MCP servers and skills: search, filter by where they run, and compare.
MCP server that reduces LLM token usage by 80%+ through intelligent file caching, semantic diffs, and content-defined chunking.
PythonMIT★ 3Few starsNo key
🎮⚡ Game Shader Cache & Stutter Elimination Engine | Production-grade Claude Code skill & Python harness (v2.0.0) for graphics optimization. Features PSO pre-compilation, driver cache tuning, & crawl4
SkillMIT★ 5No key
Real-time, provenance-invalidated cognitive cache for AI agents and RAG — build understanding once, reuse it everywhere, keep it fresh.
PythonApache-2.0★ 12Needs a key
High-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.
MCPLink only★ 7
High-throughput semantic query cache and approximate deduplicator combining exact SHA-256 and cosine similarity threshold matching with LRU eviction.
MCPLink only★ 7
AI token waste elimination and intelligent cache layer for multi-provider agents
SkillMIT★ 1Few starsNo key
Use Redis over HTTP from serverless and edge runtimes with @upstash/redis, and add rate limiting with @upstash/ratelimit. Use when the user mentions Upstash Redis, needs Redis from a Next.js route han
OfficialSkillMIT★ 40k in collectionNo key
Self-hosted, multi-tenant CDN and digital asset management (DAM) platform built on Cloudflare Workers and Pages. Features real-time image optimization, signed URLs, Workers AI vision, semantic search,
SkillApache-2.0★ 5No key
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how
OfficialSkillApache-2.0★ 256 in collectionNo key
Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-
PythonMIT★ 60No key
ContextOps toolkit for production AI agents. Compile, govern, scan, visualize & optimize LLM context before every model call — token budgets, policy governance, PII/secret scanning, Context Bill of Ma
PythonMIT★ 2Few starsNo key
Guides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high', 'tail latency', 'single query too slow', 'how to make search faster', or '
OfficialSkillMIT★ 40k in collectionNo key
Redis Vector Library. The AI-native Python client for Redis.
OfficialPythonMIT★ 432No key
High-performance local SQLite FTS5-based tool output cache and MCP multiplexer for AI agents.
PythonMIT★ 7No key
Quota-limited xAI native X search over MCP, using local magpie OAuth for any calling model
Node.jsMIT★ 5No key
MCP server that uses Gemini's context caching as extended memory for AI assistants. Load GitHub repos, URLs, PDFs.
SkillMIT★ 14No key
Agent skill to search Adobe Fonts, manage Typekit web kits, and return embed tags with CSS font-family snippets.
SkillMIT★ 7No key
RAMen is a fast in-memory data store like Redis, but built for AI: drop-in Redis protocol, native vector search, semantic caching, and a built-in MCP server for agents. Single Go binary, BSD-3.
GoBSD-3-Clause★ 37No key
The server helps coding agents retrieve the smallest useful context for a task: repo facts, search hits, snippets, symbols, memory, and large-result references. It is read-only for source files. Gener
PythonMIT★ 1Few starsNo key
Lightweight, cost-free web search MCP for AI assistants.
GoMITFew starsNo key
MCP server: gives your AI agent the real sources, public API and KDoc of any Maven/Gradle-published Kotlin or Java library
SkillApache-2.0★ 13No key
Production-ready enterprise chatbot starter — RAG, declarative tool calling + MCP, layered memory, semantic caching, guardrails and evals. LangGraph · FastAPI · LiteLLM · pgvector · Redis · Langfuse.
PythonMIT★ 1Few starsNo key
MCP server for the Perseus Digital Library — giving AI models direct access to ancient Greek texts, CTS passages, and Scaife search.
PythonMIT★ 3Few starsNo key
Who stands behind it
