# EmbeddedLLM/JamAIBase

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

Repository: https://github.com/EmbeddedLLM/JamAIBase
Canonical: https://ross.abutalabs.com/products/jamaibase
Homepage: https://www.jamaibase.com/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agents, ai, ai-agents-framework, baas, chatbot, lancedb, llm, llm-ops, python, serverless, backend-as-a-service, chatgpt, orchestration, rag, retrieval-augmented-generation, workflow, svelte, spreadsheet, intelligent-spreadsheet, llama3-1
Last push: 2026-08-17T07:25:03+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 28, longevity 58
- inputs: {"age_days": 825, "days_push": 16, "days_rel": 566, "gap_med": 42.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1101, forks 47 (observed 2026-08-28T04:03:35.684149+00:00)

## What it is
JamAI Base is an open-source backend-as-a-service platform for AI that combines an embedded SQLite database and LanceDB vector database with managed RAG, LLM, embedding, and reranker orchestration. It exposes these capabilities through a spreadsheet-like UI and a simple REST API, with Generative, Action, Knowledge, and Chat tables as core building blocks.

## Use cases
- build a RAG backend without managing an AI stack
- create chatbots with context-aware responses from uploaded documents
- generate LLM-powered columns in database tables
- orchestrate LLM workflows streamed to web or mobile apps
- upload PDFs and DOCX files for automatic chunking and embedding
- prototype AI features quickly like Firebase but for LLMs

## When to choose
- you want a self-hosted Firebase-like backend with built-in RAG and vector search
- you prefer a spreadsheet UI for iterating on prompts and LLM outputs
- you want to avoid wiring together LangChain/LlamaIndex with separate vector stores
- you need chatbot conversation storage and knowledge retrieval out of the box

## When to avoid
- you need fine-grained control over every RAG pipeline component
- you already have a mature custom AI stack and only need a vector database
- you require a fully offline solution with no hosted model dependencies
- your workload needs a database other than SQLite/LanceDB

## Facets
- artifact type: service
- maturity: active
- function: rag, vector-database, database, llm-inference, chatbot, agent-framework, workflow-automation, api-framework, web-framework
- domain: large-language-models, chatbots, backend, self-hosted, web-development
- platform: python, self-hosted, cross-platform
- tags: backend-as-a-service, generative-tables, spreadsheet-ui, lancedb, sqlite, llm-orchestration, firebase-alternative, embeddings, reranker, retrieval-augmented-generation, ai-agents, web-server, docker

## Member repositories
- EmbeddedLLM/JamAIBase (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:35.684149+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:45:40.974763+00:00, confidence not recorded.
  - readme: https://github.com/EmbeddedLLM/JamAIBase (fetched 2026-08-28T04:03:35.684149+00:00, sha b613e11c53d0)
  - homepage: https://www.jamaibase.com/ (fetched 2026-08-29T12:49:02.735592+00:00, sha fab9ef4c4232)
  - site_page: https://docs.jamaibase.com (fetched 2026-08-29T12:49:02.745166+00:00, sha 7f72cca2e04b)
  - site_page: https://www.jamaibase.com/pricing (fetched 2026-08-29T12:49:02.747662+00:00, sha e96ffed62e4c)
- Data as of 2026-08-30T08:39:29.467469+00:00.