AgentVault — own your personal agent

A self-hosted AI assistant where memories, data, and permissions stay on your device

Problem

People running local agents complain about two things: you have to approve nearly every action, making overnight automation impractical, and it's unclear whether long-term memories and personal data stay local or go to a platform that can cut you off. Someone built their own self-deployable personal agent specifically to address this.

Solution

A self-hosted personal agent runtime that separates memory from permissions. Memory lives in local SQLite and can be browsed, edited, and exported by the user. Permissions use configurable policies instead of per-action approvals, e.g. read-only folders, whitelisted commands that auto-run, and confirmation only for sensitive actions.

Users

Privacy-conscious developers, long-term AI assistant users, and anyone who wants an agent on their own hardware without constant approval prompts

MVP

Local SQLite memory that can be browsed, edited, and exported; policy-based permissions (command allowlist, read-only dirs, confirmation required actions); support for any OpenAI-compatible model; unified chat and tool execution panel; one-click Docker deployment

Revenue

Open-source core with paid hosted version, or one-time desktop bundle; enterprise per-seat pricing for audit logs and team policies

Why now

Local agents are booming but permission UX and memory ownership remain unsolved; model APIs are standardizing, letting indies focus on the safety and experience layer