Windows desktop UI context picker for AI agents: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, local OCR, and user-approved MCP output. Works with OpenAI Codex, DeepSeek Harness, and other MCP-compatible clients.
Minimal-stable DeepSeek Harness preset with Linux-shaped persistent Bash, native Windows support, on-demand capability routing, and a low-cost V4 Flash router for DeepSeek V4 Pro coding workflows.
DeepSeek Harness plugin: one click binds each conversation to its own isolated git worktree + branch, so parallel agents work on one repo without interference — every project's worktrees auto-managed in the sidebar workspace tree, backed by 9 git tools.
Open-source MCP vision server that gives text-only LLMs and AI agents image understanding, OCR, visual analysis, UI inspection, and multimodal capabilities.
Project-level change routing and reuse governance for AI coding agents. Helps Codex and Claude Code find the right capability boundary, avoid duplicate implementations, respect write constraints, and calibrate routing decisions for large full-stack repositories.
Reasoning layer for the official DeepSeek Harness: every request stays on native max effort, with isolated Flash/Vision/Pro depth controls, stability axes and reasoning toolboxes built above it. Delivered build only; commercial use open, reverse/modify/extract closed.
