내 컴퓨터의 개인 AI 에이전트

Instrumentarium

The agent can use the terminal, files, web, browser, memory, and more. Most power lives in skills and plugins so the core stays lean. The matrix below is a novice bridge: job → start surface → toolsets.

New here? Start with scenarios or the capabilities catalog. Use cases · Capabilities

Back to capabilities Ecosystem Getting started

Command Center — Open ⌘. / Ctrl+. to jump from session search to storage health and token usage without leaving Desktop.

How the product looks

Desktop chat with Plan · Report · Design · Runs, Work inbox, approvals, and skills — the same surfaces the product pages claim.

Frames as of 2026-08-06 — refreshed with each Desktop release.

VibeOS Desktop chat with Plan rail — Chat + Plan rail — ask, plan, act, verify.

Work Mode inbox — Work inbox keeps goals visible after the chat window closes.

Approval gate — Sensitive actions pause for explicit approval.

Skills picker — Skills load repeatable playbooks without bloating the core.

Privacy-scrubbed Desktop captures and marketing-demo loops — not a live customer session, credential, or private project.

Where to start

Novice bridge: match the job to a starting surface, then enable the toolsets you need. Prefer skills / plugins / MCP before asking for a new core tool.

Job	Start here	Toolsets & edges
Ship code	Desktop chat + Plan rail, or CLI/TUI	terminal · file · code_execution · skills (lang/PR)
Research brief	Desktop + Research Pro preset	web · browser · research skills · optional MCP
Ops digest	Desktop or Work Mode goal	terminal · web · cron · approvals
Messaging agent	Self-hosted gateway	messaging toolset · approvals · platform adapter
Standing automation	Cron job or kanban board	cronjob · kanban · delegation (process-local)
Custom capability	Ecosystem page → footprint ladder	skill → plugin → MCP → core tool (last)

Enable/disable per platform with `vibeos tools` or config.yaml. Service-gated tools (kanban, Home Assistant, …) stay off the schema until configured.

What it can touch

Terminal & environments

Local shell, Docker, SSH, and cloud backends. Background processes with completion notify.

Files & code

Read, search, patch, and execute code; project context from AGENTS.md / CLAUDE.md / SOUL.md.

Web & browser

Web search/extract (Firecrawl, Exa, Tavily, Yandex Search, and more), browser automation, `vibeos research` workspaces/presets, and cited briefing skills.

Memory & session search

Write curated memory, recall prior sessions, optional external memory providers.

More tool families

Built-in tool families

Cron, kanban, delegate

Schedule jobs, manage multi-agent boards, spawn leaf or orchestrator subagents.

Vision, image, TTS

Multimodal analysis, image generation, speech synthesis — enabled when providers are set.

Research Pro

Cited multi-source research without growing the core tool schema: search backends, skills that grade evidence, MCP for apps, and scheduled briefings.

Search & extract

Yandex Search (RU), Exa, Tavily, Firecrawl, and more via `web_search` / `web_extract`. Preset: `vibeos research preset research-pro --apply` (or Desktop → Settings → Research Pro).

Research skills

Bundled: professional-research, source-critique, comparative-analysis, academic-literature, longform-synthesis, quantitative-analysis, analysis-orchestration, visual-source-extract. Optional RU registries: `vibeos skills install official/research/ru-public-sources`.

Workspaces & CLI

`vibeos research run|list|show` scaffolds dated workspaces under ~/.vibeos/research/ (prompt + sources template — no LLM call). Modes: brief, deep, academic, compare, quant…

Apps & literature MCP

Catalog: Notion, GitHub, Obsidian, Linear, Tavily map/crawl, Google Workspace / Gmail / Drive, Perplexity, scholar-search. Install with `vibeos mcp install <name>`. Cron briefings: https://vibeos.com.ru/handbook/guides/research-daily-briefing/.

How capability grows

Skills

Procedural docs + scripts the model loads on demand. Zero permanent tool-schema cost.

MCP servers

Catalog MCP servers (Linear, Notion, GitHub, Google Workspace, Perplexity, scholar-search, Obsidian, n8n, …) — install with `vibeos mcp` without shipping SaaS SDKs in core.

Plugins

Model providers

OpenRouter, Anthropic, OpenAI-compatible endpoints, and more — BYOK on hosted plans.

Hooks

Run custom code at lifecycle points — observe, rewrite, or block — without crashing the agent if a hook fails.

Control surface

Enable or disable toolsets per platform with `vibeos tools` or config.yaml. Security approvals, checkpoints/rollback, and credential pools stay under your control.