token-optimization repositories
Trending repositories tagged token-optimization, ranked by trending score. Updated daily.
-
1
microsoft/TokenEconomizer
Experience-Driven Black-Box Cost Control for Coding Agents
GitHub · Python · 7,941 stars · 559 forks · +134 stars in 24 hours · Trending score 4.51
-
2
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
GitHub · Rust · 87,485 stars · 5,616 forks · +218 stars in 24 hours · Trending score 4.48
-
3
AxiomCodeAI/axiomcodegraph
Turn any codebase into a knowledge graph grounded in formal methods. Your AI agents get exact answers for any code-related task, ensure correctness, and optimize time and token usage.
GitHub · TypeScript · 769 stars · 97 forks · +293 stars in 24 hours · Trending score 4.11
-
4
snchimata/tokenfold
Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party calls.
GitHub · Rust · 409 stars · 31 forks · +277 stars in 24 hours · Trending score 4.08
-
5
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.
GitHub · Python · 80,421 stars · 6,297 forks · +95 stars in 24 hours · Trending score 4.01
-
6
vibe-any/dsh-plugin-save-token
A DeepSeek Harness (dsh) dynamic plugin that cuts token cost without cutting model intelligence
GitHub · JavaScript · 91 stars · 6 forks · +59 stars in 24 hours · Trending score 3.04
-
7
INK-Q/agy-fast
Non-invasive MCP accelerator plugin for Google Antigravity (CLI/Desktop/IDE): cuts LLM turns (-34%), token quota (-31%), and upload traffic (-40%) without affecting native UI or diffs.
GitHub · TypeScript · 419 stars · 30 forks · +215 stars in 24 hours · Trending score 2.61
-
8
localixai/tokendoctor
tokendoctor: the same Claude Code for up to 38% less. Replays your own past sessions to show what each change would have saved, then changes only what you pick
GitHub · TypeScript · 174 stars · 12 forks · +7 stars in 24 hours · Trending score 2.20
-
9
ARahim3/cachebeat
A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying full price.
GitHub · Shell · 90 stars · 11 forks · +19 stars in 24 hours · Trending score 2.19
-
10
blendbunjaku/optimaizr
Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex, opencode and your own API calls.
GitHub · TypeScript · 254 stars · 10 forks · +18 stars in 24 hours · Trending score 2.05
-
11
Green-PT/honey-for-devs
Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.
GitHub · JavaScript · 360 stars · 22 forks · +18 stars in 24 hours · Trending score 1.92
-
12
agentic-os-org/ANOLISA
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
GitHub · Rust · 688 stars · 201 forks · +5 stars in 24 hours · Trending score 1.80
-
13
archid21/rightsize
Make every Claude token count. rightsize picks the right model and effort for each prompt, while keeping cache and context costs low. It learns how you work and gets better over time.
GitHub · TypeScript · 48 stars · 13 forks · +3 stars in 24 hours · Trending score 1.76
-
14
redhat-et/ripwire
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss published. Paddle out with a map.
GitHub · C++ · 2,560 stars · 180 forks · +5 stars in 24 hours · Trending score 1.73
-
15
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.
GitHub · JavaScript · 1,251 stars · 79 forks · 0 stars in 24 hours · Trending score 1.73
-
16
chipfighter/context-attachment-manager
Keep long, image-heavy Codex and Claude Code chats fast: earlier images become ID placeholders the model fetches back on demand, even after compaction. Local, cache-friendly, MIT.
GitHub · TypeScript · 814 stars · 76 forks · +7 stars in 24 hours · Trending score 1.69
-
17
pleasedodisturb/awesome-llm-token-optimization
A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.
GitHub · Shell · 126 stars · 41 forks · +7 stars in 24 hours · Trending score 1.56
-
18
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.
GitHub · Go · 485 stars · 50 forks · +7 stars in 24 hours · Trending score 1.51
-
19
KbWen/agentic-os
Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.
GitHub · Python · 242 stars · 52 forks · +7 stars in 24 hours · Trending score 1.49
-
20
daoif/tokless
npx tokless install — Zero-dependency AST code skeleton, blind-read guard & token bill auditor for AI coding agents (Antigravity, Claude Code, Codex & more)
GitHub · JavaScript · 25 stars · 3 forks · +14 stars in 24 hours · Trending score 1.42
-
21
ppgranger/token-saver
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.
GitHub · Python · 167 stars · 17 forks · +5 stars in 24 hours · Trending score 1.36
-
22
UditAkhourii/cdaf
CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skill, reproducible benchmark.
GitHub · Python · 226 stars · 12 forks · 0 stars in 24 hours · Trending score 1.21
-
23
alexgreensh/outsourcerer
Make your AI agents work as a team. You keep working in 1 session while it orchestrates models via your other subscriptions, local models and more. Run a Software Factory: long plans, proven steps, safe merges. Carries your setup, tracks every cost.
GitHub · Shell · 201 stars · 18 forks · +2 stars in 24 hours · Trending score 1.20
-
24
Zoria-Lind/dsh-token-optimizer
Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.
GitHub · JavaScript · 25 stars · 1 forks · +5 stars in 24 hours · Trending score 1.18