Personal Assistants With an API
As of June 2026, AIDiveForge tracks 4 personal assistants with an api. Curated personal assistants with an api tracked by AIDiveForge. Listings are verified against each tool's live website and re-checked regularly.
Last updated June 2, 2026 · 4 tools
1. Alma by Olivares.AI
Alma, built by Olivares.AI, addresses that amnesia by pairing an AI assistant with persistent episodic memory that carries learned patterns, project context, and style preferences across sessions. The core workflow bundles text, image, video, and music generation under a single budget, so multi-modal creative projects don't require juggling five separate tool subscriptions. Background agents handle scheduled tasks — monitoring, reports, research — without you staying at the keyboard. The integration story extends to developer tools like Cursor, VSCode, and any MCP-compatible client, letting teams share a memory layer across their existing stack. Where it gets harder: teams needing on-premise data control find no self-hosted path, and the free tier gates most memory and agent features behind paid access.
PaidFree Trial · 14 days
2. Notis
The vendor describes Notis as a multi-agent system that receives messages — voice, image, or text — and autonomously handles the downstream work: structuring meeting notes, updating a personal CRM, drafting social posts, logging expenses from receipt photos, and scheduling recurring follow-ups. The core pitch is zero-app-switch capture that lands formatted in Notion, not in a raw notes dump. Where the system earns its keep is on recurring workflows — triggers and reminders that run without you initiating them. The ceiling shows up when your Notion architecture gets opinionated: if your databases use custom schemas or deeply nested relations, the agent's write logic may not match your structure, and you end up correcting outputs rather than just reviewing them. No self-hosted option exists, so your data and automations live on Mind the Flo's infrastructure.
PaidFree Trial · 7 days
3. 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
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.