Build and configure personal AI agents with memory, personality, and autonomy using OpenHanako on Electron.

OpenHanako Personal AI Agent Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. OpenHanako is a desktop AI agent platform built on Electron that gives each agent persistent memory, a distinct personality, and the ability to autonomously operate your computer — read/write files, run terminal commands, browse the web, execute JavaScript, and manage schedules. Multiple agents can collaborate via channel group chats or task delegation. Installation Download & Run Build from Source First Run Onboarding On first launch, the wizard asks for: 1. Language — UI language preference 2. Your name — used by agents when addressing you 3. Model provider — any OpenAI compatible endpoint 4. Three models: chat model — main conversation (e.g. gpt 4o , deepseek chat ) utility model — lightweight tasks, summarization (e.g. gpt 4o mini ) utility large model — memory compilation, deep analysis (e.g. gpt 4o ) Provider Configuration Examples Project Architecture Key Managers (via unified engine facade) Manager Responsibility AgentManager Create, load, delete agents SessionManager Conversation sessions per agent ModelManager Route requests to configured providers PreferencesManager User/global settings SkillManager Install, enable, disable, sandbox skills Agent Configuration Each agent is a self contained folder you can back up: Personality Template Example Skills System Skills extend agent capabilities. They live in skills2set/ (built in) or are installed per agent. Install a Skill from GitHub Skill Definition Format (SKILL.md → skills2set) Writing a Custom Skill (JavaScript) Memory System OpenHanako uses a recency decay memory model: recent events stay sharp, older ones fade. Memory Tiers Tier Storage Decay Working memory working.db (SQLite) Fast — recent N turns Compiled memory compiled.md Slow — summarized by utility large model Desk notes (Jian) Files on desk Manual / no decay Built in Tools Tools available to agents out of the box: Sandbox Access Tiers (PathGuard) OS level sandbox: macOS Seatbelt / Linux Bubblewrap wraps the skill process. Multi Agent Setup Scheduled Tasks (Cron & Heartbeat) Multi Platform Bridge Connect one agent to Telegram, Feishu, and QQ simultaneously: Server API (Fastify + WebSocket) The embedded Fastify server runs locally and the Electron main process communicates via stdio bridge. Testing Troubleshooting App won't open on macOS Agent not responding Check that the API key env var is set and the base URL is reachable Open DevTools ( Cmd+Option+I / Ctrl+Shift+I ) → Console for errors Verify the model name matches exactly what your provider supports Memory compilation not triggering Skill installation blocked by safety review Sandbox permission denied Check the PathGuard tier for the path being accessed Use the desktop UI: Agent Settings → Sandbox → Grant Path Access Or programmatically request elevation to Tier 3 (prompts user confirmation) Windows Defender false positive on built .exe The installer is unsigned; click More info → Run anyway in SmartScreen Add an exclusion in Windows Security if needed during development Key Links Releases: https://github.com/liliMozi/openhanako/releases Issues: https://github.com/liliMozi/openhanako/issues Homepage: https://openhanako.com Contributing: https://github.com/liliMozi/openhanako/blob/main/CONTRIBUTING.md Security Policy: https://github.com/liliMozi/openhanako/blob/main/SECURITY.md License: Apache 2.0

openhanako-personal-ai-agent