# truefoundry/cognita

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry

Repository: https://github.com/truefoundry/cognita
Canonical: https://ross.abutalabs.com/products/cognita
Homepage: https://cognita.truefoundry.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, deep-learning, generative-ai, llmops, machine-learning, mlops, model-deployment, python, rag, retrieval-augmented-generation, typescript, agent, application, data, fine-tuning, framework, llm, llm-ops
Archived: true
Last push: 2026-03-13T15:04:36+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 72, release rhythm 35, longevity 81
- inputs: {"age_days": 1134, "days_push": 173, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4418, forks 392 (observed 2026-08-28T04:08:48.712623+00:00)

## What it is
Cognita is an open-source RAG (Retrieval Augmented Generation) framework by TrueFoundry for building modular, production-ready RAG applications. It wraps LangChain/LlamaIndex with a modular, API-driven architecture, a no-code UI, incremental indexing, and pluggable vector DBs, parsers, embedders, and rerankers.

## Use cases
- build a production RAG application
- index documents and query them with an LLM
- run a self-hosted RAG chatbot over my own data
- prototype RAG pipelines with a no-code UI
- compare vector databases and embedding models for retrieval
- parse PDFs, audio, and video for retrieval-augmented search

## When to choose
- you want a modular, production-oriented alternative to notebook-style LangChain/LlamaIndex prototypes
- you need a no-code UI plus incremental indexing out of the box
- you want pluggable vector DBs, parsers, embedders, and rerankers in one framework

## When to avoid
- you need actively maintained software - the project is no longer maintained
- you want a minimal library rather than a full application framework
- you need features beyond the last 2026 release or community support

## Facets
- artifact type: framework
- maturity: abandoned
- function: rag, llm-inference, agent-framework, web-framework, search-engine, vector-database, etl
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python, self-hosted, cross-platform
- tags: llmops, no-code-ui, incremental-indexing, document-parsing, langchain, llamaindex, production-rag, retrieval-augmented-generation, ai-agents, docker, web-server

## Member repositories
- truefoundry/cognita (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:48.712623+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 2026-08-29T18:21:00.366628+00:00, confidence not recorded.
  - readme: https://github.com/truefoundry/cognita (fetched 2026-08-28T04:08:48.712623+00:00, sha 578695ba01f3)
- Data as of 2026-08-30T08:39:29.467469+00:00.