diff --git "a/index.html" "b/index.html" --- "a/index.html" +++ "b/index.html" @@ -1,19 +1,7521 @@ - - - - - - My static Space - - - -
-

Welcome to your static Space!

-

You can modify this app directly by editing index.html in the Files and versions tab.

-

- Also don't forget to check the - Spaces documentation. -

-
- + + + + + + + + LocalMind — Private AI Chat in Your Browser + + + +
+ +
+

LocalMind

+
+
+ +
+
+ + + + + +
+
+

A private AI research agent running Gemma entirely in your browser via WebGPU. Tool calling, persistent memory, and web search — all on-device.

+

Only your search queries touch the network (and only when you choose to). All reasoning stays on your device.

+

Models are cached after first download — future visits load instantly.

+

Requirements: Chrome 113+, Edge 113+, or Firefox 130+ with WebGPU.

+
Powered by Transformers.js + Google Gemma (Apache 2.0).
+
+
+

Available Models

+
    +
  • Gemma 3 1B (~760 MB) — fast, text-only chat
    • +
  • Gemma 4 E2B (~1.5 GB) — multimodal + agent
    • +
  • Gemma 4 E4B (~4.9 GB) — multimodal + agent, best quality
    • +
+

Gemma 4 Agent Tools

+
    +
  • calculate — math, percentages, conversions
    • +
  • get_current_time — date/time with timezone
    • +
  • store_memory — save facts to persistent memory
    • +
  • search_memory — recall from stored memories
    • +
  • web_search — search the web (requires API key)
    • +
  • fetch_page — read a web page’s content
    • +
  • set_reminder — browser notification after N minutes
    • +
  • list_memories — show what’s stored in memory
    • +
  • delete_memory — forget specific memories
    • +
  • segment_image — segment objects in attached images (SAM)
    • +
+

Image Segmentation (SAM)

+

Gemma 4 can call SAM (Segment Anything Model) to segment objects in attached images. Choose your SAM model in Settings — loaded on first use.

+
    +
  • SlimSAM 50 (~10 MB) — fastest, good enough for most tasks
    • +
  • SlimSAM 77 (~14 MB) — default, better accuracy
    • +
  • SAM ViT-Base (~350 MB) — full quality, slower download
    • +
  • SAM 3 (latest) — newest architecture
    • +
+

Things to try

+
    +
  • “Segment the main object in this image”
    • +
  • “Outline the person on the left”
    • +
  • “Isolate the background”
    • +
  • “How many distinct objects are in this image?”
    • +
+

Translation works directly — Gemma 4 speaks 140+ languages natively, no tool needed.

+

Gemma 3 1B works as a simple chatbot — no agent tools.

+
+
+

Document Upload

+
    +
  • Text — .txt, .md, .json, .csv
    • +
  • PDF — extracted via PDF.js, auto-summarized
    • +
  • DOCX — extracted via mammoth.js, auto-summarized
    • +
+

Documents are chunked, embedded, and stored as searchable knowledge. A summary is generated on upload.

+

Multimodal (Gemma 4)

+
    +
  • 📎 Attach — images, audio, MP4 video, or documents
    • +
  • 📷 Camera / 🎤 Mic / Paste / Drag & drop
    • +
+

Document Upload

+
    +
  • Text — .txt, .md, .json, .csv
    • +
  • PDF — extracted via PDF.js, auto-summarized
    • +
  • DOCX — extracted via mammoth.js, auto-summarized
    • +
  • Folder — open a local folder to ingest all .md/.txt/.pdf files at once; re-open to sync only changed files (incremental)
    • +
+

Conversations

+
    +
  • New Chat — archives to History + starts fresh
    • +
  • Clear — deletes without saving
    • +
  • History — sidebar, click to resume any past chat
    • +
  • Share — generate an encrypted or plain link to share any conversation; recipient opens the URL to load it
    • +
+

Memory browser

+
    +
  • Category pills — filter by fact / preference / finding / document / conversation with live counts
    • +
  • Source grouping — document chunks grouped by file; bulk “Delete all” per source
    • +
  • Audit — flags stale (>60 days), near-duplicates (cosine sim ≥0.92), and outliers (low avg similarity to category); bulk or per-item delete; auto-reruns after each deletion
    • +
+

Output & Export

+
    +
  • Save as MD — download any response as Markdown (or write directly to open folder if one is active)
    • +
  • Code download — hover code blocks for download button
    • +
  • Export / Import — in Memory panel, full data as JSON
    • +
  • Auto-backup — toggle in Settings to download on New Chat
    • +
+

Batch Prompts

+
    +
  • Enter one prompt per line in the Batch panel — they run sequentially through the full agent loop
    • +
  • {{previous}} — explicit placeholder substituted with the previous response text
    • +
  • Auto-inject — checkbox (on by default) appends the previous response as context even without a placeholder; disabled for any prompt that already contains {{previous}}
    • +
  • Stop — halts after the current generation finishes; progress shown live
    • +
+

