— · MIT
Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it. Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 13 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
v0.4.1 · MIT
Compact DeepSeek Harness desktop host with a native SwiftUI iPhone Remote source preview.
v0.1.0 · Apache-2.0
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
— · MIT
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
v2.8.8 · MIT
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
v0.4.0 · MIT
Hash-anchored read/edit/undo_last_edit tools for DeepSeek Harness (dsh). Every line gets a unique 3-char hash (A-Za-z0-9) that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.
v0.1.6 · MIT
Reach the DeepSeek Harness on your dev machine from your phone — across networks, through no server at all (iroh P2P)
v0.1.0-rc.6 · MIT
Configurable DSH web-surface plugin: wallpaper & frosted-glass themes, accent colors, custom keyboard shortcuts, app-usage panel, history strip, message Markdown — zero shell edits.
v0.6.0 · MIT
Update copilot for DeepSeek Harness: tracks the DSH core, bundled packages, and every installed plugin across npm and git, merged package-centric over all profiles, with one-click updates — the update command is identical for every profile. · DSH 更新助手:追踪
v0.4.1 · Apache-2.0
Synchronize and Orchestrate agents from CLI to GUI, across desktop to phone.
— · MIT
Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota resets..
— · MIT
Know if your agent skill actually works. A lightweight evaluation harness that tracks a success rate across Claude Code, Codex, Pi, and Hermes.
v1.3.0 · MIT
Sync your local skills across 41+ AI coding agents with a single command.
— · MIT
Obsidian 零成本同步:iPhone ↔ Mac,GitHub 自动备份。本地优先 + 长期积累。|Local First. Zero-cost Obsidian sync across iPhone, Mac & GitHub. Let knowledge grow over time.