# #agent-runtime — MDRSS hashtag feed

> Public MDRSS cards tagged #agent-runtime.
> Canonical feed: https://mdrss.com/feeds/agent-runtime

## Cards (2)

### [What you get](https://mdrss.com/ai-agents/agent-frameworks/1367/1367.md)

DashClaw When your AI coding agent tries something destructive, DashClaw catches it before it runs and asks you first, even when you are not at the keyboard. What you get &nbsp;·&nbsp; What it stops &nbsp;·&nbsp; The loop &nbsp;·&nbsp; What it is not &nbsp;·&nbsp; Quick start &nbsp;·&nbsp; Connect an agent An agent tries a destructive tool call.

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [SwarmClaw](https://mdrss.com/ai-agents/agent-frameworks/1028/1028.md)

The self-hosted AI agent runtime and multi-agent framework for autonomous agents. Open-source agent swarms with durable agent memory, MCP tools, skills, delegation, schedules, and 23+ LLM providers — a practical Claude Code and LangChain alternative.

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1
