Skip to main content

Features Overview

Anyy is a resident personal assistant: one runtime, persistent context, and multiple ways to work with it.

Core Experience​

  • Persistent sessions — continue conversations across Dashboard and terminal restarts.
  • Dashboard — visual chat, configuration, health, and management.
  • Terminal Interface — streaming interactive chat with keyboard and slash commands.
  • One-shot CLI — send a prompt or inspect status from scripts.
  • Resident Gateway — keeps sessions, Channels, schedules, and background work available.

Identity and Personal Context​

  • Roles — maintain different assistant identities and Soul instructions.
  • Memory — durable personal context separate from one conversation transcript.
  • Profiles — isolated Anyy homes for different people, purposes, or environments.
  • Workspace context — store task files and artifacts used by the assistant.

Models and Media​

  • Main and fallback models — provider authentication, model selection, and ordered availability routing.
  • Media understanding — route image, video, and audio input through declared capable models.
  • Image generation — create images with a configured output backend.
  • Speech — optional text-to-speech and speech-to-text routes.

Tools and Integrations​

  • Web search — current public-information retrieval through a configured backend.
  • MCP — add, authenticate, probe, enable, and call external MCP servers/tools.
  • Skills — install reusable instruction packages and invoke their commands.
  • Files and terminal — inspect a Workspace, edit files, and run commands.

Messaging​

  • Messaging Platforms — Telegram, Discord, Slack, WhatsApp, Facebook, Email, SMS, DingTalk, Feishu/Lark, Weixin/WeChat, QQ Bot, IRC, and LINE.
  • Access policies — pairing, allowlists, open/disabled delivery, and group mention rules where supported.
  • Multiple accounts — keep platform/account connections under the resident Gateway.

Automation​

  • Scheduled automations — prompts, Skills, scripts, or notifications on a defined schedule.
  • Heartbeat — periodically record health state and report newly observed failed Cron runs.
  • Background jobs — run work in a child session, inspect it, cancel it, and receive completion notices.
  • Conversation input and steering — queue later input or redirect active work.
  • Session Search — recall earlier conversations across the current Profile.
  • Artifacts — upload source files and receive scoped downloadable deliverables.
  • Tasks — durable structured obligations with status, priority, due time, and labels.
  • Notifications — route results to the current user or trusted Channel origin.

Trust and Recovery​

  • Audit history — retain operation and execution records for inspection.
  • Backups — create and restore Profile archives. Managed secrets/ and mcp/oauth/ directories are opt-in; inline secrets in configuration or working files can still enter a normal archive. Protect every backup as private data.
  • Maintenance — checkpoint or compact state and rebuild token-estimate caches.
  • Doctor/status — inspect configuration and runtime health before changing anything.
Add capabilities in layers

Start with one tested main model and a persistent chat. Add one Channel, tool backend, Skill, MCP server, or scheduled job at a time, and verify it before adding the next.

See Quickstart for the complete first-run path.