Back to home

Little stone, big help

HiRocky User Guide

HiRocky is a local-first desktop AI agent workbench. This guide follows a practical order—from setup to daily use—so you can get productive quickly.

1

Quick start

Install the app, configure your first model, and send your first message.

  1. Download and install

    Pick the macOS, Windows, or Linux package on the home page. If downloads are not yet available, check back for updates.

  2. First launch

    The left sidebar lists main areas; the center shows the active page. We recommend opening Settings to configure a model first.

  3. Configure a model provider

    In Settings → Models, add an OpenAI-compatible endpoint: Base URL, API key, and model name. You can add multiple providers and set a default. Use Test to verify connectivity.

  4. Send your first message

    Open Chat, create a session, choose an agent, and type in the composer. Replies stream in real time.

Tip

API keys are stored on your device and are not uploaded to a HiRocky cloud by default.

2

Interface tour

The sidebar connects the modules you use every day.

  • Chat: multi-session conversations with attachments and streaming.
  • Agents: define roles, prompts, knowledge, and skills.
  • Knowledge: import documents for retrieval in chat.
  • Memories: view and edit long-term memory per agent.
  • Skills: built-in and installed tool capabilities.
  • Channels: Feishu, WeCom, WeChat personal, SaleSmartly, and more.
  • Tasks: automation tasks (evolving).
  • Stats / Logs: usage and troubleshooting.
  • Settings: models, theme, language, and data locations.
3

Chat and agents

Sessions are where you work; agents define behavior and capabilities.

  1. Create or pick an agent

    On the Agents page, add a role with a system prompt and default model. Use prompt helpers to draft or refine instructions.

  2. Manage sessions

    Each session can bind an agent and workspace folder. Search, rename, or delete sessions. Long chats may trigger context compression with a recoverable summary.

  3. Messages and attachments

    Markdown is supported; attachments depend on agent capabilities. Stop generation anytime or regenerate a reply.

  4. Normal vs expert view

    Normal view focuses on the answer; expert view shows steps, tool calls, and timing—useful for debugging.

Tip

Use separate agents per project and bind the right knowledge bases.

4

Knowledge bases

Ground answers in your own documents.

  1. Create a library

    Add a knowledge base with a clear name (e.g. product docs, notes).

  2. Import files

    Supports TXT, Markdown, PDF, Word, PPT, Excel, RTF, and more. Text is extracted and indexed locally.

  3. Use in chat

    Bind libraries to agents so relevant chunks are retrieved automatically. Export libraries for backup.

5

Long-term memory

Let agents remember preferences and project context across sessions.

  • Memories can be organized after conversations (behavior may vary by settings).
  • Review, edit, or delete entries on the Memories page per agent.
  • New sessions can reuse existing memories to avoid repeating yourself.
Tip

Memory stays on your machine—you can clear outdated entries anytime.

6

Skills

Tools the AI can call: files, browser, weather, presentations, and more.

  • Built-ins: time/math, knowledge retrieval, filesystem, browser automation, weather, slides, controlled shell.
  • Enable capabilities per agent; expert view shows each tool run.
  • Install extensions from folders, ZIP archives, or URLs.
  • File and shell skills are scoped to the session workspace; shell uses a whitelist.
7

Channels

Reply on Feishu, WeCom, WeChat, and other messaging surfaces.

  1. Open Channels

    Choose a platform and follow in-app instructions.

  2. Authorize

    Provide app credentials or scan to log in. WeChat personal credentials stay local. Feishu official APIs are recommended first.

  3. Assign an agent

    Route inbound messages to an agent so external chats use the same skills and knowledge.

Tip

Channel features evolve—refer to the latest in-app guidance.

8

Tasks, stats, and logs

Monitor usage and diagnose issues.

  • Tasks: scheduled or triggered automation (in progress).
  • Stats: sessions, messages, tokens, and channel volume.
  • Logs: redacted local logs for safer debugging.
9

Settings and data

Personalize the app and find where data lives.

  • Models: multiple OpenAI-compatible providers and defaults.
  • Appearance: light or dark theme.
  • Language: English and Simplified Chinese in the app UI.
  • Data location: view database and file paths for backup.
10

Quick troubleshooting

Common fixes before asking for help.

  • Cannot reach the model: verify URL, key, network, and model name; run Test in Settings.
  • Slow or cut-off replies: rate limits or long context—try compression or a faster model.
  • Skill failures: check expert view; confirm workspace path and permissions.
  • Channels silent: refresh credentials and check status on the Channels page.

Ready to begin?

Head back to the home page to download the app or explore features.

Back to home