ragbits and cognita
These are complements—ragbits provides lower-level building blocks for RAG pipelines while cognita offers a higher-level framework for orchestrating modular RAG applications, so teams might use ragbits' components within a cognita-based system.
About ragbits
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
Provides modular Python packages for LLM integration (100+ models via LiteLLM), RAG pipelines with 20+ document formats, and multi-agent coordination using the A2A protocol and Model Context Protocol. Features type-safe prompt execution with Python generics, support for Qdrant/PgVector and other vector stores, Ray-based distributed document ingestion, and OpenTelemetry observability—installable as granular components (core, agents, document-search, evaluate, guardrails, chat, CLI) rather than monolithic framework.
About cognita
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
This framework helps developers quickly build, organize, and deploy Retrieval Augmented Generation (RAG) applications that can answer questions based on specific documents or data. It takes in various document types (text, audio, video) and uses them to power a question-answering system. Data scientists and machine learning engineers who need to move RAG prototypes from notebooks to production-ready systems would use this.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work