GitHub topic

token-optimization GitHub repositories

Explore 12 tracked GitHub repositories tagged token-optimization. Compare their recorded star activity and implementation languages, then follow related topics to find other projects.

Snapshot: 2026-10-28. The collection gained 263 stars since the previous daily snapshot.

Tracked repositories: 12
Total stars: 172,077
Stars gained · 7 days: +2,130
Stars gained · 30 days: +7,470

Compare star activity

Up to five projects on this page, ordered by daily star growth. Open a project for its description and recorded star history.

Swipe to compare all star periods →

Star activity for token-optimization repositories on this page
Repository	Total stars	Today	7 days	30 days
rtk-ai/rtk	84.8K	+133	+700	+2,954
headroomlabs-ai/headroom	78.0K	+114	+1,302	+4,085
ratel-ai/ratel	539	+4	+38	+38
ojuschugh1/sqz	669	+4	+12	+37
jgravelle/jcodemunch-mcp	2.8K	+3	+22	+96

Explore repositories

Showing 1–12 of 12 tracked repositories.

rtk-ai/rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

★ 84.8K+133 todayRust

llm claude-code

View ↗

headroomlabs-ai/headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

ratel-ai/ratel

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

★ 539+4 todayRust

llm mcp

View ↗

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

jgravelle/jcodemunch-mcp

Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client.

JayPokale/Chisle

Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

gglucass/headroom-desktop

Menu Bar App on MacOS and Windows that cuts Claude Code and Codex token costs by ~50%

★ 625+1 todayRust

llm ai

View ↗

nadimtuhin/claude-token-optimizer

Cut the tokens Claude Code loads at session start. CLI that sets up a small CLAUDE.md with on-demand docs, measures startup tokens, and keeps them small.

★ 633+1 todayJavaScript

llm claude-code

View ↗

Tura-AI/tura

Build agent that uses 80% less token and delivers better results.

★ 658+1 todayRust

llm mcp

View ↗

ooples/token-optimizer-mcp

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

★ 563+0 todayJavaScript

llm ai

View ↗

zdk/lowfat

lowfat - slim your command output. strips noise, saves tokens.

★ 582+0 todayRust

llm developer-tools

View ↗

Paritok-official/paritok-4b-v1

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

★ 1.4K+0 todayPython

ai ai-agents

View ↗

token-optimization GitHub repositories

Compare star activity

Explore repositories

rtk-ai/rtk

headroomlabs-ai/headroom

ratel-ai/ratel

ojuschugh1/sqz

jgravelle/jcodemunch-mcp

JayPokale/Chisle

gglucass/headroom-desktop

nadimtuhin/claude-token-optimizer

Tura-AI/tura

ooples/token-optimizer-mcp

zdk/lowfat

Paritok-official/paritok-4b-v1

Sign in to continue

Loading

Account settings

Delete listing?