Other

+
    +
  • Web Search — Settings → provider + API key → 🌐 button
    • +
  • Thinking Mode — see chain-of-thought (collapses when done)
    • +
  • Cache management — view/clear cached models in Settings
    • +
  • Custom models — Settings → paste a Hugging Face ONNX repo id (causal LMs only). The validator probes the HF API, picks the best available quantisation, estimates real load size, and hard-blocks anything that exceeds the device’s WebGPU buffer limit or the 6 GB ceiling.
    • +
  • Response badges — On-device / Agent / Web-enriched
    • +
+
+
+

JavaScript API (experimental)

+

Settings → tick Expose window.localmind. Same-tab only — cross-origin scripts cannot reach it. The object is frozen and non-writable; disable the toggle to detach.

+

Surface (v1.0)

+
    +
  • version · ready · model — live state getters
    • +
  • listModels() — full registry incl. custom models with loaded flag
    • +
  • load(idOrKey) — loads a model (short key or HF id); resolves when ready
    • +
  • chat.completions.create({ messages, max_tokens, temperature, top_p, model }) — non-streaming, returns OpenAI-shaped chat.completion
    • +
  • chat.completions.create({ …, stream: true }) — async iterator yielding chat.completion.chunk objects
    • +
+

Not exposed

+
    +
  • Tools / tool calling
    • +
  • Memory read/write
    • +
  • File system, web search, search API keys, user profile
    • +
  • Multimodal input
    • +
+

Activity log

+

Every API call is logged in-memory (last 50). Click the • API chip in the toolbar or Settings → View activity log. Each call shows method, prompt length, tokens generated, duration, and outcome (ok / err / busy).

+

Demo

+

Open demo.html in the same folder. It iframes LocalMind, auto-flips the toggle, waits for the model, and runs both a non-streaming and a streaming completion against iframe.contentWindow.localmind.

+
Experimental — the shape may change before a stable v1.1.
+
+
+

Math & Conversions

+ What is 15% of 2450? + Convert 72 Fahrenheit to Celsius + Compound interest: $10K at 7% for 5 years? +

Time & Reminders

+ What time is it in Tokyo? + Remind me in 5 minutes to check the oven +

Memory

+ Remember: I'm a software engineer on Dashboard Pro + What do you know about me? + Forget my preferences +

Translation

+ Translate "Good morning" to Japanese, French, Hindi + Train station directions in Spanish & German +

Writing & Analysis

+ Write a polite meeting decline email + Microservices vs monolith: pros and cons + Explain WebGPU in 3 simple sentences +

Documents (attach a PDF, DOCX, or text file)

+ Summarize the uploaded document + Main conclusions from my document +

Multimodal (attach an image first)

+ Describe this image in detail + Transcribe text from this image +

Web Research (requires API key)

+ Top tech news today + Latest WebGPU browser support status + AI in the browser: recent articles with sources +

Coding

+ Sieve of Eratosthenes in Python + async/await vs Promises explained +
Click any prompt to paste it. Web search needs a provider in Settings. Multimodal needs a Gemma 4 model + an attached image.
+
+
+
+
+ + Initializing... +
+
+
+ + +
+ +
Drop image, audio, or video here
+ + +
+
+
🧠
+

Private AI, right in your browser

+

Gemma runs entirely on your device. Nothing is sent to any server.

+

Switch to a Gemma 4 model for tool calling, memory, and multimodal input.
Web search requires an API key (Tavily, Brave) or a self-hosted SearXNG instance.

+
+
+ + +
+
+
+
+
Preparing to download model...
+
+ + +
+
+
+
+
Loading SAM model...
+
+ + +
+ + + + + + +
+ +
Loading...
+
+
+ +
+ + +
+
+
+
+ Must be a Hugging Face repo with ONNX files under onnx/. Multimodal + custom models are not yet supported. Added models appear in the model selector. +
+
+
+ + +
+ Lets other JavaScript on this page call the loaded model via an OpenAI-shaped + method. Same-tab only — cross-origin scripts cannot reach it. No tool calling, + memory access, or web search is exposed. +
+ +
+
+ + +
+ + +
+
+ Memory + 0 memories +
+
+ + +
+
+
+
+ + + + +
+
+ + +
+
+ Batch Prompts + 0 prompts +
+ +
+ + + + +
+
+ + +
+ + + + + + + + + + API + +
+ + +
+
+ + + +
+ +
+ + +
+
+
+ + +
+
+
+ History + 0 conversations +
+
+
+
+ + +
+ Shared conversation detected + + + +
+ + +
+
+
+ API activity log +
+ + +
+
+
+
No API calls yet.
+
+
+
+ + +
+
+

Share Conversation

+ + + + + +
+
+ + +
+ +
+ + +
+
+ + + + + +
+ ⬅ More Projects + ⌨ Source +
+ + +