# gomate-community/TrustRAG

TrustRAG：The RAG Framework within Reliable input,Trusted output

Repository: https://github.com/gomate-community/TrustRAG
Canonical: https://ross.abutalabs.com/products/trustrag
Homepage: https://gomate-community.github.io/TrustRAG
Language: Python
License Family: other
Topics: rag, retrieval-augmented-generation, deep-research, deep-search
Last push: 2026-01-07T08:00:32+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 61, release rhythm 35, longevity 67
- inputs: {"age_days": 941, "days_push": 238, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1276, forks 138 (observed 2026-08-28T04:04:13.164606+00:00)

## What it is
TrustRAG is a configurable and modular Retrieval-Augmented Generation (RAG) framework in Python built around the principle of reliable input and trusted output for retrieval-based question answering. It includes a DeepResearch module that performs intent understanding, recursive depth-first search, and intelligent action selection (search, read, reflect, answer, code) to produce high-quality answers.

## Use cases
- build a modular rag pipeline for question answering over documents
- retrieval augmented generation framework in python
- run a deep research agent that recursively searches and reads sources
- reduce hallucinations in llm answers with trusted retrieval
- configure and swap individual rag components like retriever, parser, and generator
- implement multi-step deep search with intent understanding and token budgets

## When to choose
- You want a Python RAG framework with highly configurable, modular components you can tune per application
- You need deep-research style agentic search with recursive queries, reflection, and action planning
- You are building retrieval-based QA where answer trustworthiness and reliable input matter

## When to avoid
- You need a turnkey hosted RAG product with a ready-made UI rather than a framework you assemble
- You require a project with an explicit open-source license for commercial use, since the repository lists no license
- You work outside the Python ecosystem

## Facets
- artifact type: framework
- maturity: active
- function: rag, search-engine, agent-framework, llm-inference
- domain: large-language-models, artificial-intelligence
- platform: python, cross-platform
- tags: deep-research, agentic-rag, retrieval-augmented-generation, question-answering, modular-framework, document-parsing, hallucination-reduction, recursive-search, search, ai-agents, natural-language-processing

## Member repositories
- gomate-community/TrustRAG (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.164606+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 2026-08-30T05:02:56.514167+00:00, confidence not recorded.
  - readme: https://github.com/gomate-community/TrustRAG (fetched 2026-08-28T04:04:13.164606+00:00, sha 4749585d4eca)
  - homepage: https://gomate-community.github.io/TrustRAG (fetched 2026-08-29T12:13:59.995218+00:00, sha 26c956c55409)
  - registry_pypi: https://pypi.org/pypi/trustrag/json (fetched 2026-08-29T12:14:00.004707+00:00, sha 1307b8008e71)
- Data as of 2026-08-30T08:39:29.467469+00:00.