{"repo":"deerwork-ai/deer-workflow","free":true,"listed":false,"github":"https://github.com/deerwork-ai/deer-workflow","clone":"git clone https://github.com/deerwork-ai/deer-workflow.git","description":"An open-source graph engineering runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes.","language":"TypeScript","stars":477,"topics":["agent","ai","ai-agent","ai-agents","ai-coding","dynamic-workflow","dynamic-workflows","llm","workflow","bun"],"license":"MIT","category":"ai-agents","readme_excerpt":"English 简体中文 deer-workflow An open-source Dynamic Workflow runtime for building observable, reusable Agent graphs. deer-workflow is a pilot project for DeerFlow 3.0 , also known as DeerWork . Index - Why Deer Workflow - How to use - Quick Start - Examples - Documentation - How to develop - Set up - Validate changes - Contribute - License Why Deer Workflow Deer Workflow is a code-first implementation of Graph Engineering : TypeScript defines the valid execution paths, while Coding Agents perform the semantic work inside each node. - Code is the plan. Control flow, phases, inputs, and failure handling live in reviewable TypeScript rather than an opaque Agent conversation. - Agents are replaceable. Codex is the default runtime; Claude Code and Pi are built in; and the public Agent interface remains vendor-neutral. - Execution is observable. Interactive runs provide a phase-aware TUI; automation can consume a stable JSONL event stream. How to use Quick Start Install Bun and sign in to Codex CLI, then install the released CLI: Describe the orchestration you want. Deer Workflow asks Codex to apply the bundled workflow-creator Skill and writes a runnable TypeScript module: Use --agent claude or --agent pi to generate with another installed Harness. Codex remains the default. Run the generated Workflow with its example input: Interactive terminals show phases and Markdown logs in a live TUI. For servers, CI, and process pipelines, add --print or -p to stream one JSON event per stdout","default_branch":null,"files":null,"tree":[],"storefront":"/r/deerwork-ai","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/deerwork-ai/deer-workflow/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}