deerwork-ai
Featured
deer-workflow
An open-source Dynamic Workflow runtime that combines deterministic TypeScript orchestration with replaceable Agent runtimes.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It introduces a novel human-in-the-loop paradigm for agent collaboration, combining visual FSM orchestration, Docker sandboxes, and support for multiple agent backends (Cursor, Claude Code, CodeBuddy, Trae) in a single self-hosted system.
Who it is for
- Developers building complex multi-agent pipelines
- Teams requiring human oversight in automated code generation
- Open-source enthusiasts interested in agent workflow frameworks
- AI/ML engineers experimenting with safe agent execution
Use cases
- Designing multi-step coding workflows with human approval gates
- Running sandboxed agent tasks with rollback on failure
- Integrating different agent backends under a unified orchestration layer
- Self-hosting a secure agent execution environment with audit trails
Strengths
- Visual FSM editor (Vue Flow) for intuitive workflow design
- Real Docker sandboxes isolate agent execution and enable safe git operations
- Multi-backend support allows switching between Cursor, Claude Code, etc. without changing infrastructure
- Open-source MIT license with full self-hosting capability and CI/CD badges indicating active testing
Considerations
- Requires a Linux host with Docker Compose and a large sandbox image download
- No sample pipeline on fresh install—users must build workflows from scratch
- Documentation may be incomplete; advanced configuration relies on separate README files
README quick start
Quick start
Description
Approving is an open-source, self-hostable platform for turning coding agents into visual, reviewable, and recoverable delivery workflows. Agents run in real Docker sandboxes, exchange structured artifacts, and pause for human Approve at critical nodes.
Related repositories
Similar projects matched by category, topics, and programming language.
makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.