v0.3.8 · Apache-2.0
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
v0.12.1 · Apache-2.0
Secure, reproducible sandboxes for AI agent evaluation, training, and data synthesis.
v2.5.0 · MIT
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
v2.3.0 · MIT
DeepSeek Harness 的执行迷宫——看 Agent 真实怎么干活：迷宫时间轴 · 数据轨道 · 确定性执行分析 · 多会话对比 | The execution maze for DSH agents: maze timeline, per-step data tracks, deterministic execution analysis, multi-session comparison. Formerly dsh-trace-compare.
v0.1.5 · MIT
Say goodbye to copy-pasting and DSH Token anxiety. Let ChatGPT on the web connect directly to your local project, code on its own, and hand complex tasks to DSH for sustained execution.
— · MIT
Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Codex · GLM).