Devin-AXIS/iPolloWork

Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.

What it solves

iPolloWork provides a unified, enterprise-grade workbench for managing multiple AI agent engines and their outputs. It solves the problem of fragmented workflows where users must switch between different agent runtimes (like Codex or DeepSeek Harness) and deal with static outputs (like chat transcripts) that cannot be easily edited.

How it works

It acts as a workspace layer that connects various agent runtimes through a shared engine boundary. It uses a local-first approach where users can run the system locally and bring their own models. The workbench integrates different engines—such as OpenCode (default), DeepSeek Harness, and Codex (via MCP)—into a single control surface. This allows teams to coordinate tasks, schedules, and plugins across different agents while keeping the generated results (code, documents, presentations, websites, design, and video) editable within the same environment.

Who it’s for

It is designed for people and agent teams who need a professional environment to collaborate on multi-agent projects, moving beyond simple chat interfaces to a full production loop involving various media types.

Highlights

  • Multi-Engine Support: Use multiple agent runtimes (Codex, DeepSeek Harness, OpenCode) in one workspace without rebuilding the project experience.
  • Global Extension System: A single system for installing and managing portable plugins, Skills, and commands across different engines.
  • Editable Production Loop: Generated outputs like presentations, websites, and videos remain editable instead of becoming finished files.
  • Human-Agent Collaboration: Shared project views for tracking responsibilities, tasks, and execution health.
  • Local-First Control: Supports local execution and "bring your own model" with optional cloud connectivity for organization services.

Related

  • Project
    jsgrrchg/NeverWrite

    A local-first agentic markdown workspace that integrates knowledge management, AI agent sessions, and a deliberate review system for AI-generated edits.

  • Project
    Devin-AXIS/deepseek-design

    A native visual design system for DeepSeek Harness that allows AI to generate and manually refine editable websites, presentations, and videos.

  • Project
    Pinvou/pinvou-agent

    Pinvou Agent is a cross‑platform desktop AI‑assistant that lets you work, design, or code with LLMs. It combines chat with file attachments, a local knowledge base, persona cards, and a plug‑in tool store, producing editable artifacts (Markdown, designs, code) that persist across sessions. Built with React + Vite UI on Tauri 2, it uses the CodeWhale engine for model calls, MCP tool execution and Skills. Supports local vLLM or any OpenAI‑compatible endpoint, runs on Windows/macOS/Linux, and is MIT‑licensed.

  • Project
    nexu-io/open-design

    An open-source, local-first design platform that enables coding agents to generate and render web prototypes, decks, and motion graphics based on a brand's design system.

  • Project
    0xsline/OpenChatCut

    An open-source, local-first AI video editor that combines a professional multitrack timeline with conversational agents for editable, agent-driven video production.