bisheng

bisheng is a LLM observability tool - 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.

Overview

Proudly made by Chinese，May we, like the creators of Deepseek and Black Myth: Wukong, bring more wonder and greatness to the world.

BISHENG is an open LLM application devops platform, focusing on enterprise scenarios. It has been used by a large number of industry leading organizations and Fortune 500 companies.

"Bi Sheng" was the inventor of movable type printing, which played a vital role in promoting the transmission of human knowledge. We hope that BISHENG can also provide strong support for the widespread implementation of intelligent applications. Everyone is welcome to participate.

1. 🚀 Task Mode: a general-purpose agent for complex, multi-step work You give it a goal and, if needed, attach files, knowledge bases, tools and skills. The agent breaks the goal into tasks, runs them step by step, and delivers a report, PPT, Excel or Word file.

bisheng is open-source, written primarily in Python, with 12,060 GitHub stars under the Apache 2.0 license. The latest release is v2.6.0-fix2 (2026-08-11).

Key capabilities

From the project's documentation:

• 🙋 Human in the loop: When the agent needs information that only you have, the task pauses until you answer.
• 🗂️ Organized content: Multi-level folders, tags, card and list views, and search by keyword and tag together.
• 🎯 Precise filtering: Custom rules filter titles and body text, so only relevant articles stay.
• Human in the loop: A running flow can stop and wait for a person to give input, confirm, or make changes.
• Audit: Records conversation content and system operation logs, searchable by user, time and module.
• Xinchuang (domestic IT stack) support: Supports both MySQL and Dameng DM8.

How it fits a local-AI stack

bisheng runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related LLM observability tools in the directory:

• "langfuse"
• "plano"
• "RagaAI-Catalyst"

Sources

• Source code & docs: dataelement/bisheng
• Official website: http://www.bisheng.ai

Stats from GitHub, 2026-10-19.