Cluster 638348

10 repos

Python · 7

Rust · 2

TypeScript · 1

token-optimization ·3,594

context-engineering ·3,473

claude-code ·2,971

context-window ·2,601

codex ·2,430

claude-plugin ·2,309

agentskills ·2,309

cost-management ·2,309

claude-code-skill ·2,309

cost-optimization ·2,309

Related clusters

Cluster 63401322 Cluster 63383227 LLM-powered AI agents and assistants35 Cluster 63399940 Cluster 63400726 Cluster 63401225

ppgranger/token-saver

Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output…

Python

151

168 commits

iKislay/copium

Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for…

Python

435 commits

alexgreensh/token-optimizer

Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

Python

2,309

1,002 commits

DFKHelper/token-goat

Token burn reducer and focus keeper for Claude Code, Codex, Copilot, Gemini CLI, and more: surgical…

TypeScript

121

1,179 commits

fajarhide/omni

Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a…

Rust

370

1,071 commits

alibaba/anolisa

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime,…

Rust

622

2,645 commits

haxo98098/slicegrep

grep that returns ranked, token-budgeted code slices — built for LLMs and coding agents. CLI +…

Python

31 commits

KrismithReddy12/headroom

No description

Python

2,362 commits

SamirSengupta/tokenash

Local-first context compression for LLM apps. 50–90% fewer tokens, same answers.

Python

3 commits

Mibayy/token-savior

MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and…

Python

1,155

219 commits