token optimization

2 articles

← All topics

lean-ctx: local AI Value Gate with withdrawn benchmark

lean-ctxmcptoken-optimizationrustopen-source+2+3

yvgude/lean-ctx is an Apache-2.0 Rust binary that compresses reads, proxies requests, and tracks costs across 30+ AI coding agents — but its headline benchmark is withdrawn.

Headroom: open-source token compression for AI agents

headroomai-agentstoken-optimizationcontext-compressionmcp+10+11

Headroom v0.27.0 is an Apache-2.0 context-compression layer for AI agents: library, proxy, agent wrapper, and MCP server. Published savings reach 92% on code search and SRE debugging.