MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Radix tree KV cache prefix caching manager for fast decoding (SGLang style)
SkillLink only★ 8
Multi-turn conversational AI harness with MCP tool integration, built for LLMs with cache-hit mechanisms (e.g. DeepSeek). A dual-path router keeps the main model's prompt prefix stable to maximize cac
MCPLink only★ 2Few stars
RadixAttention prefix tree cache high-throughput serving runtime (vLLM/SGLang style)
SkillLink only★ 8
In-memory LRU cache with per-key TTL expiration, deterministic eviction, and hit/miss/stale telemetry for LLMs
MCPLink only★ 7
这个 skill 用来排查 Claude Code 的 prompt-cache / 1h cache 断点问题。适合发给下一个 AI：让它按固定证据链检查，而不是凭 `cache_creation_input_tokens` 猜
SkillLink only★ 4Few stars
High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation
MCPLink only★ 7
High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation
SkillLink only★ 7
MCP server #30 for caching: HTTP cache header analyzer, cache key generator, LRU/LFU/TTL simulation, CDN detector, browser cache analyzer Install: npx @rog0x/mcp-cache-tools
MCPLink onlyFew stars
High-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.
MCPLink only★ 7
Semantic prompt cache deduplicator calculating Jaccard token overlap to prevent redundant LLM cost
SkillLink only★ 8
High-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.
MCPLink only★ 7
Semantic prompt cache deduplicator calculating Jaccard token overlap to prevent redundant LLM cost
SkillLink only★ 7
PagedAttention chunked prefill KV cache & GPU memory allocator (vLLM)
SkillLink only★ 8
High-throughput agent artifact cache & snapshot checkpointer (BearDrive style)
SkillLink only★ 8
Vercel KV Redis semantic query cache compiler
SkillLink only★ 9
Memory Cache Server for use with supported MCP API Clients.
MCPLink onlyFew stars
Caching MCP proxy with event-based invalidation for code-index
MCPLink only★ 3Few stars
High-performance in-memory Trie and multi-keyword search engine for prompt routing and entity extraction
MCPLink only★ 7
提升 DeepSeek-V4 (Pro/Flash) 模型 Prompt 缓存命中率的 Claude Code Skill
SkillLink only★ 4Few stars
Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.
SkillLink only★ 116
Who stands behind it
