# dataelement/bisheng

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.

Repository: https://github.com/dataelement/bisheng
Canonical: https://ross.abutalabs.com/products/bisheng
Homepage: http://www.bisheng.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, ai, chatbot, rag, workflow, enterprise, genai, gpt, langchian, llama, llm, llmdevops, llmops, ocr, openai, orchestration, python, react, finetune, sft
Last push: 2026-08-26T14:28:43+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 97, longevity 78
- inputs: {"age_days": 1101, "days_push": 7, "days_rel": 22, "gap_med": 11.0, "n_releases_24m": 31}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11911, forks 1950 (observed 2026-08-28T04:10:50.475503+00:00)

## What it is
BISHENG is an open-source LLM DevOps (LLMOps) platform for building enterprise AI applications, offering GenAI workflow orchestration, RAG, agents, unified model management, evaluation, SFT/fine-tuning, dataset management, and observability. It is a self-hosted Python/React platform used by large enterprises, including Fortune 500 companies.

## Use cases
- build enterprise LLM applications with a visual workflow
- create RAG pipelines over company documents
- orchestrate AI agents with human-in-the-loop review
- manage and evaluate multiple LLM models centrally
- fine-tune models with SFT and manage datasets
- deploy a self-hosted chatbot platform for my company
- add observability to LLM app deployments
- extract data from documents with OCR in AI workflows

## When to choose
- you need an enterprise-grade, self-hosted LLMOps platform combining workflows, RAG, agents, and evaluation
- you want human-in-the-loop intervention inside AI workflows
- you need unified model management plus fine-tuning (SFT) and dataset tooling in one platform
- your organization requires enterprise-level system management and observability for GenAI apps

## When to avoid
- you only need a lightweight library or SDK to call LLMs from code
- you want a fully managed cloud service with no self-hosting overhead
- you need a minimal single-purpose RAG or chatbot tool rather than a full platform
- your team cannot operate a multi-component Python/Docker deployment

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, llm-inference, workflow-automation, chatbot, ocr, machine-learning, data-science, monitoring, etl
- domain: large-language-models, chatbots, developer-tools, self-hosted, erp
- platform: python, self-hosted, cross-platform
- tags: llmops, llm-devops, genai, workflow-orchestration, fine-tuning, sft, evaluation, enterprise-ai, model-management, observability, human-in-the-loop, ai-agents, retrieval-augmented-generation, natural-language-processing, automation, docker, web-server

## Member repositories
- dataelement/bisheng (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:50.475503+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 2026-08-29T17:15:13.212545+00:00, confidence not recorded.
  - readme: https://github.com/dataelement/bisheng (fetched 2026-08-28T04:10:50.475503+00:00, sha 819fe7198dfd)
- Data as of 2026-08-30T08:39:29.467469+00:00.