Hybrid cloud-local AI Employee that runs 24/7 on a cloud VM, monitors Gmail/WhatsApp, drafts responses, and queues approvals via git-synced Obsidian vault. Human-in-the-loop safety gates for email, so
Why this rank:Release freshnessStrong adoptionHealthy release cadence
Description
Hybrid cloud-local AI Employee that runs 24/7 on a cloud VM, monitors Gmail/WhatsApp, drafts responses, and queues approvals via git-synced Obsidian vault. Human-in-the-loop safety gates for email, social media, and Odoo ERP. Platinum tier.
README
Personal AI Employee
Hackathon Tier: Platinum | All 7 Capabilities Live
A hybrid cloud-local autonomous AI agent that monitors multiple sources (filesystem, Gmail, WhatsApp), processes tasks through a git-synced Obsidian vault pipeline, and executes actions via MCP servers with human-in-the-loop safety gates. The cloud VM (Ubuntu 24.04) works 24/7 even when your laptop is off â detecting events, drafting responses, and queueing approval requests. When you come back online, review and approve with a single file move. Built for the 2026 Personal AI Employee Hackathon.
# 1. Initialize vault
python src/setup_vault.py
# 2. Start file watcher
python src/file_drop_watcher.py
# 3. Drop a file and process
cp document.pdf ~/Desktop/DropForAI/
claude "check and process needs action"# 4. Start Gmail watcher (requires credentials.json)
python .claude/skills/gmail-watcher/scripts/gmail_poll.py
# 5. Start scheduler daemon
python .claude/skills/daily-scheduler/scripts/scheduler_daemon.py
# 6. Run central orchestrator
python .claude/skills/central-orchestrator/scripts/orchestrator.py
# 7. Generate CEO briefing
claude "generate CEO briefing"
MCP Servers
Registered in .claude/settings.json. All default to DRY_RUN=true.
aiA productive AI coworker that learns, self-improves, and ships work.main@2026-10-23
rex-cliLocal-first AI agent bootstrap: Playwright Browser MCP + ContextDB for Codex CLI, Claude Code, Gemini CLI, and OpenCode.v6.11.0
More in MCP Servers
litellmPython SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropi
ruflođ The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade archit
@claude-flow/cliRuflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
claude-plugins-officialOfficial, Anthropic-managed directory of high quality Claude Code Plugins.