AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
Home/
RAG / Knowledge Base/
haiku.rag
haiku.rag logo

haiku.rag

Active·★ 529·MIT·Updated 2026-05-29
★ RAG / Knowledge Base★ LLM Infra

Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling

Haiku RAG is an agentic retrieval-augmented generation (RAG) system built with LanceDB, Pydantic AI, and Docling. It offers advanced features like hybrid search, multi-agent workflows for research, complex analytical tasks via code execution, and conversational RAG with session memory.

#RAG#Agentic AI#Hybrid Search
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

#Vector Database
#Question Answering
#Reranking
#Conversational AI
#Local-first
$ Install
$ pip install haiku.rag
↗ Visit site★ GitHub
01

Features

01Hybrid search — Vector + full-text with Reciprocal Rank Fusion
02Research agents — Multi-agent workflows via pydantic-graph: plan, search, evaluate, synthesize
03RLM agent — Complex analytical tasks via sandboxed Python code execution
04Conversational RAG — Chat TUI and web application for multi-turn conversations with session memory
05Local-first — Embedded LanceDB, no servers required. Also supports S3, GCS, Azure, and LanceDB Cloud
02

Compatibility

Python
Runtime
Verified via docs
Ollama, OpenAI, vLLM
Embedding/LLM Providers
Verified via docs
LanceDB
Vector Database
Verified via docs
Claude Desktop
AI Assistant Integration
Verified via docs
Docker
Deployment
Verified via docs
03

Quick start

1
$ pip install haiku.rag
04

Use cases

↳Indexing various document types (e.g., PDFs, URLs) for search and retrieval.
↳Performing question answering with source citations to verify information.
↳Executing complex analytical tasks using sandboxed Python code (RLM mode).
↳Engaging in multi-turn conversations with memory for contextual understanding.
↳Integrating as a tool for AI assistants (e.g., Claude Desktop) for document management, search, and QA.
05

Alternatives

mindsdb logo
mindsdb★ 39.2k
Federated Query Engine for AI - The only MCP Server you'll ever need
vs →
Brave Search MCP logo
Brave Search MCP★ 86.5k
Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.
vs →
ragflow logo
ragflow★ 81.5k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Related searches

haiku.rag AlternativesBest RAG / Knowledge Base Tools 2026Open Source RAG / Knowledge Basehaiku.rag Tutorialhaiku.rag Vs CompetitorsRAGAgentic AIHybrid Search

Comments

Log in to leave a comment
  • L
    Logan NguyenApr 25, 2026

    Dropped this into flexible pipeline and it just worked. Handles edge cases better than expected.

  • A
    Alex PatelApr 3, 2026

    Setup was straightforward, seamless config and running in minutes. Would recommend for seamless use cases.

  • C
    Corey DavisMar 27, 2026

    Dropped this into flexible pipeline and it just worked. Integrates well with existing opinionated setups.

  • E
    Ellis AndersonMar 13, 2026

    The opinionated coverage is surprisingly complete. Good documentation, reduces onboarding time.

  • A
    Aspen ClarkMar 9, 2026

    Powered via MCP is exactly the right abstraction. No complaints after 3 months of use.

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
Stats
GitHub Stars★ 529
Last commit
vs →
Claude Flow logo
Claude Flow★ 56.4k
The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms.
vs →
MaxKB logo
MaxKB★ 21.1k
An open-source platform for building enterprise-grade agents. Powerful and easy to use.
vs →
ruflo logo
ruflo★ 56.4k
🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration
vs →
GPT Researcher logo
GPT Researcher★ 27.4k
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations.
vs →
deer-flow logo
deer-flow★ 70.0k
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
vs →
See all alternatives →
1d ago
StatusActive
LicenseMIT
CategoryRAG / Knowledge Base
Trend (30d)
+21.1↑ 0.6%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad