mudler/LocalAGI

LocalAGI is a powerful, self-hostable AI Agent platform designed for maximum privacy and flexibility. A complete drop-in replacement for OpenAI's Responses APIs with advanced agentic capabilities. No clouds. Local AI that works on consumer-grade hardware (CPU and GPU).

What it solves

LocalAGI provides a self-hostable platform for creating and managing AI agents and automations that run 100% locally. It eliminates the need for cloud service keys and agentic Python libraries, ensuring data privacy by keeping all processing on the user's own hardware (CPU or GPU).

How it works

LocalAGI is a no-code platform that allows users to design agents via a web-based interface. It integrates with LocalAI for model inferencing and LocalRecall for knowledge base management (RAG). Agents can be configured with "Skills" (reusable tools) and custom actions written in Go that are interpreted at runtime without needing compilation. It also supports agent teaming, where multiple agents can cooperate based on a single prompt, and provides connectors for platforms like Discord, Slack, Telegram, and GitHub.

Who it’s for

It is designed for users who want to deploy private, local AI agents on consumer-grade hardware, as well as developers who want to integrate agentic capabilities into their workflows via a REST API or by using LocalAGI as a Go library.

Highlights

  • No-Code Agent Creation: Configure multiple agents and cooperative teams through a Web UI.
  • Coded Extensibility: Write custom agent behaviors in interpreted Go code.
  • Built-in RAG: Integrated knowledge base for file uploads and semantic search.
  • Broad Hardware Support: Optimized Docker setups for CPU, NVIDIA, Intel, and AMD GPUs.
  • Multi-Platform Connectors: Native integrations for Telegram, Discord, Slack, IRC, and GitHub Issues.
  • OpenAI Compatible: Every agent exposes a drop-in replacement for OpenAI's Responses APIs.

Related

  • Project
    zeenie-ai/OpenCompany

    A self-hosted, no-code canvas for building AI agent workflows that integrates with local or cloud LLMs and over 30 external services.

  • Project
    zeroclaw-labs/zeroclaw

    A self-hosted agent runtime written in Rust that lets you run a private AI assistant with local control over data, providers, and hardware interaction.

  • Project
    amplifthq/opentag

    A self-hosted framework that turns an AI coding agent into a persistent Slack teammate that executes tasks on a user-controlled local machine.

  • Project
    BidingCC/BuildingAI

    BuildingAI is an enterprise-grade, no-code platform for creating intelligent AI agents and applications, featuring built-in RAG pipelines, model aggregation, and business billing systems.

  • Project
    open-webui/open-webui

    A self-hosted, extensible AI platform that provides a unified interface for local and cloud-based models, featuring built-in RAG, agent creation, and enterprise-grade user management.