.
When to use it
Onboarding, code review prep, exploring third-party drops, drafting documentation.
When NOT to use it
Production decisions without verifying the cited code — LLMs still hallucinate.
Practical example
'Where does this app validate uploads?' → Decoder cites the relevant server function and quotes the zip-slip guard.
FAQ
Glossary
- Grounding
- Anchoring an LLM answer in retrieved source content rather than the model's general knowledge.
Related
Repository Analysis turns a codebase into something you can read, search and interrogate. Upload a ZIP or import a public GitHub project; Decoder indexes structure, runs static checks and gates AI features behind your own key.
BYOK means you bring your own AI provider key. Decoder never proxies AI calls through a shared account: your key, your billing, your privacy boundary.
Local AI lets you use Decoder's explain and chat features against a model running on your own hardware via Ollama or LM Studio — useful when code cannot leave your environment.
Ollama is a lightweight runtime for serving open-weight LLMs locally. Decoder talks to it through its OpenAI-compatible endpoint.
AI-Origin Detection estimates whether a code artefact was likely produced by an LLM, and explains why. The goal is informed review, not gatekeeping.