Documentation

Use this page as the shortest path into the docs. Pick the workflow that matches what you are trying to do.

---

Start here

Quick Start Start with SQL, or jump into the Agent Memory Python loop.

Agent Memory Build an agent flow with time-series evidence, context retrieval, and prompt cache.

HTTP API Use SQL endpoints, Agent Memory endpoints, auth, metrics, and admin APIs.

Python API Query data, use dataframe helpers, and call memory/cache helpers from Python.

---

Choose a path

Build an agent

Start with the Agent Memory overview, then use the Python or HTTP reference for implementation details.

Agent Memory → · Python API → · HTTP API →

Run time-series workloads

Learn the SQL surface, ingestion options, benchmarks, and feed handlers.

SQL Reference → · Benchmarks → · Feed Handlers →

Deploy and operate

Move from a local server to Docker, production deployments, Kubernetes, and security operations.

Docker → · Production Deployment → · Security Operations →

Evaluate fit

Compare ZeptoDB against kdb+, ClickHouse, InfluxDB, and TimescaleDB before choosing an architecture.

vs kdb+ → · vs ClickHouse → · vs TimescaleDB →

---

Common tasks

Task	Go to
Start a local server	Quick Start
Configure Agent Memory persistence	HTTP API Reference
Write an agent context flow	Agent Memory
Query from Python	Python API Reference
Use SQL temporal functions	SQL Reference
Deploy with Docker	Docker Deployment
Run in production	Production Deployment
Set up SSO/RBAC/audit	Security Operations Guide
Review latency numbers	Benchmarks

---

Current Agent Memory boundary

Agent Memory v0 is single-node. In clustered deployments, route /api/ai/* to one sticky pod or treat the memory layer as a per-pod cache. The distributed time-series cluster remains available for time-series workloads.

For implementation details, use HTTP API Reference and Python API Reference.