messkan / prompt-cache
Cut LLM costs by up to 80% and unlock sub-millisecond responses with intelligent semantic caching.A drop-in, provider-agnostic LLM proxy written in Go with sub-millisecond response
Why this job: topics: rag, vector-database, semantic-search
What it does
PromptCache is a lightweight, self-hosted semantic cache for GenAI workloads. It sits between your application and an LLM provider, detects similar prompts, and can return a previously cached response instead of making another model call.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 427
- +1 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.4.0
- Released 6 months ago
- Built with
- Go
- 93% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 43% closed
- 4 still open
- Pull requests
- 9 merged
- 2 waiting
- Releases
- 4
- 4 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
More: languages, topics and project record
Languages
- Go 93%
- Shell 5%
- Makefile 1%
- Dockerfile 1%
Topics
- ai
- badgerdb
- cache
- claude
- cost-optimization
- go
- langchain
- llm
- middleware
- mistral
- openai
- performance
Project record
- JobRAG and search
- StatusListed
- Commits47
- Forks43
- Watching1
- Stars in 28 days+4
- CreatedNov 22, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026