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.

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.

vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!

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.

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

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。

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.

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.

Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.

MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.