Orchestration frameworkSoftware development
bisheng
Build enterprise AI workflows, RAG systems, agents, and model operations in one platform.
- Stars
- 11,518
- Forks
- 1,888
- Updated
- Updated Jul 14, 2026
Apache-2.0
Build enterprise AI workflows, RAG systems, agents, and model operations in one platform.
BISHENG is a self-hosted platform for creating and operating enterprise LLM applications. It brings workflow orchestration, RAG, agents, model and dataset management, evaluation, fine-tuning, administration, and observability into one browser-based environment. Deployment uses Docker Compose; the documented minimum is four virtual CPU cores and 16 GB of RAM, and the default stack also installs Elasticsearch, Milvus, and OnlyOffice.
Resource types
Use cases
Runtime
Orchestrate multi-agent automation with role-based teams and event-driven flows.
Configure and run custom multi-agent workflows without writing orchestration code.
Capabilities
Audience
Public GitHub facts last synced Jul 14, 2026.
Coordinate AI coding agents with persistent git-backed work tracking
Keeps coding agents iterating through role-based loops until the task is complete or the limit is reached.