PANACHES symbol PANACHES
Language EN
Français English Español
Theme Night

AI

Amber AI

PANACHES' built-in AI engine to summarize, write, code and document, with conversation memory and a RAG knowledge base over your own sources.

Download All features
Icon for the Amber AI module in PANACHES
App access
Amber AI
Target module
AI
Reference
PANACHES' local AI assistant, offline by default.
Screenshot of the PANACHES Amber AI chat panel.

Module overview

An AI that stays on your machine, useful from the first question

Amber AI is the artificial intelligence engine built into PANACHES: conversational chat with memory and searchable history, code and documentation generation from the editor (function, class, script, API, test, refactor...), a local knowledge base (RAG) to query your own documents with citations and a confidence score, seven AI personality profiles and a reusable prompt library. Models run on your machine, with automatic GPU detection, no Internet connection required.

What the module brings

  • Chat with AI, with history, search and conversation export.
  • Generate code, tests, documentation and technical explanations from the editor, choosing the type and style.
  • Query your own locally indexed documents (RAG knowledge base), with citations and a confidence score, without sending that content to a forced cloud.
  • Choose among seven AI personality profiles and save your favorite prompts in a reusable library.
  • Switch local models on the fly (Gemma, Mistral, LLaMA, Qwen...) depending on the task and your machine's power.

In practice

What the module brings.

Amber AI runs on local Gemma, Mistral, LLaMA and Qwen models with automatic GPU/CPU detection, streaming responses, seven personality profiles, a reusable prompt library and a RAG knowledge base with source citations over your own documents.

For : Developers, writers, analysts, any creative profile who wants AI without depending on the cloud

Capabilities

What you can do.

  • Local streaming chat
  • Code and doc generation
  • Local RAG knowledge base

Module overview

Real situations

Offline question

Ask Amber AI a question on a train or without network access: the local model answers instantly, with no connection.

Instant documentation

Generate a first draft of documentation or unit tests from the code editor, then review and adjust it.

Searching your own notes

Enable the knowledge base, index a folder of PDFs or notes, then ask questions that cite your sources.

Switching models for the task

Switch from a general-purpose model to a code-oriented model for a refactoring session, without losing the conversation history.

Workflow

A concrete use case.

  1. Open the Amber AI panel
  2. Ask a question, attach a file or enable the knowledge base
  3. Follow the streaming answer, with citations if RAG mode is active
  4. Reuse the answer in a document, code or a moodboard
  5. Find the conversation again later through the searchable history

PANACHES connections

Code editor Jupyter Word Excel PDF EPUB Web Sticky notes

Same family

Related modules.

Icon for the External AI agents module in PANACHES

External AI agents

Invite Claude Code, Codex or OpenRouter into the chat, one agent at a time, with explicit permissions and an encrypted API key.

Explore