RAG and document tools for building AI agents
Retrieval tools that let agents search documents, PDFs and knowledge bases and answer from them (RAG). Of the 247 tools on our building AI agents page, 22 fit this narrower job. By pricing: 19 open source, 1 source-available, 1 free or freemium, 1 pricing on the maker's site. The most-starred open repos here are Mem0 (67,147 stars), Context7 (63,157 stars), PrivateGPT (57,594 stars). Most come from the frameworks (11), memory & RAG (6), MCP servers (2) categories.
Updated
Mem0
Mem0 is an open-source memory layer for AI agents that extracts facts from conversations in a single add-only pass, links entities across memories and retrieves them in later sessions, with an Apache-2.0 SDK and a managed platform.
Added
Context7
MCP server and platform that feeds coding agents up-to-date, version-specific library documentation.
Added
PrivateGPT
Open-source API layer that turns local models into private AI applications, with RAG, tools, skills, MCP and text-to-SQL on any OpenAI-compatible server.
Added
LlamaIndex
Framework for agents over your data (RAG, document agents).
Added
AstrBot
Open-source agent chatbot platform and framework that connects LLMs, plugins and tools to mainstream messaging apps for assistants, support bots and knowledge bases.
Added
MindsHub
MindsDB's agent workspace for research, analysis, documents and coding, with a model router, a scoped vault for connected data and swappable open-source agent harnesses.
Added
DSPy
Stanford framework for programming rather than prompting language models, with optimizers that tune prompts and weights for RAG pipelines and agent loops.
Added
ScrapeGraphAI
Python library that uses LLMs and graph logic to build scraping pipelines: describe the data you want and it extracts it from websites or documents.
Added
Serena
MCP toolkit that gives coding agents semantic code retrieval and editing, like IDE features.
Added
Haystack
Open-source orchestration framework for building production LLM apps, RAG and agents.
Added
llmware
Framework for building private, local RAG and agent applications with small specialized models on AI PCs, edge and self-hosted setups.
Added
txtai
All-in-one Python framework for semantic search, LLM orchestration and agents built on an embeddings database of vector, graph and relational indexes.
Added
UltraRAG
Low-code MCP-based framework from OpenBMB for building and debugging complex RAG pipelines with visible reasoning logic.
Added
Kiln
Free desktop app and open-source library for building AI systems with evals, RAG, agents, fine-tuning and synthetic data in one workbench.
Added
DocETL
System for agentic, LLM-powered document processing and ETL pipelines from UC Berkeley.
Added
SimpleMem
Research-backed lifelong memory library for LLM agents that stores, compresses and retrieves text and multimodal memories, usable over MCP.
Added
Neuron AI
PHP framework for creating and orchestrating AI agents with LLMs, tools, vector stores and memory.
Added
Langchain.rb
Ruby library for building LLM-powered applications, RAG and assistants.
Added
Pixeltable
Multimodal data layer that combines storage, transforms, indexing and retrieval in one Python library for building agents over images, video and documents.
Added
BaseAI
Web AI framework from Langbase for building AI agents with memory (RAG) and deploying them serverless.
Added
Dynamiq
Python orchestration framework for building agentic and RAG applications from reusable nodes and workflows.
Added
Mastra
TypeScript framework for agents, workflows and RAG.
Added
GitHub repos (21)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| Mem0 ↗ | 67,147 | Apache License 2.0 | 2026-10-21 |
| Context7 ↗ | 63,157 | MIT | 2026-10-21 |
| PrivateGPT ↗ | 57,594 | Apache License 2.0 | 2026-10-20 |
| LlamaIndex ↗ | 52,485 | MIT | 2026-10-14 |
| AstrBot ↗ | 42,095 | GNU Affero General Public License v3.0 | 2026-10-21 |
| MindsHub ↗ | 39,800 | MIT | 2026-10-19 |
| DSPy ↗ | 38,676 | MIT | 2026-10-20 |
| ScrapeGraphAI ↗ | 31,882 | MIT | 2026-10-06 |
| Serena ↗ | 30,329 | GPL-3.0-or-later for the Serena application; MIT for SolidLSP | 2026-10-20 |
| Haystack ↗ | 26,748 | Apache License 2.0 | 2026-10-21 |
| llmware ↗ | 14,814 | Apache License 2.0 | 2026-10-01 |
| txtai ↗ | 13,024 | Apache License 2.0 | 2026-10-20 |
| UltraRAG ↗ | 5,729 | — | 2026-10-13 |
| Kiln ↗ | 5,195 | — | 2026-10-21 |
| DocETL ↗ | 4,133 | MIT | 2026-10-09 |
Top 15 of 21 by stars. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for building AI agents focused on RAG and documents?
We list 22. The first three by GitHub stars and featured status are Mem0: Mem0 is an open-source memory layer for AI agents that extracts facts from conversations in a single add-only pass, links entities across memories and retrieves them in later sessions, with an Apache-2.0 SDK and a managed platform.; Context7: MCP server and platform that feeds coding agents up-to-date, version-specific library documentation.; PrivateGPT: Open-source API layer that turns local models into private AI applications, with RAG, tools, skills, MCP and text-to-SQL on any OpenAI-compatible server.
Are there free or open-source options?
Yes: 19 open source, 1 source-available, 1 free or freemium, 1 pricing on the maker's site. Pricing is as each maker states it.
More from building AI agents
Tools are grouped by what each says it does. Missing one? Submit it free.