Self-Hosted Personal Assistants
As of June 2026, AIDiveForge tracks 4 self-hosted personal assistants. Curated self-hosted personal assistants tracked by AIDiveForge. Listings are verified against each tool's live website and re-checked regularly.
Last updated June 9, 2026 · 4 tools
1. Aitne
Aitne is a local-first, open-source personal agent that runs on your machine, wakes at 04:00, pulls from your calendar, email, GitHub, and Markdown notes, and drops a one-page briefing into your Slack, Telegram, Discord, or WhatsApp DMs before your day starts. Hourly nudges surface urgent emails and pending PR reviews throughout the day. By evening it journals what actually happened, building a Markdown knowledge base you own entirely. The agent runs via npm with no cloud dependency — your data never leaves your machine. The ceiling appears fast: this is a single-user, single-machine system, and anything requiring team-wide coordination or multi-account enterprise integrations lives outside its scope.
FreeOpen Source
2. Owlfy AI
The scraped page content provided belongs to a different product entirely — a travel identification app called Spotter — and does not describe the tool listed in the input data. No production details, workflow specifics, or feature claims for the named tool can be sourced from this page. The tool data and validator context describe a voice-driven AI agent with local processing, batch document handling, email and calendar automation, and CLI execution capability, but none of these claims can be verified against the provided page content. Publishing listing copy based on unverified assertions would misrepresent the tool to engineers vetting it for production use.
PaidFree Trial · 20 days
3. Swipeer AI
Swipeer is a desktop AI client that gives you keyboard-driven access to multiple language models, browser automation, file analysis, and OS-level task control from one interface. The agentic layer — browser control, form filling, and tool execution in a loop — means it can run multi-step research tasks without you shepherding each step. File analysis covers PDFs, CSVs, images, and code, so analysts who need quick data-to-summary pipelines get that without leaving the desktop. The free tier runs on daily credits, which caps how much autonomous work you can run before hitting a ceiling. Teams doing continuous, high-volume automation will exhaust free credits fast and need to evaluate whether a paid tier fits the workload.
Paid
4. TinyHumans
OpenHuman runs as a desktop app, keeping memory and agent execution on your machine rather than a vendor's cloud — which means your work context, preferences, and knowledge base don't get packaged and sent upstream. NeoCortex handles the memory layer as an API, targeting teams who want deterministic recall baked into production applications. The agent layer is genuinely agentic: the vendor page describes joining meetings, executing code, controlling browsers, and running scheduled tasks autonomously. Where this architecture shows its limits is the managed backend services — even OpenHuman requires account sign-in and model routing that connect to TinyHumans-operated infrastructure, so 'local-first' is partial, not absolute. Teams needing fully air-gapped deployments will hit that wall.
Paid
Listings on this page are sourced and verified by the AIDiveForge data pipeline. AIDiveForge is editorially independent — no money changes hands for inclusion.