Chat & Sessions
Multi-model chat, session history, artifacts, search, and export workflows.
Basic Chat
Open the Chat page to start a conversation. HexClaw supports:
- Streaming responses - token-by-token rendering while the model is generating
- Markdown rendering - full Markdown support with syntax highlighting for code blocks
- Model switching - swap providers and models at any point within the same session
- Message actions - copy, edit, and regenerate responses
Files & Multimodal Inputs
The composer supports multiple attachment types depending on the selected model's capabilities:
| Input Type | Supported Models |
|---|---|
| Images | GPT-4o, Claude family, Gemini family, Qwen-VL, Doubao Vision, and LLaVA |
| Video | Gemini 2.5 and 2.0 family models |
| Audio | Gemini 2.5 and 2.0 family models |
| Files | All text-capable models with automatic content extraction |
Session Management
- New session - click the "+" button in the sidebar
- Session history - browse and reopen prior conversations from the left panel
- Delete session - remove a conversation through the context menu or swipe action
- Persistent storage - all messages are saved in the local SQLite database
Artifact Preview
When a response contains code or structured output, HexClaw can extract it into an artifact:
- Supported types:
code,html,markdown, andfile - Code artifacts include syntax highlighting and one-click copy
- HTML artifacts can be previewed live in the side panel
Message Search
Use Search Conversations (⌘+F) to search message content across every session.
Exporting Messages
Open the session menu and choose Export. HexClaw supports three formats:
- JSON - structured data for backup and re-import
- Markdown - readable output for archiving and sharing
- PDF - formatted output for formal documentation
@ Mentions
Type @ in the composer to open the mention menu and quickly bring an agent or teammate into the conversation context.
Chat Modes
HexClaw offers three chat modes, switchable via the tabs at the top:
| Mode | Purpose | Description |
|---|---|---|
| Chat | General Q&A | Standard chat, direct conversation with an LLM |
| Agent | Task execution | The agent plans autonomously, invokes tools, and executes multi-step tasks |
| Deep Research | Research reports | Multi-step search → analysis → synthesis → report generation, with a 4-stage progress panel |
Document Parsing
You can upload document files directly in chat. HexClaw automatically extracts text content and sends it to the LLM as context:
| Format | Supported Types |
|---|---|
.pdf — extracts text from all pages, displays page count | |
| Word | .docx — extracts body content |
| Excel | .xlsx / .csv — extracts each sheet as tabular text |
| Plain text | .txt / .md / .json |
Text exceeding 50,000 characters is automatically truncated with a warning.
Chat Parameters
Click the ⚙️ Parameters button in the chat toolbar to adjust parameters for the current session:
- Temperature (0 to 2) — higher values produce more creative responses, lower values are more deterministic
- Max Tokens (256 to 128,000) — maximum length of a single response
Parameters apply only to the current session and do not affect other sessions.
Message Actions
Context Menu
Right-click (or long-press) on a message bubble to open the context menu:
- Copy — copy the message content to the clipboard
- Retry — delete the current reply and regenerate
- Edit — modify a sent user message and fetch a new response
- Delete — remove the message (also deletes the database record)
Session Renaming
In the left session list, double-click a session title to rename it directly. You can also choose "Rename" from the context menu.
Token Count
The toolbar displays an estimated token count for the current session (e.g., ~1.2k tok), helping you gauge context window usage.
Voice Input
Click the 🎤 microphone button next to the input box to start speech recognition (STT). After recording, the transcribed text is automatically inserted into the input box. Requires browser Web Speech API support or an external STT service configuration.
Chat Shortcuts
| Shortcut | Action |
|---|---|
Enter | Send message |
Shift + Enter | New line |
⌘ + F | Search messages |
Esc | Stop generation |
@ | Mention an Agent / Skill |