sandbaseai/管理代理是从[[T0]导入的代理技能候选人。
概览
sandbaseai/管理代理是从[[T0]导入的代理技能候选人。
概述（AI 翻译）
英文 |中文
AI可读项目元数据：llms.txt ·安装指南
为AI代理提供本地优先的运行时。会话、沙盒工具、内存， 凭证、审计追踪和内置控制台——全部运行在你的 机器或你自己的基础设施。
为什么
代理SDK负责模型循环。生产代理需要更多：持久化
会话、工具治理、沙盒边界、凭证处理、内存，
可审计性，以及供人类检查发生情况的用户界面。managed-agents
是运行时层——而不是可视化的工作流程构建器，也不是另一个模型SDK。
| 需求 | 安全带提供的 |
|---|---|
| 安全运行生成代码 | 本地、Docker、Kubernetes 和自架工作者沙箱 |
| 检查长期运行的代理 | 持久会话、可恢复事件流、审计和重放 |
| 控制工具访问 | MCP 工具集、凭证库、权限策略和审批 |
| 操作任何型号 | OpenAI、Anthropic、MiniMax 以及兼容 OpenAI 的提供商，包括 DeepSeek V4 |
| 基础设施保有 | 本地优先SQLite和文件存储，无需托管控制平面 |
特色
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
SandBase Harness
AI-readable project metadata: llms.txt · installation guide
A local-first runtime for AI agents. Sessions, sandboxed tools, memory, credentials, audit trails, and a built-in Console — all running on your machine or in your own infrastructure.
Why
Agent SDKs handle the model loop. Production agents need more: persistent
sessions, tool governance, sandbox boundaries, credential handling, memory,
auditability, and a UI for humans to inspect what happened. managed-agents
is that runtime layer — not a visual workflow builder and not another model SDK.
| Need | What Harness provides |
|---|---|
| Run generated code safely | Local, Docker, Kubernetes, and self-hosted worker sandboxes |
| Inspect long-running agents | Persistent sessions, resumable event streams, audit, and replay |
| Control tool access | MCP toolsets, credential vaults, permission policies, and approvals |
| Operate any model | OpenAI, Anthropic, MiniMax, and OpenAI-compatible providers, including DeepSeek V4 |
| Keep infrastructure yours | Local-first SQLite and file storage with no required hosted control plane |
Features
- Claude Managed Agents-style
/v1API and local Console - SQLite metadata by default for agents, sessions, environments, credential vaults, memory stores, files, skills, and API keys — local file/skill bytes in the workspace state directory
- Resumable Server-Sent Events for session replay and debugging
- One active model provider boundary configured through Settings V2
- Sandbox backends: local process, Docker (per-session containers), Kubernetes (kubectl exec/cp), self-hosted worker queue
- MCP toolsets, permission policies, built-in tools, and skill packages
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add sandbaseai/managed-agents