agentscope-ai/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.
Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()
Appears on
Quick read
Latest capture 2026-09-09 03:05
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
9 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Agent workspace 4
Claude Code 4
8 observed captures since 2026-05-23. Observed captures are shown by default.
Stars from first capture +3103
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
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.
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Kubernetes-native sandbox platform to run AI agents, coding assistants and harnesses.
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.