What is pumaDB?
pumaDB is an AI developer tool that gives AI agents a shared, persistent memory layer without requiring any database, vector store, or RAG stack to set up. It solves the common problem of agents losing useful context between sessions, tools, and chats by offering one durable place to save and reuse notes, facts, preferences, project context, transcripts, and task state. Agents connect through two access methods: a hosted MCP (Model Context Protocol) server at api.pumadb.ai/mcp for agent clients like ChatGPT, Claude, and Codex, or a server-side REST API for application code. pumaDB stores multiple memory types — skills markdown, project conventions, user preferences, research clippings, task state, and typed safe memory — and adds safety controls including scoped table limits, rate limiting, and natural-language edit filtering. It keeps automatic version history with 30-day retention, and every update or delete archives the prior row so content can be restored. Documented account limits include 20 tables, 1,000 rows per table, and 25 MB of storage, with rate limits of 30 writes and 60 reads per minute per key, and OAuth authentication for the hosted MCP endpoint. As an AI developer tool for agent memory, it targets developers who want a persistent memory backend without managing infrastructure.
What is pumaDB used for?
Giving developers a persistent, shared memory backend for AI agents without setting up a database, vector store, or RAG stack
How much does pumaDB cost?
Documented account limits
20 tables, 1,000 rows per table, 25 MB storage
Pros and cons
Pros
- Persistent shared memory for AI agents with no database, vector store, or RAG stack to manage
- Dual access via hosted MCP endpoint (for ChatGPT, Claude, Codex) and a server-side REST API
- Stores multiple memory types: skills markdown, conventions, preferences, task state, and typed safe memory
- Automatic version history with 30-day retention; every update/delete archives the prior row for restore
- Built-in safety with scoped table limits, rate limiting, and natural-language edit filtering
Cons
- Account limits are modest (20 tables, 1,000 rows/table, 25 MB storage) which may constrain larger projects
- Rate limits of 30 writes and 60 reads per minute per key can bottleneck high-throughput agents
- No pricing is published, so cost beyond documented limits is unclear
- Aimed at developers, so non-technical users get little value
Questions about pumaDB
What is pumaDB used for?
pumaDB gives AI agents a persistent shared memory layer so they can save and reuse notes, facts, preferences, project context, transcripts, and task state across sessions without setting up a database or vector store.
How do agents connect to pumaDB?
Agents connect through a hosted MCP server at api.pumadb.ai/mcp for clients like ChatGPT, Claude, and Codex, or through a server-side REST API for application code, using OAuth for the hosted MCP endpoint.
Does pumaDB require a vector database or RAG stack?
No. pumaDB provides agent memory without a database, vector DB, or custom RAG infrastructure to set up or manage — that is its core value proposition.
Can you recover deleted data in pumaDB?
Yes. Every update and delete archives the prior row content, and pumaDB keeps automatic version history with 30-day retention, so earlier states can be restored.
Reviews
Sign in to rate and review pumaDB.
Sign in to reviewNo reviews yet. Be the first to review pumaDB!
