Agentic Rag Python Packages

haystack-ai

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

honcho-ai

Memory library for building stateful agents

openviking

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

deeplake

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

langchain-openviking

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

farm-haystack

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

vector-vault

The first serverless vector database (2023). Stateless compute + object storage, open source Python. pip install vector-vault

haiku-rag-slim

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

haiku-rag

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

pdf-mcp

MCP server that lets Claude Code and other AI agents read and search large PDFs, one file or a whole folder: agentic RAG with hybrid semantic + keyword search, selective page reads, tables, images, OCR, chart data, and multi-column/CJK layouts.

honcho-cli

Memory library for building stateful agents

next-plaid-client

NextPlaid, ColGREP: Multi-vector search, from database to coding agents.

monkeyllm

Knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph the agent navigates over MCP. Curated summaries, typed edges, cited answers, SQL over your spreadsheets, no chunking. Same 12B local model: 0/11 on multi-hop questions as top-k RAG, 11/11 as a navigator. Python, Apache-2.0, self-hostable.

tldw-server

tl/dw (Too Long, Didn't Watch): Your Personal Research Multi-Tool - a naive attempt at 'A Young Lady's Illustrated Primer' (Open Source NotebookLM)

caesar-agent

Caesar — autonomous AI research agent with graph-based deep web exploration and adversarial answer synthesis. Open-source alternative to ChatGPT Deep Research, Perplexity, and Gemini Deep Research.

orka-reasoning

Orchestrator Kit for Agentic Reasoning - OrKa is a modular AI orchestration system that transforms Large Language Models (LLMs) into composable agents capable of reasoning, fact-checking, and constructing answers with transparent traceability.

knowledge-storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

sochdb

SochDB is a high-performance embedded, ACID-compliant database purpose-built for AI agents and memory - python sdk

vectara-agentic

A python library for creating AI assistants with Vectara, using Agentic RAG

mcp-unified

tl/dw (Too Long, Didn't Watch): Your Personal Research Multi-Tool - a naive attempt at 'A Young Lady's Illustrated Primer' (Open Source NotebookLM)

financebench-rag-agent

Multi-agent LangGraph RAG for financial Q&A — 72.7% on FinanceBench under κ=0.932 calibrated judge. RBAC at the vector layer, multi-party HITL on high-stakes answers, self-hosted LLM observability. pip install financebench-rag-agent

velocirag

Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.

ragfabric-server

RagFabric: self hosted, measurement first RAG platform. Four retrieval strategies (Traditional, Agentic, Graph, Vectorless) behind one interface, a query router, real evaluation, configurable providers and stores, access control, observability.

ragfabric

RagFabric: self hosted, measurement first RAG platform. Four retrieval strategies (Traditional, Agentic, Graph, Vectorless) behind one interface, a query router, real evaluation, configurable providers and stores, access control, observability.