inferencache
Multi-tier semantic caching for LLM APIs. Stop paying for the same prompt twice.
pip install "inferencache[embed,serve]"
export ANTHROPIC_API_KEY=sk-ant-...
inferencache serve
# landing: http://localhost:8080/
# dashboard: http://localhost:8080/dashboard/
# proxy: http://localhost:8080/v1/messages
Point Cursor or Claude Code at http://localhost:8080 — no code changes required.
See CONTRIBUTING.md for development setup.
1 maintainer
Metadata
1 maintainer
Release files for inferencache 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| inferencache-0.1.0.tar.gz | 547.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| inferencache-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.1 MB
Release files / inferencache-0.1.0.tar.gz
| Download URL | inferencache-0.1.0.tar.gz |
|---|---|
| Size | 547.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fcca912faa74e5da0a28baa2256e04d193300588944b745889fc28ef398ac4a0
|
|
BLAKE2b-256 checksum How to use checksums |
a40db9b1654e07026f6a9e06671b7a8415785924529e71704ae1fa3099157fe4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
Release files / inferencache-0.1.0-py3-none-any.whl
| Download URL | inferencache-0.1.0-py3-none-any.whl |
|---|---|
| Size | 561.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e25b6310b3298f684f7a644cabd32b32a06de7a3eed23812f9b6aaddd8c55b48
|
|
BLAKE2b-256 checksum How to use checksums |
578dd2ca422176a2d2c3b76d7782441d6b341bdbaf5777d93a8206711542a6bf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
