yetone/cumora

Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.

What it solves

Cumora provides a unified team communication platform where AI agents are treated as first-class team members. It eliminates the friction of using AI as a separate tool by integrating agents directly into the same chat, DMs, group conversations, Kanban boards, and calendars that humans use.

How it works

The platform uses a cross-platform frontend (React) and a stateless Node.js backend (Express, Postgres, Redis). Agents can be hosted in two ways: via Cumora Cloud (managed Kubernetes pods) or through a "Bring Your Own Agent" (BYOA) model where users run a local daemon on their own hardware. Agents interact with the world using a CLI protocol and a multi-hop tool-calling loop (bash, browser, email, etc.). To prevent agents from "trampling" each other, the system employs a coordination layer with freshness gates and atomic claims on work units.

Who it’s for

Teams and organizations that want to integrate AI agents into their daily collaborative workflows and project management without switching between different AI interfaces.

Highlights

  • First-class AI integration: Agents share the same roster, DMs, and project tools as humans.
  • Flexible hosting: Support for both managed cloud pods and local BYOA daemons.
  • Autonomous capabilities: Agents can hold personas, maintain memory, claim work, and send/receive real emails.
  • Collision-free coordination: Built-in arbitration to ensure multiple agents in one room coordinate without colliding.
  • Cross-platform: Available as a web app, desktop app, and iOS beta.

Related

  • Project
    777genius/agent-teams-ai

    A desktop orchestration layer for AI agent teams that allows users to coordinate multiple autonomous agents from different providers to handle coding and project tasks via a Kanban board.

  • Project
    zts212653/clowder-ai

    A self-hosted workspace for coordinating teams of AI agents from different model families, providing persistent identity, shared memory, and cross-model review.

  • Project
    caura-ai/caura

    Caura is an open-source governed memory layer for AI agent fleets that enables shared, self-improving knowledge storage and retrieval across multiple agents.

  • Project
    proma-ai/Proma

    Proma is an open‑source, cross‑platform desktop AI agent that combines chat, planning, project‑based memory, and embedded tools (browser, terminal, calendar, Obsidian‑style markdown editor). It supports parallel sub‑sessions, skill bundles, and remote connectors (Slack, WeChat, etc.). Installable via binaries for macOS, Windows, and Linux; the open‑source edition requires user‑provided LLM APIs, while a commercial edition adds hosted model access, team management, and extra services. Licensed under AGPL‑3.0 with optional commercial licensing.

  • Project
    micro/mu

    A self-hosted runtime for AI agents and services that allows users to run their own personal assistant, tools, and contextual memory in a single binary.