erthorpabar/pabar_agent_runtime

agent runtime

What it solves

It provides a framework for building an AI agent runtime that evolves from simple chat to complex autonomous execution. It aims to solve the problem of integrating chat, private knowledge bases (RAG), and agentic loops for both desktop and mobile applications.

How it works

The project follows an evolutionary path: starting with a basic chat interface, expanding into streaming voice interaction (Character), integrating private knowledge bases (RAG), and implementing an agent loop for task execution. These components are integrated into a desktop application (using Wails) for Windows and macOS, with plans for mobile support on Android and iOS.

Who it’s for

Developers and users looking to build AI agents capable of professional tasks such as browser automation, computer operation automation (e.g., video editing management), code architecture analysis, knowledge structure mapping, and project metric monitoring (e.g., quantitative trading).

Highlights

  • Integrated chat, RAG, and agent loops.
  • Cross-platform support for Windows, macOS, Android, and iOS.
  • Support for streaming voice interaction.
  • Targeted at professional automation tasks like browser and OS operation.

Related

  • Project
    langflow-ai/openrag

    An intelligent agent-powered document search platform that enables users to upload, process, and query documents through a chat interface using RAG.

  • Project
    Shy2593666979/AgentChat

    AgentChat is an open‑source, full‑stack conversational AI platform. It combines a Vue 3 front‑end with a FastAPI + LangChain back‑end to deliver LLM‑driven chat, multi‑agent collaboration, three‑tier memory (short‑term, summarised history, long‑term user prefs), RAG via vector stores, tool calling (including custom OpenAPI tools), and Model‑Context‑Protocol integration. Docker‑compose provides one‑click deployment; the project is MIT‑licensed.

  • 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.

  • Project
    Shubhamsaboo/awesome-llm-apps

    A collection of 100+ open-source AI agent and RAG application templates, providing ready-to-deploy examples for single agents, multi-agent teams, and voice AI.

  • Project
    uvwt/agentdock

    AgentDock is an open‑source runtime that lets LLM chat agents (e.g., ChatGPT) safely perform file operations, run commands, use Git, automate browsers, and coordinate work across multiple computers or containers via a secure HTTP‑based MCP endpoint. It provides fine‑grained permission controls, task persistence, and extensible Skills, but does not include its own chat UI or model inference.