Knowledge Base & RAG
Enterprise search and RAG platforms — alternatives to Glean and Notion AI.
156 projects
See methodology for ranking rules; order uses public GitHub metrics within this scenario.
| Rank | Project | Stars | Forks | Updated | License |
|---|---|---|---|---|---|
| 21 |
opendataloader-pdf
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source. |
28.9K | 2.8K | 08/28/26 | Apache-2.0 |
| 22 |
kotaemon
An open-source RAG-based tool for chatting with your documents. |
25.7K | 2.1K | 07/14/26 | Apache-2.0 |
| 23 |
MaxKB
🔥 MaxKB is an open-source platform for building enterprise-grade agents. |
22.6K | 3.1K | 08/29/26 | GPL-3.0 |
| 24 |
WeKnora
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. |
20.9K | 3.0K | 08/29/26 | Other |
| 25 |
gpt-crawler
Crawl a site to generate knowledge files to create your own custom GPT from a URL |
22.4K | 2.4K | 07/07/25 | Other |
| 26 |
unstructured
Open-source ETL for converting complex documents into clean, structured data for language models. |
15.4K | 1.3K | 08/28/26 | Apache-2.0 |
| 27 |
llm_wiki
A cross-platform desktop app that automatically builds and maintains an interlinked personal wiki from your documents, using LLM-driven incremental ingestion and source-grounded retrieval. |
17.1K | 2.0K | 08/25/26 | Other |
| 28 |
memvid
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory. |
16.5K | 1.4K | 07/14/26 | Apache-2.0 |
| 29 |
Skill_Seekers
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection |
14.9K | 1.5K | 08/27/26 | MIT |
| 30 |
llmware
Unified framework for building enterprise RAG pipelines with small, specialized models |
14.9K | 2.9K | 05/17/26 | Apache-2.0 |
| 31 |
memU
Personal memory across agents |
14.4K | 1.1K | 08/28/26 | Other |
| 32 |
claude-obsidian
Self-organizing AI second brain that turns any source into a linked Markdown knowledge graph for Obsidian and Claude Code. |
14.3K | 1.4K | 08/26/26 | MIT |
| 33 |
note-gen
Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with AI. |
12.7K | 960 | 08/27/26 | GPL-3.0 |
| 34 |
FlagEmbedding
Retrieval and Retrieval-augmented LLMs |
12.1K | 909 | 08/24/26 | MIT |
| 35 |
semantica
Graph-Native Infrastructure for Context and Accountable AI Systems |
11.2K | 1.2K | 08/29/26 | MIT |
| 36 |
blinko
An open-source, self-hosted personal AI note tool prioritizing privacy, built using TypeScript . |
11.0K | 777 | 08/27/26 | GPL-3.0 |
| 37 |
PandaWiki
PandaWiki is an AI-large-model-driven open-source knowledge base system for building intelligent product docs, technical docs, FAQs, and blogs, with AI writing, Q&A, and search. |
10.2K | 1.0K | 08/21/26 | AGPL-3.0 |
| 38 |
local-deep-research
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted. |
9.0K | 798 | 08/29/26 | MIT |
| 39 |
PixelRAG
The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/ |
9.8K | 836 | 08/29/26 | Apache-2.0 |
| 40 |
paper-qa
High accuracy RAG for answering questions from scientific documents with citations |
9.1K | 913 | 08/26/26 | Apache-2.0 |