Stop AI agents from doing things you didn't ask for.

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

A Claude Code mod that puts a live agent dashboard in your terminal: context and cost, advisor timeline, every permission check, subagent cards and swimlanes.

Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

Know when your DeepSeek Harness tasks need you. Local alerts, quiet notifications, and a task inbox.

Read-only Agent work-path observer for DeepSeek Harness

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.

Audit trail and traceability for AI agents. See what every coding agent did, block risky calls, ask a human for approval, and prove it with signed trust checks.