managed-agents
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
102 results
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
DSH inline visualization plugin: a visualize tool + bundled skill let the model render interactive HTML fragments as sandboxed cards in the conversation (Codex /visualize semantics).
Sandbox-first automatic permission policy for DeepSeek Harness
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
DeepSeek Harness plugin: installs the 'minimal-gitbash' agent preset — the Windows variant of the shipped minimal preset that routes the bash tool through Git for Windows bash (MSYS), with automatic shell discovery and sandbox-aware gating.
Declarative Claude Code-style permission rules plus a Codex-style process-level network policy for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), workspace-path, and network-target (domain/ip/port/scheme) matching on the tools/pre-execute waterfall, a built-in local HTTP/CONNECT proxy governing shell subprocess traffic, three network modes mapped onto the official sandbox presets, full session-log audit, HMR rule reload, and a settings page with a rule editor, block counters, and recent interception lists.
Session-aware sandbox escalation compatibility plugin for DeepSeek Harness
dsh-passwords: a server-grade gateway that turns DeepSeek Harness into a multi-tenant platform — remote access + automatic HTTPS, per-subuser permissions & quotas, sandbox enforcement, first-run setup, SQLite auth with at-rest encryption, rate-limit and audit log (bilingual zh/en UI)
Native ECharts and Mermaid visualization canvas for DeepSeek Harness conversations, with declarative pure-JSON payloads and a sandboxed HTML escape hatch.
Normalize redundant sandbox requests and malformed justifications in DeepSeek Harness tools
Visualizer plugin for DeepSeek Harness: the `visualizer` tool streams a self-contained HTML document into the chat as it is written, live-previewed by a sandboxed inline frame. One package ships both halves: the model-facing tool and the Web GUI preview card.
Use Git for Windows Bash as the default DSH shell with restricted-mode support
Windows-first bash tools for DeepSeek Harness: git_bash (Git Bash) and wsl_bash (WSL2) model tools with bwrap sandbox, approval mode, terminal-style UI cards, and background-job support
Tensorlake sandbox execution providers for DeepSeek Harness
Sprites remote development environments for DeepSeek Harness through Cordis and MCP.
Net Access permission preset for DeepSeek Harness (Windows): HTTPS works inside the sandbox while file writes stay confined like workspace-write.
DSH sandbox extension: configurable trusted writable roots outside the workspace, for both sandboxed CLI commands and the write/edit tools. 为 DSH 默认沙箱增加可配置的「沙箱授权目录」,允许工作区外的受信修改。
Fail-closed microsandbox microVM provider and model-facing guest tools
DeepSeek Harness 的 Docker 容器沙箱部署级插件(与 dsh-plugin-vm-sandbox 全能力对齐):39 个 docker_* 模型工具、快照/回滚、文件传输、端口转发、后台任务、审计、共享/配额/回收、网络策略、多容器并行执行与华丽原生 UI。无需 OrbStack,Linux/Windows/macOS 均可使用。
让DSH使用你的魔法:把沙箱里的 agent 接上你本地的 HTTP 代理,一条命令抓取被墙的网站、文档和 API(net_fetch 代理隧道抓取 + net_proxy_status 代理诊断)。Give DSH your magic: plug sandboxed agents into your local HTTP proxy and fetch blocked sites, docs and APIs in one shot (net_fetch + net_proxy_status).
Run the DeepSeek Harness agent's filesystem, bash and PTY terminals inside a Docker container, so execution state survives a harness restart.
DSH compatibility plugin that treats redundant non-escalating sandbox permission fields as a no-op
dsh-yolo-mode —— DeepSeek Harness 双面包插件:当会话处于可写沙箱模式且审批策略为 ask 时,用大模型自动裁决沙箱升权申请,支持内置预设与自定义权限层级,并提供宿主 settings + 自发布设置桥(/yolo-mode)与 Web 客户端 UI。
Self-evolving plugin for DeepSeek Harness: observes agent behavior, proposes improvements to its own skills/policies via LLM, validates them in a sandboxed trial agent, and applies versioned mutations with rollback.