Skip to main content

HatiData Documentation

Agent-Native Data Infrastructure for AI agents. Sub-10ms SQL, persistent memory, verifiable reasoning, semantic triggers — all through a single Postgres connection.

Quickstart → | What is ANDI? → | GitHub →

What is HatiData?

HatiData is Agent-Native Data Infrastructure (ANDI) — the data layer purpose-built for AI agents. It speaks the Postgres wire protocol, transpiles Snowflake-compatible SQL for execution, and delivers sub-10ms query latency. Beyond SQL, HatiData gives agents persistent memory, semantic triggers, chain-of-thought logging, and branch isolation out of the box.

Read the full ANDI definition →

Five Pillars of ANDI

PillarWhat It DoesLearn More
Agent IdentityPer-agent keys, scopes, billing, and audit attributionIdentity Model
Persistent MemorySQL + vector hybrid search across sessionsMemory
Chain-of-ThoughtImmutable cryptographically hash-chained reasoning tracesCoT Ledger
Semantic TriggersConcept-based rules with webhook, notify, and review actionsTriggers
Branch IsolationCopy-on-write speculative queries with merge strategiesBranching

How It Works

Every SQL query flows through a multi-stage pipeline that handles access control, SQL transpilation, execution, column masking, metering, and audit automatically. Security and compliance are built into every query path — not bolted on after.

For the full pipeline, see Architecture in 60 Seconds.

Three Deployment Tiers

TierPriceData LocationBest For
LocalFreeYour machineDevelopment, prototyping, CI
Cloud$29/monthHatiData-managedSmall teams, startups
EnterpriseCustomYour VPCRegulated industries, production

The same SQL, SDKs, and agent code work across all tiers. Only the connection string changes.

Key Differentiators

  • Agent-native — Agents identify themselves via startup parameters. Per-agent billing, scheduling, and audit happen automatically.
  • Sub-10ms latency — Embedded columnar engine with three-tier caching (in-memory, high-performance local SSD, object storage).
  • Snowflake SQL compatible — The transpiler handles function mapping (NVL, IFF, DATEDIFF), type mapping (VARIANT, TIMESTAMP_NTZ), and construct rewriting (FLATTEN, OBJECT_CONSTRUCT).
  • Secure by default — Access control, column masking, metering, and audit built into every query path.
  • Local-first — Start with hati init and query immediately. No cloud account needed.

Integrations

HatiData works with every major AI agent framework and any Postgres-compatible tool:

Open Source

The CLI, SDKs, and integrations are open source under the Apache-2.0 license:

V2: Governed Runtime

New in V2

HatiData V2 adds a Governed Runtime — lifecycle management for agent tasks, with full lineage, explainability, and human-in-the-loop checkpoints.

V2 FeatureWhat It DoesLearn More
Tasks & AttemptsIntent vs execution separation, leases, recoveryTasks & Attempts
Lineage & ExplainabilityTrace any artifact to its prompt, model, and costLineage
Branching & Isolation4 visibility modes, no-leak guaranteeBranching
Human-in-the-LoopGate predicates, review queues, recovery workflowsHITL
Optimization & ReplayReward signals, bandit routing, counterfactual replayOptimization

Migrating from V1? See the V1 to V2 Transition Guide.

Next Steps

Stay in the loop

Product updates, engineering deep-dives, and agent-native insights. No spam.