COOKBOOK
Developer Cookbook
Step-by-step framework guides for building AI agents with HatiData. Pick your framework, follow the recipe, ship in minutes.
OpenAI Agents SDK + HatiData: Persistent Memory
Ollama + HatiData: Air-Gapped Local AI
Arrow-Native Queries + Polars: Zero-Copy Analytics
LangChain + HatiData: Persistent Memory in 5 Minutes
CrewAI + HatiData: Multi-Agent Shared Memory
Claude MCP + HatiData: Connect in 60 Seconds
AutoGen + HatiData: Stateful Agent Groups
OpenAI Agents SDK + HatiData: Agent Memory
MCP Memory Tools: Store & Search
Claude MCP + HatiData: Full-Stack Agent Setup
Ollama + HatiData: Local LLM + Memory
Gemini + HatiData: Fraud Detection Pipeline
Build an intelligent fraud detection agent using Google Gemini and HatiData's hybrid SQL.
CrewAI + HatiData: Supply Chain War Room
Deploy a multi-agent crew that monitors suppliers, routes, and inventory with shared memory.
LangChain + HatiData: Contract Auditor
Build a contract review agent with LangChain that analyzes clauses and maintains an immutable audit trail.
OpenAI Agents SDK + HatiData: Persistent Memory
Add persistent memory to OpenAI agents. Agents remember past conversations across sessions.
Vertex AI + HatiData: Enterprise Reasoning Engine
Build an enterprise reasoning engine with Vertex AI and HatiData. Deploy in your VPC with full compliance.
AutoGen + HatiData: Research Team
Build a multi-agent research team with AutoGen GroupChat and shared HatiData memory.
LlamaIndex + HatiData: Structured RAG
Build a RAG pipeline with LlamaIndex that queries structured SQL and semantic vector search through HatiData.
Ollama + HatiData: Air-Gapped Local AI
Run AI agents completely locally with Ollama and HatiData. Zero cloud dependencies.
Arrow-Native Queries + Polars: Zero-Copy Analytics
Query HatiData and load results directly into polars or pandas DataFrames via Apache Arrow IPC — zero parsing, full type fidelity.
LangChain + HatiData: Persistent Memory in 5 Minutes
Give your LangChain agent persistent memory that survives restarts. Store and retrieve conversation context with semantic search.
CrewAI + HatiData: Multi-Agent Shared Memory
Build a CrewAI crew where agents share persistent memory through HatiData. One agent's discoveries become another's context.
Claude MCP + HatiData: Connect in 60 Seconds
Connect Claude Desktop or Claude Code to HatiData via MCP. Get 24 agent-native SQL tools in under a minute.
AutoGen + HatiData: Stateful Agent Groups
Build AutoGen agent groups with persistent state. Agents remember past conversations and share context across group chat sessions.
OpenAI Agents SDK + HatiData: Agent Memory
Add persistent memory to OpenAI Agents SDK agents. Store conversation context and retrieve it with semantic search across sessions.
LangChain + HatiData: CoT Replay & Audit
Log chain-of-thought reasoning from LangChain agents into HatiData's tamper-proof ledger. Replay sessions and verify hash chain integrity for compliance auditing.
CrewAI + HatiData: Semantic Trigger Setup
Configure semantic triggers that fire webhooks when CrewAI agents discuss specific topics. Use vector-based concept matching for intelligent alerting.
OpenAI Agents + HatiData: Branch-Based Exploration
Use HatiData's branch isolation to let OpenAI agents explore hypothetical scenarios without affecting the main data state. Merge successful outcomes back.
MCP Memory Tools: Store & Search
Set up HatiData's MCP server for Claude Desktop with persistent memory storage and semantic search across sessions.
LangChain + HatiData: Hybrid SQL+Vector Search
Combine SQL metadata filters with vector similarity search in a LangChain retrieval chain for precise, contextual document retrieval.
CrewAI + HatiData: Cross-Agent Memory
Build a CrewAI crew where researcher and writer agents share a persistent memory namespace for seamless knowledge transfer across agent roles.
AutoGen + HatiData: State Branch & Merge
Use HatiData branching to let AutoGen agent groups explore multiple solution paths simultaneously, then merge the best outcome.
LlamaIndex + HatiData: SQL-Based RAG Pipeline
Build a RAG pipeline that uses HatiData's SQL interface for structured data retrieval alongside vector search for unstructured content.
Vercel AI SDK + HatiData: Streaming + Memory
Build a Next.js chat interface with streaming responses from Vercel AI SDK and persistent conversation memory backed by HatiData.
LangChain + HatiData: Policy Enforcement
Set up HatiData's policy engine to enforce query governance on LangChain agents. Block dangerous queries, log violations, and audit agent behavior.
CrewAI + HatiData: Chain-of-Thought Audit
Add full chain-of-thought logging to a CrewAI crew for compliance auditing. Replay any agent's decision-making process and export audit reports.
MCP + HatiData: Trigger to Webhook Pipeline
Build an MCP-based trigger pipeline that fires HMAC-signed webhooks when agents discuss specific topics. Monitor agent conversations in real-time.
OpenAI Agents + HatiData: Agent RBAC Setup
Set up per-agent API keys with scoped permissions in HatiData. Control what each OpenAI agent can read, write, and administer.
LangChain + HatiData: Multi-Tenant Memory
Build a multi-tenant LangChain application where each customer's agent memories are logically isolated in HatiData using namespace-based tenancy.
Arrow/Polars + HatiData: ML Feature Pipeline
Build a zero-copy ML feature pipeline that loads HatiData query results directly into Polars DataFrames via Apache Arrow IPC format.
dbt + HatiData: dbt Adapter Transforms
Use the HatiData dbt adapter to run SQL-based data transformations in the agent data warehouse. Create models, run tests, and build data pipelines.
Claude MCP + HatiData: Full-Stack Agent Setup
Set up Claude Desktop with all 24 HatiData MCP tools for a complete agent-native data experience including memory, CoT, triggers, branching, and queries.
Ollama + HatiData: Local LLM + Memory
Build a fully local AI agent setup using Ollama for inference and HatiData for persistent memory — no cloud APIs, no data leaving your machine.
Vertex AI + HatiData: Enterprise Agent Deploy
Deploy an enterprise-grade Vertex AI agent with HatiData persistent memory on Google Cloud Run. Production-ready with IAM, VPC, and monitoring.
CrewAI + HatiData: Credit-Aware Agents
Build a CrewAI crew that monitors HatiData credit usage in real-time and adapts agent behavior based on remaining budget to prevent overspend.