zeenie-ai/OpenCompany

Self-improving AI Employees turning LLM tokens into work and dollars.

What it solves

OpenCompany provides a self-hosted, no-code canvas for building and deploying AI agent workflows. It eliminates the need for expensive subscriptions and usage limits by allowing users to run agents on their own hardware using local models (via Ollama or LM Studio) or their own API keys, while integrating these agents with a vast array of third-party services like email, calendars, and messaging apps.

How it works

Users drag and drop nodes from a palette onto a visual canvas to create workflows. These nodes can be AI agents, triggers (like webhooks or schedules), or service integrations.

Key technical components include:

  • Durable Execution: Uses Temporal to ensure workflows retry failures and handle long-running tasks reliably.
  • Memory & Context: A Context node allows conversations to persist across triggers, while a Memory tool provides long-term recall via vector search.
  • Agent Orchestration: "AI Employee" or Orchestrator nodes can lead teams of specialist agents, assigning and monitoring tasks through a built-in Task Manager.
  • Local-First: Supports local LLM providers (Ollama, LM Studio) and encrypts credentials at rest using AES-128-CBC.

Who it’s for

  • Non-developers who want to build complex AI automations without writing code.
  • Self-hosters seeking privacy and control over their AI workforce and data.
  • Developers who want a modular framework to quickly extend AI capabilities via a Python-based plugin system.

Highlights

  • Extensive Integrations: 146 nodes across 31 categories, including Google Workspace, Microsoft 365, WhatsApp, Telegram, Discord, and Stripe.
  • Hardware Control: Ability to control Android phones via QR code pairing.
  • Web Automation: Integrated browser navigation, scraping (via Crawlee/Apify), and search tools.
  • Diverse Model Support: Integration with 13 providers including OpenAI, Anthropic, Google, xAI, and local options.
  • Smarter Context Management: Automatically compacts long conversations into summaries when context limits are approached to maintain efficiency.

Related

  • Project
    Team-Commonly/commonly

    An open-source workspace for collaborating with AI agents from any runtime, providing them with persistent identity and shared project memory to eliminate redundant context-setting.

  • Project
    Agenta-AI/agenta

    An open-source workspace for building and running AI agents that can automate work through interactive chat or scheduled background tasks.

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents can share threads, files, and a browser to work together.

  • Project
    mudler/LocalAGI

    A self-hostable, no-code AI agent platform that allows users to create private, local AI automations and agents on their own hardware.

  • Project
    the-open-agent/openagent

    An open-source personal AI assistant platform that combines LLMs, RAG, and autonomous agent loops into a single, self-hostable binary.