Open source · Personal assistant with agent capabilities

Your AI assistant
for code and desktop.

Kaoru talks with you, remembers context and stays with you through text, voice and a Live2D presence. It can also work as an agent: investigate your project or chain results across desktop apps, with a visible plan, permissions and checks.

Write to Kaoru in chat; it can reply with synthesized speech. The interface is available in English, Spanish and Japanese since v2.3.

Kaoru Live2D
Kaoru’s Live2D avatar. You can choose another model with the appropriate usage rights.
Kaoru’s Live2D avatar. You can choose another model with the appropriate usage rights.
Conversation with contextTasks with toolsVoice and local memoryLive2D presence
KAORU / Requirements

What your device needs

Provisional minimums for using a remote AI provider. This starting point comes from one Linux x64 measurement and still needs validation on more devices and platforms.

Terminal agent and chat

No windows, voice or avatar. Installed from source.

Resource Minimum Recommended
RAM 4 GB 8 GB
CPU 2 cores 4 cores
Free disk 2 GB 4 GB

Dedicated GPU: not required with a remote provider.

Desktop with Live2D

Chat, memory and avatar; voice optional.

Resource Minimum Recommended
RAM 8 GB 16 GB
CPU 2 cores 4 cores
Free disk 3 GB 5 GB

Dedicated GPU: optional; graphics acceleration improves the avatar.

Voice, Chromium and local AI models may need more resources. A local model's GPU requirement depends on that model; no universal minimum has been measured yet.

01 / KAORU

More than a coding agent

Talk with Kaoru, ask it to remember what matters or delegate a multi-step task. It can help across your project and desktop; available capabilities depend on your provider, operating system and permissions.

01

Work in a repository

Explore files, dependencies and LSP symbols to inform a plan. Read and edit code, run commands and use Git. The structural index is bounded; references and file contents still need confirmation through project tools.

02

Check changes

In the smart workflow, a recognized mutation triggers configured verification. Compatible focused tests run before general checks; a skipped or failed result does not count as a passed test.

03

Resume an objective

Objectives, steps and evidence can persist in SQLite so work can continue. If storage falls back to memory, that continuity does not survive application shutdown.

04

Keep context in conversation

Local memory retrieves facts, preferences and episodes related to a conversation. You can ask Kaoru to forget memories. Retrieved context may be included in a request to your AI provider.

05

Use voice and an avatar

Edge TTS generates speech through a Microsoft service. Microphone input is not available in the current interface. The avatar supports configurable models and gestures.

06

Chain desktop tasks

Ask for several results, such as opening a report, creating a reminder and confirming both. Kaoru reviews the plan, asks for initial authorization and checks each result; missing evidence pauses the mission. Beta: tested with scripted scenarios, without external validation yet. Accessibility varies by app, and macOS lacks semantic parity.

07

Connect your tools

GitHub and local plugins expand available tasks. Review each tool's permissions and origin before using it.

08

Receive timely suggestions

Configured sensors provide system and project signals. Proactivity evaluates context and policies to suggest help; it does not grant the model additional execution permissions.

09

Choose where the model runs

Configure a compatible provider or a local endpoint. Quality, cost, vision and tool availability depend on the selected model and service.

10

Terminal and chat side by side

Open a chat beside a terminal in the same project. Review selected or recent output before choosing to send it to the model; Kaoru does not send it automatically. Single-line shell snippets can be pasted or run after confirmation.

02 / KAORU

From conversation to results

Ask for guidance, continue a conversation or delegate several results in a desktop mission. Kaoru interprets the request with your chosen model and shows its plan and tool activity in chat; permission and verification are decided outside the model.

  1. 01

    Inspect

    Examine the workspace, find relevant paths and consult available symbols.

  2. 02

    Plan

    Break the objective into observable results and review whether any are missing.

  3. 03

    Authorize

    A desktop mission asks for initial authorization; out-of-scope actions require their own permission.

  4. 04

    Execute

    Use tools and retain their results as evidence of the work.

  5. 05

    Verify

    Check each result in the environment; missing evidence pauses the mission with a pending step.

03 / KAORU

Choose what Kaoru can access

Configure permissions for your task and device. The application separates model proposals from the controls that authorize tools.

Tool permissions

Allow, ask and deny rules automate specific operations, request confirmation or block them. Not every action displays a prompt: the active policy determines that.

Separate desktop capabilities

Applications, browser, screen, pointer, keyboard, processes and camera have independent controls. The current camera tool checks status or opens the camera application; it does not take photos or record video.

Isolation depends on the environment

Electron windows are isolated from direct Node access. Command isolation is a separate mechanism and depends on the system’s capabilities and configuration.

Checkpoints and recovery

Kaoru captures a baseline for recognized changes. Recovery has limits: remote actions, arbitrary commands and external effects may not be reversible.

External content

Web and integration results are treated as untrusted content in the flows that delimit them. These controls reduce the risk of malicious instructions; they do not guarantee immunity.

Data and credentials

Memory and embeddings are stored locally. Prompts may leave the device for your chosen provider. The system keychain is used when available; configuration backups require care.

04 / KAORU

Set up Kaoru for the way you work

Personal use

Start with conversation, one workspace and the permissions you need. Enable voice, memory or suggestions to suit your routine; you can change the Live2D model.

Development

Declare repository rules, prepare dependencies and configure verification commands. Review diffs and results before integrating important changes.

Teams and client projects

Define what information may reach the provider, who manages credentials and which tools are allowed. The code license does not cover characters or replace your organization’s policies.

On your desktop

Actual project screenshots. Appearance varies with your model and configuration.

KAORU / User guide

Start with a conversation. Delegate when you need to.

Choose a provider and a project. You can begin with a question or request a small result you can check. The guide covers installation, permissions and platform limits.

  1. Install and open Kaoru.
  2. Configure the provider and select a workspace.
  3. Request a read-only analysis before allowing changes.