Context management
LMCache
KV-cache reuse layer (context infrastructure, not agent memory)
Open sourceself-hostable
★ 12,326 on GitHub · +3 today · last commit Nov 10, 2026
At a glance
- Business model
- Open source
- License
- Apache-2.0
- Self-hosting
- Yes, can be self-hosted
- Access
- vLLM integration
- Architecture
- KV-cache
GitHub activity
This product has a public repository, so we read it nightly from the GitHub API. Stars measure developer attention, not quality or market share.
“LMCache: Supercharge Your LLM with the Fastest KV Cache Layer” (repository description)
- Stars
- 12,326
- Change since last reading
- +3
- Forks
- 2,152
- Open issues
- 966
- Last commit
- Nov 10, 2026 (0 days ago)
- License (GitHub)
- Apache-2.0
Links and sources
- Official sitelmcache.ai
- GitHub repositorygithub.com/LMCache/LMCache