RedDB Cloud · Source available

Stop running 7 databases. Run RedDB.

Postgres, Mongo, Redis, Pinecone, Neo4j, Influx, RabbitMQ — replaced by one engine that also answers natural-language questions across your data. For startups that can't afford a 5-person infra team.

Start free — no credit card Explore the database →

Or self-host with npm i @reddb/cli

7→1
databases consolidated
<1ms
cache-hit latency
fsync+WAL
durable on every commit
BSL 1.1
every line auditable

red://ask · connected

The stack problem

Your app should not need seven databases to answer one question.

Most startups end up paying five vendors and writing the glue between them. RedDB makes the data model a query capability instead of a separate product to deploy, sync, observe and recover.

See one query across every model →

fragmented stack

Postgresrows
Mongodocs
Neo4jgraphs
Pineconevectors
Rediskv + cache
Influxmetrics
RabbitMQqueues
→

RedDB

Collectionsone engine
ASKcross-model context
DriversRust · JS · Python

One engine. Everything on top.

The database is the start. AI runs on it.

Retrieval, embeddings and grounded answers already ship inside the engine. On top of it we are building the services your models and agents need — memory, storage, a model API and a place for agents to live.

Agents Agent Hosting Hermes AgentOpenClawPaperclip Planned
AI services RedDB ModelsAgent MemoryAI Storage Planned
Engine RedDB ASKembeddingsvector searchMCP tablesdocumentsgraphsvectorskvcachetime-seriesqueues Live

Live in the engine today

Ask your data. Get the receipts.

ASK pulls context from rows, documents, graph edges and vectors, then answers with citations tied to the records it used. Embeddings happen on write; similarity search is a query, not another service.

  • Embeddings on write. An EMBED policy on a collection embeds the declared fields asynchronously over CDC, so writes never wait on the provider.
  • Vector and hybrid search. SEARCH SIMILAR, hybrid text + vector search, and HNSW indexes that apply filters before ranking.
  • MCP for agents. Agents read and write durable state in RedDB through the Model Context Protocol, over stdio.
See AI in the engine →
red://ask Example output

red> ASK 'who owns passport AB1234567 and what do they use?' USING groq;

Answer

Alice Costa owns passport AB12345671 and uses billing, admin-console and vpn2. A suspicious login was flagged on her account3.

  1. [1] users passport AB1234567 → Alice Costa
  2. [2] identity OWNS → billing, admin-console, vpn
  3. [3] logs warning: suspicious login

Built on the engine · planned

Everything your agents need, on the same data.

These managed services are on the way. Tell us what you would run on them — we onboard early users by email and talk fit before anything is deployed.

Agent HostingPlanned A home for the agents you choose. Planned managed hosting for Hermes Agent, OpenClaw and Paperclip, with persistent customer environments. Explore Agent Hosting →
Agent MemoryPlanned Give the next session somewhere to start. Extracted on write, embedded, and recalled by meaning when the next session starts. Explore Agent Memory →
RedDB ModelsPlanned One endpoint. One key. Explore Models →
AI StoragePlanned Keep the work your agents create. Explore AI Storage →
Explore RedDB AI How AI is priced

Explore by product

Start with the database. Build on it.

Every product line shares one engine. The database is live today; around it we ship AI features in the engine and build the services and agents that use it.

60 seconds to first query

Merge the stack. Ship the next thing.

Claim a free nano database on Cloud — no credit card, no sales call — or self-host it free under BSL 1.1.

Start free See pricing
Self-host quick start More paths →

$ npx reddb-cli@latest server --http --bind 127.0.0.1:5055

$ docker run --rm -p 5055:5055 ghcr.io/reddb-io/reddb:latest