Open Source AI Assistants Apps

The self-hosted job search assistant that tracks applications, reviews resumes with AI, and auto-discovers matching roles from Greenhouse, Lever, and Ashby boards — all while keeping your data on your own server.

Self-hosted AI transcription with speaker diarization, smart tagging, and multi-user collaboration — your recordings stay on your infrastructure.

Local-first AI dictation that understands your active app — private, offline, and built for speed.

An open-source, multiplayer agent harness that gives every employee and every room in a company its own scoped memory, sandbox, and AI agent — in Slack and on the web.

An open-source platform for persistent AI teammates that own their own conversations, memory, routines, and computers — self-hosted, model-agnostic, and available on web, desktop, and mobile.

A self-hostable AI second brain that chats with your documents, searches the web, builds custom agents, and runs entirely on your own LLM.

The open-source AI workspace that puts your data, your rules — with local LLMs, CRDT collaboration, and full self-hosting built in.

A 100% private, on-device macOS dictation and meeting-transcription app — hold Control to talk, transcribes and pastes locally via Apple Silicon with no cloud APIs or data leaving your Mac.

Rasa Open Source is a Python machine learning framework for building contextual, multi-turn chatbots and voice assistants that understand natural language and maintain conversation state.

Bloomberg-grade financial data and AI-powered analysis through a conversational chat interface you can self-host.

Open-source Chrome extension for AI-powered web automation — run multi-agent browser workflows locally using your own LLM API keys, free from cloud subscriptions.

A fully local web research assistant that iteratively searches, summarizes, and refines markdown reports using any Ollama or LMStudio model—no cloud or API keys required.

An open-source, on-device Mac desktop pet that types what you say, takes meeting notes with speaker labels, and talks back — a private alternative to Wispr Flow and Granola.

Run large language models privately on your laptop — no GPU, no cloud, no data leaving your device.

Self-hosted enterprise AI knowledge hub that compiles internal docs into a scoped, reviewable wiki and serves it to Claude and other LLMs through an MCP server.