Open-source macOS record-and-replay workflow recorder for computer use agents. Captures mouse, keyboard, and UI events as structured traces so agents can learn, replay, and automate real desktop tasks.

Unified DSH checkpoints: session + workspace + config three-state snapshots with one-shot rollback — /checkpoint and /rewind commands, a checkpoint tool, automatic interval snapshots, a Settings page timeline with pairwise diffs, and seed-replay session r

GenUI for DeepSeek Harness: interactive UI components rendered inline in assistant replies via the dsh-ui fence — layout, charts, plots, forms, quizzes, mermaid, 3D scenes, and an action event loop back to the model. Ships the fence-teaching host plugin, the browser renderer (client half), and the genui skill.

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

Pixel-perfect clones of any webpage. Paste a URL, get a measured Vite + React replica.

Use ChatGPT Codex, Claude, Grok, Antigravity, Kimi, GLM, Cursor, Kiro, Copilot, Qwen, ERNIE, Spark, JetBrains, Perplexity, Replit, and Cody subscriptions as DeepSeek Harness LLM providers via OAuth.

DeepSeek Harness coding-subscription OAuth: SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code, Claude Code. Fixes AUTH API key is invalid, INVALID_REPLAY_STATE, grok-4.6 xhigh, Kimi Bearer vs x-api-key.

A library for patching, replacing and decorating DeepSeek Harness plugins during runtime

Text-to-speech for DeepSeek Harness: speak agent replies in the Web UI with a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak).

GenUI for DeepSeek Harness: interactive charts, forms, calculators, dashboards, and mini apps rendered inline in assistant replies, with actions that flow back to the model.

Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-t

Evidence-backed UI delivery for coding agents working on existing Web products: declared criteria, criterion-bound artifacts, findings linked to declarations, and repair guidance. Evaluator review does not replace human semantic approval.

Manage DeepSeek Harness system-prompt sections from the Web GUI: enable, edit, and subscribe markdown prompt entries, switch named presets from the composer, feed them machine facts as {{variables}}, replace the instruction DSH sends when it compacts the