Open-source sandboxes for AI agents, untrusted code execution, and durable services.

DeepSeek Flow — Markdown-first visual workflow plugin for DeepSeek Harness with executable Boolean gate semantics, two-way canvas sync, and AI review/optimization.

Memory for coding agents — Claude Code, Codex, Cursor and 17 others. Indexes the sessions they already wrote to disk, including months from before you installed it, and recalls them in any of them. No LLM, no embeddings, one local Go binary.

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

Deepseek Harness 综合智能办事平台 — 独立政务风 WebUI（默认端口 3081），通过宿主 apiProxy 1:1 对接 dsh 的会话/模型/权限/统计等全部 Agent 能力

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

Deterministic Runtime Execution Governance & Security Circuit-Breaker for DSH & Multi-Agent Workstations

Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance

Expose DeepSeek Harness agent capabilities as an MCP server, so an external MCP client (e.g. Hermes) can drive Harness to execute coding tasks. Hermes = brain, Harness = arms.

DSH plugin: run every agent shell command through Git for Windows bash on Windows instead of PowerShell. Replaces the pwsh executor with a Git Bash ctx.shell provider and materializes Git Bash variants of the standard/minimal/code/cordis agent presets int

Unified capability menu for DeepSeek Harness: manage exposure level (context footprint) and execution mode of MCP tools & skills via Exposed/Progressive/Blocked tiers.

🐳 The Everything-Plugin Quant OS — AI-native & DSH-native: 46 tools, 6 pluggable domains (data/alpha/ML/risk/execution), one end-to-end PDAT→PET pipeline. Methods open, secrets internal.