# deepsense-ai/ragbits

Building blocks for rapid development of GenAI applications

Repository: https://github.com/deepsense-ai/ragbits
Canonical: https://ross.abutalabs.com/products/ragbits
Homepage: https://ragbits.deepsense.ai
Language: Python
License: MIT
License Family: permissive
Topics: rag, document-search, evaluation, guardrails, agents, llms, optimization, prompts, vector-stores
Last push: 2026-05-18T07:51:25+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 77, longevity 52
- inputs: {"age_days": 730, "days_push": 107, "days_rel": 155, "gap_med": 6, "n_releases_24m": 38}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1668, forks 143 (observed 2026-08-28T04:05:19.776021+00:00)

## What it is
Ragbits is a Python framework of modular building blocks for rapidly developing generative AI applications, covering LLM interaction, prompt management, RAG document ingestion and search, and multi-agent workflows. It includes developer CLI tools, type-safe LLM calls via LiteLLM, support for multiple vector stores, and Ray-based distributed ingestion.

## Use cases
- build a RAG pipeline over PDFs and other documents
- swap between 100+ LLM providers without rewriting code
- ingest documents into Qdrant or PgVector vector stores
- create multi-agent workflows with the A2A protocol
- test and manage prompts from the terminal
- add guardrails and evaluation to GenAI apps
- run distributed document ingestion at scale

## When to choose
- you want a batteries-included Python framework for GenAI/RAG development
- you need flexible document ingestion across many formats and cloud sources
- you want type-safe prompting and swappable LLM backends
- you're building multi-agent systems with interoperability needs

## When to avoid
- you need a simple one-off LLM API call without framework overhead
- you're not working in Python
- you need a fully managed SaaS solution rather than a self-assembled toolkit

## Facets
- artifact type: framework
- maturity: active
- function: rag, llm-inference, agent-framework, prompt-engineering, vector-database, etl, cli, sdk
- domain: large-language-models, machine-learning, developer-tools
- platform: python, cross-platform
- tags: genai, llm, document-ingestion, vector-stores, a2a-protocol, guardrails, prompt-management, litellm, retrieval-augmented-generation, ai-agents, natural-language-processing

## Member repositories
- deepsense-ai/ragbits (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:19.776021+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 2026-08-30T03:42:49.560491+00:00, confidence not recorded.
  - readme: https://github.com/deepsense-ai/ragbits (fetched 2026-08-28T04:05:19.776021+00:00, sha 00cd21214812)
  - homepage: https://ragbits.deepsense.ai (fetched 2026-08-29T11:16:08.509933+00:00, sha 0cc59130a56d)
  - registry_pypi: https://pypi.org/pypi/ragbits/json (fetched 2026-08-29T11:16:08.518774+00:00, sha ce7fe1082a7c)
- Data as of 2026-08-30T08:39:29.467469+00:00.