RetainDB
Memory layer for AI agents that stores user preferences, history and corrections and connects Slack, GitHub, docs and tickets into an askable knowledge layer
The product is a memory layer for AI agents that stores user preferences, history, corrections, and decisions so agents do not reset each session and can answer from connected tools like Slack, GitHub, and docs. It is for developers and product and data teams building B2B AI products such as customer support agents, coding assistants, research agents, and company copilots. It is delivered as a SaaS infrastructure API with SDK, MCP integrations, and a filesystem interface, starting with durable per-user memory and expanding into a shared company knowledge layer.
Key features
- Durable user and agent memory
- Company brain from Slack and GitHub
- Connect docs, tickets and files
- Agent filesystem as browsable paths
- MCP for Claude, Cursor, Codex
- Context injection from memory
- Local tools and code context
- npx wizard setup
- No social media activity within the last 30 days
GTM channels
- Blog
- Marketplace
- API
- Docs
ICP
- Software developers
- Engineering teams
- Product teams