#5353rd of 60 in RAG, knowledge and search
jamaibase
RAG backend with spreadsheet-style tables over SQLite and LanceDB
- Stars
- 1.1k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Feb 2025
- Language
- Python
1,068 on 21 Apr 20261,103 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
JamAI Base is a RAG backend that stores data in embedded SQLite and LanceDB and exposes it as spreadsheet-like tables, where columns can be filled by LLM prompts. It provides Generative, Action, Knowledge and Chat tables, with built-in embedding, reranking, query rewriting and hybrid search, reachable through a web UI and a REST API. It can be used on the hosted cloud or self-hosted.
Who it is for: Developers wanting a RAG backend with a table-style UI and REST API
Strengths
- Embedded SQLite and LanceDB, so no separate database server is listed
- Built-in hybrid search, reranking and query rewriting without assembling a RAG pipeline
- Spreadsheet-style UI plus a REST API
- Supports multiple LLM providers, including OpenAI, Anthropic and Llama models
Weaknesses
- Self-hosting steps live in external docs; README has no Docker or compose instructions
- Last release is 2025-02-13, while commits continue into 2026-10
- Existing v1 installs need a migration to v2
- Contributing guide link in the README is a placeholder
What it needs
- Docker + Compose
- Needs SQLite, LanceDB
- Models: OpenAI GPT-4, Anthropic Claude 3, Meta Llama 3, BGE M3 embeddings
What changed
- v0.4 ↗ (opens in a new tab)Breaking
“Backend (GenTable) - Breaking: Add Page column to knowledge table.”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in RAG, knowledge and search
See all 60| Rank | Project | Score |
|---|---|---|
| 1 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 90 out of 100 |
| 2 | Open NotebookSelf-hosted NotebookLM alternative for research notebooks, chat, and podcasts | 90 out of 100 |
| 3 | LightRAGGraph-based RAG framework with a REST server and WebUI | 90 out of 100 |
| #4 | deeptutorTutoring workspace with knowledge bases, guided learning, memory and quizzes | 89 out of 100 |
| #5 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 89 out of 100 |