모형 Context 의정서 (MCP)를 가진 빠르 시약에 건설된 각자 최후 AI 조수. 계획, 연구, 디자인, 코드, 테스트 및 함께 배포 할 수있는 멀티 시약 팀.

Status: 활성 개발. 공개 릴리스 선율은 v1.0.0]에서 시작합니다. 핵심 건축은 AGENTS.md에 문서화되고 [T2]].

무엇 그것

• Multi-agent spawn: 7-role agile 팀 (PM, BA, SA, Dev, Designer, QE, DSO)는 간 시약 이메일 및 회의 프로토콜을 준수합니다.
• MCP-first tools: filesystem, GitHub, Atlassian, Figma, 웹스크랩링(스크램핑), Roborock vacuum, Google Calendar / Gmail, story crawler, TTS - MCP 서버로 모든 노출. -Hands-free voice: 실시간 STT (faster-whisper, VAD, 선택적 깨어있는 단어) + 스트리밍 TTS (Edge default; ElevenLabs / OpenAI / Azure / System opt-in) 와 WebSocket. 스토리는 무료 가장자리로 고정되어 있으므로 유료 엔진은 긴 형식의 할당량을 태우지 않습니다.
• **웹 대시보드 **: Vue + Vite UI for chatting with Jarvis, 구성 제공 업체, 음성 엔진, 보고 에이전트 타임라인, 관리 비밀.
• Self-host friendly: Single docker compose up -d은 Linux 박스에 전체 스택을 가져옵니다.

행동에서 본다

Jarvis

Self-hostable AI assistant built on fast-agent with the Model Context Protocol (MCP). Spawns a multi-agent team that can plan, research, design, code, test, and deploy together.

Status: active development. Public release lineage starts at v1.0.0. Core architecture is documented in AGENTS.md and docs/SELF_HOSTING.md.

What it does

• Multi-agent spawn: a 7-role agile team (PM, BA, SA, Dev, Designer, QE, DSO) coordinates over inter-agent email and meeting protocols.
• MCP-first tools: filesystem, GitHub, Atlassian, Figma, web scraping (Scrapling), Roborock vacuum, Google Calendar / Gmail, story crawler, TTS — all exposed as MCP servers.
• Hands-free voice: real-time STT (faster-whisper, VAD, optional wake word) + streaming TTS (Edge default; ElevenLabs / OpenAI / Azure / System opt-in) over WebSocket, with barge-in. Stories are locked to free Edge so paid engines never burn long-form quota.
• Web dashboard: Vue + Vite UI for chatting with Jarvis, configuring providers, voice engines, viewing agent timelines, managing secrets.
• Self-host friendly: single docker compose up -d brings up the whole stack on a Linux box.

See it in action

Not one chatbot — a whole team. Jarvis orchestrates a roster of specialist agents (research, finance, IoT, music, and more) — each one inspectable and directly reachable.

It remembers you — across conversations. Tell Jarvis a fact once; it saves to durable memory (not just chat history) and recalls it later in a brand-new conversation — no scrolling back, no re-explaining.

1. Teach it a fact:

2. Ask in a brand-new conversation — it recalls:

Chat with any specialist directly — not just the orchestrator. Switch straight to a subagent (here, the IoT agent) and ask your robot vacuum for its live status — real IoT (Roborock), not a mockup.

And it extends itself — live. No tool for the job? Jarvis scaffolds, installs, and wires in a brand-new MCP tool, then uses it in the same conversation — no package to hunt down, no redeploy.