DeepSeek Harness Web 侧边栏 DeepSeek API 额度卡片 + 充值面板插件 | Sidebar quota card & recharge panel for DeepSeek Harness: real-time official /user/balance (60s auto-refresh), recharge tiers/payment methods matching the official site, official top-up QR, API key stays in Host. One-command install: bash install.sh
ArchGraph — an architecture-graph driven framework for Agentic Engineering. A long-term memory for coding agents, built on one ArchiMate 3.2 intent graph read/written through a single MCP interface.
Claude Pro/Max OAuth model provider for DeepSeek Harness with Google/Gmail login in Settings, auto-token refresh, live model discovery, and real-time quota tracking
OpenAI-compatible HTTP surface for DeepSeek Harness (dsh): POST /v1/chat/completions, POST /v1/responses, GET /v1/models over the harness webServer + llm runtime
DSH plugin: Codex-style computer use for Windows - read the screen, drive mouse & keyboard via SendInput; pairs with picturereader to close the look-act-verify loop.
Two-layer long-term memory for DeepSeek Harness (DSH): global + per-project markdown, live re-read, zero extra LLM cost, with a Settings panel. 给 DSH 的两层长期记忆。
Per-conversation skill catalog picker for DeepSeek Harness (dsh) — choose which skills are loaded into each conversation. Unselected skills are unavailable in that conversation.
Give DeepSeek (text-only) models **vision** in Claude Code and Codex by routing image files to any OpenAI-compatible vision endpoint (OpenRouter, SiliconFlow, DashScope, Ollama, llama.cpp, vLLM, LM Studio, …). Zero runtime dependencies, MIT licensed.
DeepSeek Harness plugin for local image / voice / music / SFX generation: the same character stays the same character across calls, degenerate output is refused rather than returned, and the GPU is untouched when idle. Hand the image half to any OpenAI-shaped API instead and its engine and 10.1 GiB of weights are never installed.