Aisop – Define AI agent workflows as Mermaid or JSON flow graphs
AISOP is an open protocol designed for defining structured AI programs using either Mermaid or JSON flow graphs. It allows for the creation of multi-step AI workflows with features like branching, parallel execution, and error handling. The protocol is machine-readable and optimized for large language model comprehension, making it versatile for various applications.
- ▪AISOP supports dual flow formats, allowing both Mermaid strings and JSON flow objects to coexist in the same program.
- ▪The protocol includes over 14 control flow patterns, enabling complex workflows with features like error handling and sub-task support.
- ▪AISOP files are plain JSON, making them editable in any text editor and versionable in git.
Opening excerpt (first ~120 words) tap to expand
AISOP — AI Standard Operating Protocol 中文版 README An open protocol for defining structured AI programs using Mermaid or JSON flow graphs. AISOP enables defining multi-step AI programs with visual (Mermaid) or structural (JSON) control flow — branching, parallel execution, sub-tasks, and error handling — all in a single portable JSON format. Why AISOP? Approach Definition Portable Machine-readable Token-efficient Natural language prompts Free text Yes No No Python / YAML workflows Code / config No Partially No Visual builders (Dify, etc.) Proprietary No No No AISOP Mermaid + JSON Yes Yes Yes AISOP files are plain JSON with flow graphs (Mermaid or JSON) — readable by any language, editable in any editor, versionable in git, and optimized for LLM comprehension.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.