HolaOS

Active
GitHub TypeScript NOASSERTION

Description

HolaOS is a local-first super agent for work that learns your context in minutes, never forgets it, and integrates 100+ tools to take over daily tasks.

Key Features

  • Local-first - data and runtime stay on-device with privacy and offline in mind
  • 100+ integrations with auto-fetch - one-click OAuth to Linear, GitHub, Slack, Jira, Gmail, and more
  • Permanent memory - learns and remembers your working context across sessions
  • Proactive agent - a unified agent manager coordinates sub-agents to act autonomously
  • Desktop runtime - Electron-based customizable workspace and dashboard
  • MCP-native - extends capabilities via standard tools and data sources

Use Cases

💡 Act as a personal work assistant that triages email, tasks, and calendar
💡 Auto-sync context and follow up across many workplace tools
💡 Run workflows with sensitive business data locally
💡 Build a long-term collaborative agent that remembers your preferences

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (11.2k stars)
  • Responsive to issues, low backlog

⚠️ Limitations

  • No clear open-source license

Quick Start

# Clone and launch the desktop app (requires Node.js)
git clone https://github.com/holaboss-ai/holaOS && cd holaOS
npm install && npm run dev
# Or download the macOS desktop app from https://holaos.ai

Related Projects

Engram

6.4k · Go
Active A

Engram is a persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI interfaces.

memorysqlitemcp +1
  • · Persistent memory system for AI coding agents with SQLite + FTS5 full-text search
  • · Agent-agnostic: works with Claude Code, OpenCode, Gemini CLI, Codex, VS Code, Cursor, and any MCP-compatible agent
  • · Single Go binary with zero dependencies — no Node.js, Python, or Docker required

memU

14.4k · Python
Active A

A memory system for 24/7 proactive agents with MCP protocol integration, providing long-term memory management, skill storage, and proactive reasoning capabilities for continuously running AI agents.

memoryagentmcp +2
  • · 24/7 proactive memory agent that continuously captures and understands user intent
  • · File-system-like memory structure with folders, files, symlinks, and mount points for organized knowledge
  • · Significantly reduces LLM token cost with smaller context windows (~1/10 of comparable usage)

Bitterbot

2.5k · TypeScript
Active A

A local-first personal AI with biological-style memory and a Dream Engine that consolidates skills while you sleep, plus a P2P skills marketplace settling in USDC.

personal-agentmemoryp2p +2
  • · Biological-style memory — memory persists and grows across devices instead of dying with the session
  • · Dream Engine — tidies and consolidates memory while idle, distilling provenly useful behavior into reusable skills
  • · Self-graded — dreaming is scored by whether its outputs actually get used