v1.0.0 · MIT
Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.
v2.4.1 · Apache-2.0
45% cost reduction measured. The only Claude Code plugin built from CC source analysis — cache expiry prevention, SubTask auto-delegation, zero-cost context restoration, real-time dashboard. Max Plan + API pay-per-use.
v0.3.0 · MIT
Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.
— · Apache-2.0
vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!
v1.4.0 · MIT
Context-as-image compression proxy for LLMs: renders bulky context (system prompt, tool docs, history) as dense PNG pages with exact per-provider billing math (Anthropic/OpenAI/Gemini). Node and Cloudflare Workers. Part of the OmniRoute family.
v0.4.0 · MIT
DeepSeek Harness Token 余额监控插件:鲸鱼娘待机/扣费/复苏动画、峰谷计费、连续扣费飘字与会话费用统计。
v1.12.2 · MIT
DeepSeek Harness 用量与消耗插件(dsh-usage-plugin)—— 每次调用的 token 用量/缓存命中统计、峰谷计费、余额查询、CSV/JSON/PNG 导出,可经桌面端一键安装或命令行 dsh plugin add 安装。
v1.8.7 · MIT
Markdown and HTML renderer for Svelte 5 — built for rendering streaming AI agent output from Claude Code, ChatGPT, and agentic workflows. XSS-safe defaults, streaming-aware sanitization, token caching, TypeScript types, and Svelte 5 runes.
— · Apache-2.0
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
v0.8.0 · MIT
DeepSeek bills peak hours at 2x, and peak is 09-12 and 14-18 Beijing time. npx dsh-lean audit shows what your session paid and what it costs off-peak. DeepSeek 峰时按 2 倍计费,峰时正好是上班时间。
v1.0.0 · MIT
Energy & carbon metering for DeepSeek Harness: per-turn/per-request energy, cache carbon savings, electricity cost.
v0.1.9 · MIT
Enhanced, persistent web search plugin for DeepSeek Harness (multi-engine search, SQLite+LRU cache, platform backends, Playwright rendering)
— · MIT
Memory for Claude Code that survives the session boundary — install the plugin into any repo: a hot cache injected every session under three hook-enforced caps, per-session handoffs, audit-driven promotion into knowledge and rules, plus agent orchestration and QA layers. Zero deps.
v0.5.5 · Apache-2.0
本地优先、零普通运行时依赖的 DSH 项目记忆:有界会话冻结 Hot Memory、倒排 BM25 召回、生命周期与缓存命中优化、中英双语 GUI。 / Local-first DSH project memory with zero regular runtime dependencies: bounded session-frozen Hot Memory, inverted-index BM25 recall, lifecycle, cache-aware design, and a bilingual GUI.
v0.1.0 · MIT
Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.
v0.2.7 · MIT
MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness
— · MIT
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.