Full size image
Checking...

Start a conversation

Send a message or attach a file to begin chatting with your local LLM.

~0 tokens

Parameters

Temperature ⓘ 0.7
PreciseCreative
Top P ⓘ 0.90
FocusedDiverse
Repeat Penalty ⓘ 1.10
OffStrong
Parameters are only sent to Ollama when changed from their defaults. Saved per thread.
Processing...

Settings

Appearance

Theme

Processing

Text Chunk Size (bytes)
PDF Pages per Chunk
Context Window (messages)

API Configuration

Ollama Endpoint
Perplexity API Key
OpenAI API Key
Tavily API Key
Gemini API Key

Agentic Functions

Auto-title Threads
LLM names thread after first exchange
Auto-search (Tavily)
LLM decides when to search (single pass)
Auto-summarise Context
Summarise older messages when context fills
Auto Fact-check
Verify factual claims via Tavily
⚗ Experimental Off by default — may affect performance
Agent Loop
LLM iteratively searches to refine answer
Proactive Clarification
LLM asks if prompt is ambiguous
Suggested Follow-ups
Show clickable follow-up questions
Auto-extract Memories
Persist key facts across threads
Auto-attachment Strategy
LLM picks best processing method ⚠

WebGPU Model ○ Chrome / Edge only

Enable Qwen3.5:0.8b (WebGPU)
Runs entirely in-browser, no Ollama needed
~850MB download, cached by browser after first use. Appears in model selector when enabled.
Model status Not loaded

Danger Zone

Clear all messages in thread
View & manage memories
Clear all memories
Reset entire database

Create New Thread

Remembered Facts

Facts injected into every Ollama conversation as context. Delete any that are wrong or no longer relevant.

Keyboard Shortcuts

Send message
Enter
New line
Shift Enter
New thread
Alt N
Search messages
Alt S
Open settings
Alt ,
Show shortcuts
Alt /
Toggle fullscreen
F11
Close modal
Esc