Taskosaur/Taskosaur

Open Source Project Management with Conversational AI Task Execution. Built for teams who want conversational workflow management alongside traditional PM features. Self-hostable with modular architecture.

What it solves

Taskosaur is an open-source project management platform that eliminates the need to manually navigate menus and forms. It allows users to manage projects, create tasks, and handle workflows using natural language conversations with an integrated AI assistant.

How it works

The platform combines traditional project management tools (like Kanban boards and sprints) with a conversational AI layer. Users can connect their own LLM via API keys (OpenAI, Anthropic, OpenRouter, or local models). The AI doesn't just suggest actions but performs them directly through in-app browser automation, navigating the interface and executing multi-step operations based on the user's natural language commands.

Who it’s for

It is designed for teams and individuals who want a self-hosted project management tool that supports AI-driven task execution and integrates with existing tools like Jira and Trello.

Highlights

  • Conversational Task Execution: Perform bulk operations and complex workflows via chat instead of manual clicks.
  • Browser Automation: AI can navigate the application interface and fill forms in real-time.
  • BYO LLM: Supports multiple providers including local models for data privacy.
  • External Integrations: Bidirectional sync capabilities for Jira and Trello at both workspace and project levels.
  • Self-Hosted: Full control over data and infrastructure.

Related

  • Project
    desplega-ai/agent-swarm

    agent‑swarm is an open‑source platform that turns a lead AI agent into a task‑routing hub, delegating work to containerised worker agents (Claude Code, Codex, etc.). It integrates with Slack, GitHub, email, and many other tools, persisting context via vector memory, and can automatically generate PRs, replies, or scheduled scripts. The system is model‑agnostic, runs via Docker (or Helm on Kubernetes), and is licensed under MIT.

  • Project
    keinsaasforever/better-chatbot

    An open-source AI chatbot platform that integrates multiple LLMs and the Model Context Protocol (MCP) to provide advanced automation, visual workflows, and custom agents.

  • Project
    OpenWhispr/openwhispr

    OpenWhispr is a cross‑platform desktop app for privacy‑first voice dictation, meeting transcription, and AI‑assistant interaction. It supports offline speech‑to‑text with Whisper‑based models or cloud services, offers speaker diarisation, note‑taking with semantic search, team collaboration, and a public API for developers.

  • Project
    openchamber/openchamber

    OpenChamber is an open‑source, cross‑platform workspace that lets developers start AI coding agents (via OpenCode), monitor their progress, compare multiple model runs, review changes with guided walkthroughs, preview the app being edited, and integrate directly with GitHub—all while syncing sessions across desktop, web/PWA, VS Code, and mobile devices.