Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
agentscope-runtime
A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.
807stars
158forks
Python
a2aagentagentscopeagnodeploymentdockerkuberneteslanggraphmcpmodelstudioruntimesandbox
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
A production-ready framework for running agent applications with secure tool sandboxing and streaming APIs, now archived in favor of AgentScope 2.0.
Use this when
- Need secure execution of untrusted Python/shell/GUI tools in isolation
- Want to expose an agent as a streaming API for real-time responses
- Building multi-agent systems with sandboxed tool access
- Running agent apps locally or in Kubernetes with elastic scaling
- Debugging agent behavior with full-stack observability (logs/traces)
Don't use when
- Building new projects (use AgentScope 2.0 instead)
- Need non-sandboxed tool execution
- Want a GUI-based agent builder (use AgentScope 2.0 WebUI)
Capabilities
- Secure sandboxing for Python/shell/GUI/browser/filesystem tools
- Agent-as-a-Service APIs with streaming responses
- Local/Kubernetes/serverless deployment with elastic scaling
- Full-stack observability via logs and traces
- Async sandbox implementations for concurrent tool execution
- A2A and MCP protocol compatibility for agent interoperability
InstallMCPRun via uvx (Python)
Universal installANY TOOL
$ npx skillcity@latest agentscope-ai/agentscope-runtimeAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
uvx agentscope-runtime
MCP Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"agentscope-runtime": {
"command": "uvx",
"args": [
"agentscope-runtime"
]
}
}
}Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
agentscope-runtime — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt