LMCache/LMCache — 8,660 Stars
Supercharge Your LLM with the Fastest KV Cache Layer
Watch Episode
About This Repo#
LMCache/LMCache — 8,660 ⭐
Supercharge Your LLM with the Fastest KV Cache Layer - LMCache/LMCache
Narration#
Your LLM is wasting compute on every request. LMCache is the fastest KV cache layer for LLM inference — storing key-value caches across GPU memory, SSDs, and remote backends to slash time-to-first-token and boost throughput. Engine-independent, vendor-neutral, and already integrated with vLLM and SGLang. Eight thousand six hundred stars on GitHub. Check out LMCache today.
Watch#
DeusData/codebase-memory-mcp — 9,534 Stars
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms...
runtypelabs/persona — 16 Stars
Create agentic front-end experiences for the web in VanillaJS™️. Lightweight, extensible, and WebMCP-native.
Kong/insomnia — 39,389 Stars
The open-source, cross-platform API client for GraphQL, REST, WebSockets, SSE and gRPC. With Cloud, Local and Git storage.