# arc53/DocsGPT

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

Repository: https://github.com/arc53/DocsGPT
Canonical: https://ross.abutalabs.com/products/docsgpt
Homepage: https://app.docsgpt.cloud/
Language: Python
License: MIT
License Family: permissive
Topics: ai, python, natural-language-processing, react, chatgpt, docsgpt, information-retrieval, language-model, llm, machine-learning, pytorch, rag, semantic-search, transformers, hacktoberfest, agent-builder, agents, search, hacktoberfest2025
Last push: 2026-08-26T15:37:05+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 85, longevity 93
- inputs: {"age_days": 1308, "days_push": 7, "days_rel": 20, "gap_med": 33.0, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18229, forks 2134 (observed 2026-08-28T04:11:26.470028+00:00)

## What it is
DocsGPT is an open-source AI platform for building private agents, assistants, and enterprise search over your own documents. It includes an Agent Builder, deep research tools, document analysis across many formats, multi-model support, and API connectivity for actionable agent tools.

## Use cases
- chat with my pdf documents
- build an enterprise search over internal docs
- create an AI assistant grounded in company knowledge
- ingest websites and github repos into a searchable knowledge base
- build agents that call external APIs
- transcribe meeting recordings into searchable knowledge
- self-host a private chatgpt alternative

## When to choose
- you need private, self-hosted RAG over documents with source citations
- you want a full platform with UI, agent builder, and multi-model support out of the box
- you need to ingest diverse formats (PDF, Office, audio, web) into one knowledge base

## When to avoid
- you only need a lightweight RAG library to embed in your own code
- you need a simple vector-store wrapper rather than a full application
- you require fully offline operation with no LLM API access and no local model capability

## Facets
- artifact type: application
- maturity: active
- function: rag, agent-framework, chatbot, search-engine, nlp, llm-inference, web-framework, speech-recognition, pdf
- domain: artificial-intelligence, large-language-models, chatbots, self-hosted
- platform: python, self-hosted, cross-platform
- tags: enterprise-search, document-analysis, agent-builder, semantic-search, multi-model, citations, knowledge-base, retrieval-augmented-generation, ai-agents, search, natural-language-processing, web-server, docker

## Member repositories
- arc53/DocsGPT (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:26.470028+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 2026-08-29T17:02:06.815622+00:00, confidence not recorded.
  - readme: https://github.com/arc53/DocsGPT (fetched 2026-08-28T04:11:26.470028+00:00, sha 609ae41aec96)
  - homepage: https://app.docsgpt.cloud/ (fetched 2026-08-29T08:00:02.193559+00:00, sha 1f547221d9f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.