Busabase is an open-source database and workspace designed for AI agents and human teams, storing agent outputs as structured data, documentation, skills, and internal applications across local and cloud environments.
What the product does and how it is positioned
Busabase serves as a centralized database and collaboration workspace for AI agents and human team members. Instead of leaving agent outputs scattered across individual chat sessions, the platform organizes agent-generated results into structured data tables, documentation, operational skills, and lightweight internal applications.
The platform supports local-first desktop usage, Docker-based self-hosting within internal corporate networks, and managed cloud deployments. External agents connect through standard interfaces such as the Model Context Protocol, OpenAPI, command-line tooling, or dedicated agent skills to read and update shared data.
Source-supported ways to use the product
Agents reference product facts and question databases to draft replies, which human operators review and approve before delivery.
Teams track briefs, marketing contacts, social post schedules, and assets across shared pipelines updated directly by connected agents.
Meeting summaries, decisions, and contextual background are captured in documentation tables so subsequent agent sessions do not reset to zero.
Teams maintain supplier records, product specifications, stock data, and project statuses in shared relational tables accessed by agents.
The documented workflow, where available
Integrate coding assistants, automation systems, or custom agents using Model Context Protocol, Agent Skills, OpenAPI, or the command-line interface.
Changes made by agents log the contributor identity and revision history, with the option to hold specific updates for human approval.
Subsequent agents, team members, or internal applications query the persisted tables, docs, and skills without restarting workflows from scratch.
Busabase structures agent activity into specialized functional modules including Data Base, Knowledge Base, Apps Base, Skills Base, and Playbooks. Data Base establishes tables with consistent field schemas, supporting multiple autonomous agents and human editors read and write identical data definitions without schema drift.
Integration with external AI tooling occurs through open standards including Model Context Protocol, OpenAPI, command-line interfaces, and specialized agent plugins. Changes committed through these endpoints record origin metadata and maintain historical audit trails, enabling oversight across automated operations.
Checks to run with your own material and workflow
What was checked and when
Answers based on the source-checked product record
Busabase is open-source software provided under the MIT license, allowing teams to inspect code and run it in self-managed environments.
Busabase can be used as a desktop application on a personal computer, self-hosted on company servers using Docker, or accessed via Busabase Cloud.
The platform works with agents such as Claude Code, Codex, Cursor, Hermes, OpenClaw, WorkBuddy, and custom agents via MCP, OpenAPI, CLI, or Agent Skills.
Each write operation records who made the change along with a full edit history, and sensitive actions can be queued for human review before execution.
Busabase Desktop stores data locally in a directory on the user computer, operates without usage tracking, and continues to function without an internet connection.
