#Token-reduction

Showing 13 of 13 repositories tagged #token-reduction, ranked by stars

ModelTC
ModelTC
LightCompress

[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

Score
100
★ 731 ⑂ 78
Python
manojmallick
manojmallick
sigmap

97% token reduction for AI coding sessions — zero deps, 31 languages, MCP server

Score
100
★ 590 ⑂ 39
JavaScript
edouard-claude
edouard-claude
snip

CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.

Score
80
★ 361 ⑂ 38 +5/day
Go
fajarhide
fajarhide
omni

The Context OS for Autonomous AI Agents. Distill terminal noise into pure semantic signal, stop agent hallucinations, and cut token costs by up to 90%.

Score
60
★ 296 ⑂ 29 +3/day
Rust
brandondocusen
brandondocusen
CntxtPY

A discovery and compression tool for your Python codebase. Creates a knowledge graph for a LLM context window, efficiently outlining your project | Code structure visualization | LLM Context Window Efficiency | Static analysis for AI | Large Language Model tooling #LLM #AI #Python #CodeAnalysis #ContextWindow #DeveloperTools

Score
20
★ 115 ⑂ 13
Python
Huzaifa785
Huzaifa785
context-compressor

AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.

Score
17
★ 86 ⑂ 14 +1/day
Python
brandondocusen
brandondocusen
CntxtJS

A lightweight tool to optimize your Javascript / Typescript project for LLM context windows by using a knowledge graph | AI code understanding | LLM context enhancement | Code structure visualization | Static analysis for AI | Large Language Model tooling #LLM #AI #JavaScript #TypeScript #CodeAnalysis #ContextWindow #DeveloperTools

Score
0
★ 64 ⑂ 7
Python
ZON-Format
ZON-Format
zon-TS

ZON → 35-70% cheaper LLM prompts than JSON/TOON. Zero overhead.

Score
83
★ 49 ⑂ 4
TypeScript
Madhan230205
Madhan230205
token-reducer

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

Score
67
★ 38 ⑂ 3 +7/day
Python
SuppieRK
SuppieRK
ccp

Customizable CLI proxy for coding agents that cuts noisy terminal output while preserving command behavior

Score
40
★ 27 ⑂ 0 +1/day
Go
GabrielBarberini
GabrielBarberini
laconic

Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.

Score
33
★ 17 ⑂ 0
Python
jqbit
jqbit
TLDR

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

Score
50
★ 14 ⑂ 3 +1/day
JavaScript
mehmetdemirci
mehmetdemirci
comb-ai

Context-Optimized Memory Bank — Reduce AI token usage with structured documentation and cache-aware reading strategies

Score
0
★ 11 ⑂ 0
Shell
Related Topics
#llm#developer-tools#claude-code#cli#token-optimization#open-source#python#large-language-models#claude#cursor#gemini#codex

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly