Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Rustojuschugh1/sqz

sqz

Compress LLM context to save tokens and reduce costs

75.7/100
621Forks: 43
View on GitHubHomepage →
Loading report...

Similar Projects

nasiko

77

Developer Control Plane for your AI Agents

Rust6.6K

jcode

86

The most RAM efficient harness

Rust19.5K

tensorzero

75

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

Rust11.7K

helix-db

89

HelixDB is an OLTP graph database with native vector and full-text search built in Rust on Object Storage.

Rust5.9K
Back to List