A

AutoSwarm-Shadow-Adapter

AutoSwarm-Shadow-Adapter is a zero-modification human-machine collaboration adapter for OpenOPC's proxy DAG runtime.

🌍 OverseasFreeOpen sourceDev开源PythonFastAPIReact
Platforms: WebAPI
Region
Overseas
Pricing
Free
Open source
Yes
GitHub Stars
★ 2.7k
Source
GitHub
Added
2026-10-23
Last verified
2026-10-23

Overview

AutoSwarm-Shadow-Adapter is a high-concurrency Temporal Bridge for AutoSwarm. It allows AutoSwarm agent DAGs to pause when human approval or remote GPU execution is required, without causing engine timeouts or blocking parallel branches. The adapter achieves non-blocking task interception by intercepting task execution, storing tasks in an isolated SQLite WAL database, and immediately releasing execution threads. It also provides a secure React UI and REST API for human reviewers and remote workers. Additionally, it automatically packages ancestor deliverables, structured Markdown briefings, and uploads file artifacts for downstream context inheritance.

Key features

  • ▪Non-blocking task interception
  • ▪Provides secure React UI and REST API
  • ▪Automatically packages context information
  • ▪Instant recovery of AutoSwarm state machine

Use cases

Automating multiple workloadsEnhancing understaffed or overloaded rolesEnterprise-level regulatory complianceRunning fully automated business processes

Pros

  • +Supports multi-user access control
  • +Persistent storage in SQLite WAL DB
  • +Supports file attachments
  • +Built-in iterative retry loop

Limitations / notes

  • -Requires internet connectivity
  • -Higher learning curve

Who it's for

DevelopersProject managersEnterprise teamsFreelancers

This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.

FAQ

Is it free?

Yes, the project is open-source and free.

Do I need scientific internet access?

Not required, but a stable network connection is recommended.

Does it support Chinese?

Documentation is primarily in English, but code and interface may support multiple languages.

Can it be used commercially?

Yes, the project uses the MIT license.

Similar agents

Something wrong? Let us know on the About page and we'll fix it.