Explore tools for running models or agent components on your own hardware. Separate local inference from other network-dependent steps, including search, external tools and optional telemetry.
Atomic Agent is a local-first terminal coding assistant that runs open-weight models through llama.cpp and keeps its control loop and state on the user’s machine. It can browse, work with files and Git, retain memory across sessions, and connect external tools over MCP.
CorvinOS is a self-hosted agentic OS that connects local and cloud models to messaging platforms including Discord, Telegram, WhatsApp, Slack, and email.
Jan is an open-source, development-stage ChatGPT alternative that operates fully offline on diverse hardware platforms, supporting universal architectures from PCs to multi-GPU clusters
LocalGPT is an open-source project for secure, private interactions with documents locally, featuring comprehensive model support, embeddings, API for RAG applications, and GUI options, with a focus on privacy and local data processing
A local-first terminal coding agent that connects to user-selected models and supports tool calling, MCP, and custom commands.
Ollama is a tool for running large language models locally, offering easy setup for macOS, Windows, Linux, and Docker, along with a library of models and quickstart guides for customization and integration
POK-Agent is a Windows computer-use and coding agent that combines a planner with a fast screen-action model, verifies step outcomes, and can record and replay successful task sequences.
PrivateGPT is a secure, offline-capable AI tool for querying documents with Large Language Models, offering high-level and low-level APIs for privacy-conscious, context-aware application development
Screenpipe captures screen and audio locally, then exposes searchable work history and agent context through an MCP server. It supports scheduled agent workflows and per-pipe access policies, with processing options that include local and configured remote models.
A self-hosted server for personal AI agents with persistent private memory, shared wiki, delegated agents, scheduled work, and web, shell, and browser tools across terminal, browser, and mobile clients.
Build a practical cost worksheet for self-hosted agents that includes models, tools, retries, idle infrastructure and human review.
Read the guide