proma-ai/Proma

Proma brings a seamless general-purpose Agent experience to your workflow. Built for 100× professionals and the proactive Agent era

What it solves

Proma is a general-purpose desktop Agent application designed for professional users who need a more transparent and configurable environment for AI agents. It addresses the problem of poor context management in standard AI interfaces by providing structured project-based organization, integrated tools, and advanced session management to ensure agents have the exact context they need to perform complex tasks.

How it works

Proma organizes the user experience into three main areas: a session management area (left), a primary agent interaction area (center), and a support area (right) containing files, browsers, and tools. It manages context through a project-level AGENTS.md file for global constraints and a MEMORY.md index for specific memories, ensuring the agent's behavior is tailored to the specific project.

Who it’s for

Professional users, developers, and researchers who rely heavily on AI agents for knowledge management, coding, and automation, and who require deep integration with their local files, calendars, and knowledge bases (like Obsidian).

Highlights

  • Advanced Sessioning: Supports "Sub-sessions" for parallel deep research and "Exploration Mode" to create branches of a conversation that can be later merged back into the main thread.
  • Integrated Tooling: Features an embedded browser and terminal that the agent can actively use for automation and web research.
  • Professional Workflow Integration: Deeply integrates with Obsidian for markdown editing, macOS Reminders/Calendar for task and schedule management, and Git worktrees for developers.
  • Extensibility: Supports Skills, MCP (Model Context Protocol), and CLI tools, allowing users to create custom agent capabilities based on real-world workflows.
  • Project-Based Memory: Uses a structured file-based memory system to maintain project-specific constraints and long-term knowledge.

Related

  • Project
    shibing624/agentica

    Agentica is an open‑source, Apache‑2.0‑licensed framework that lets you run LLM‑powered agents locally via a CLI, web UI, or desktop app. It supports many models, async multi‑tool execution, loss‑less context compression, automatic skill generation, and multi‑agent collaboration, with Python and TypeScript SDKs for embedding.

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.

  • Project
    EXXETA/exxperts

    A local-first AI agent framework that uses approval-gated memory to create persistent AI colleagues that learn and remember only what the user explicitly approves.

  • Project
    vastsa/PI-Desktop

    PI‑Desktop is a cross‑platform, local‑first desktop application that provides a persistent, plugin‑extensible workspace for AI agents. It lets you connect any LLM (cloud or local), orchestrate multiple agents or sub‑agents, and build custom functionality via plugins (panels, commands, widgets, services, etc.). All data stays on your machine, and the system is built on the open‑source pi agent ecosystem.

  • Project
    netease-youdao/LobsterAI

    A desktop AI agent that operates within your local environment, automating tasks across files, terminals, browsers, and office software.