#Token-optimization

Showing 58 of 58 repositories tagged #token-optimization, ranked by stars

rtk-ai
rtk-ai
rtk

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

Score
100
★ 69.8k ⑂ 4.3k +125/day
Rust
headroomlabs-ai
headroomlabs-ai
headroom

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

Score
100
★ 58.3k ⑂ 4.3k +65/day
Python
yvgude
yvgude
lean-ctx

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.

Score
50
★ 3.2k ⑂ 296
Rust
cytostack
cytostack
openwolf

Sharper context. Fewer tokens. Open-source middleware for Claude Code.

Score
97
★ 2.1k ⑂ 184 +11/day
TypeScript
jgravelle
jgravelle
jcodemunch-mcp

Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.

Score
100
★ 2.0k ⑂ 301 +1/day
Python
alexgreensh
alexgreensh
token-optimizer

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

Score
0
★ 1.6k ⑂ 127 +48/day
Python
zdk
zdk
lowfat

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

Score
0
★ 554 ⑂ 18
Rust
nadimtuhin
nadimtuhin
claude-token-optimizer

Optimize token usage for Claude API calls

Score
94
★ 511 ⑂ 61
JavaScript
GMaN1911
GMaN1911
claude-cognitive

Working memory for Claude Code - persistent context and multi-instance coordination

Score
68
★ 451 ⑂ 40 +1/day
Python
ooples
ooples
token-optimizer-mcp

Intelligent token optimization for Claude Code - achieving 95%+ token reduction through caching, compression, and smart tool intelligence

Score
100
★ 431 ⑂ 43
TypeScript
gglucass
gglucass
headroom-desktop

Unlock 2x more Claude Code and Codex usage

Score
88
★ 428 ⑂ 40 +4/day
Rust
juyterman1000
juyterman1000
entroly

Cut your Claude / OpenAI / Gemini bill 70–95% on AI coding. Local proxy that compresses context, keeps provider caches hot, and verifies LLM output ($0 hallucination guard). Drop-in for Cursor, Claude Code, Codex, Aider + 34 more and custom providers — 30s, no code changes

Score
91
★ 419 ⑂ 66
Python
IyadhKhalfallah
IyadhKhalfallah
clauditor

Stop Claude Code from burning through your quota in 20 minutes. Auto-rotates oversized sessions and preserves context.

Score
79
★ 408 ⑂ 40 +2/day
TypeScript
ojuschugh1
ojuschugh1
sqz

Compress LLM context to save tokens and reduce costs

Score
85
★ 395 ⑂ 27 +10/day
Rust
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
82
★ 361 ⑂ 38 +5/day
Go
Lap-Platform
Lap-Platform
LAP

Your agents are guessing at APIs. Give them the actual Agent-Native spec. 1500+ API's Ready To-Use skills, Compile any API spec into a lean, agent-native format. 10× smaller. OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman.

Score
74
★ 339 ⑂ 31
Python
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
76
★ 296 ⑂ 29 +3/day
Rust
oxygen-fragment
oxygen-fragment
claude-modular

Production-ready modular Claude Code framework with 30+ commands, token optimization, and MCP server integration. Achieves 2-10x productivity gains through systematic command organization and hierarchical configuration.

Score
9
★ 286 ⑂ 43 +1/day
skibidiskib
skibidiskib
ai-codex

Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation

Score
71
★ 271 ⑂ 23
TypeScript
mpecan
mpecan
tokf

Config-driven CLI tool that compresses command output before it reaches an LLM context

Score
65
★ 189 ⑂ 20 +1/day
Rust
ratel-ai
ratel-ai
ratel

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

Score
93
★ 181 ⑂ 9 +9/day
TypeScript
fkiene
fkiene
llmtrim

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

Score
62
★ 156 ⑂ 7 +8/day
Rust
Green-PT
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.

Score
59
★ 146 ⑂ 8 +13/day
JavaScript
Alegau03
Alegau03
CTX

CTX - Context Runtime Engine for Coding Agents

Score
44
★ 138 ⑂ 13 +1/day
Rust
NickCirv
NickCirv
engram

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via npm + OpenVSX + Anthropic plugin directory. 89% measured token reduction. Local SQLite, zero cloud, Apache 2.0.

Score
53
★ 137 ⑂ 14
TypeScript
johunsang
johunsang
semble_rs

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.

Score
56
★ 136 ⑂ 21
Rust
flightlesstux
flightlesstux
prompt-caching

Automatic prompt caching for Claude Code. Cuts token costs by up to 90% on repeated file reads, bug fix sessions, and long coding conversations - zero config.

Score
41
★ 129 ⑂ 5 +2/day
TypeScript
borhen68
borhen68
TokenTamer

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.

Score
50
★ 123 ⑂ 20 +1/day
Python
0xhimanshu
0xhimanshu
governor

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

Score
38
★ 123 ⑂ 6
Python
reshaprio
reshaprio
reshapr

The open source, no-code MCP Server for AI-Native API Access

Score
47
★ 107 ⑂ 20
Java
HoangP8
HoangP8
tokless

A unified CLI to install and update token-saving plugins — RTK, Caveman, CodeGraph, and Context-Mode — for Claude Code, OpenCode, Codex, and Antigravity. Minimal setup. Any OS.

Score
35
★ 107 ⑂ 10 +19/day
Go
pcx-wave
pcx-wave
vibe-skill

Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage

Score
32
★ 107 ⑂ 10
Shell
glincker
glincker
stacklit

One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto-configures Claude Code, Cursor, Aider.

Score
100
★ 99 ⑂ 8
Go
lokikill123
lokikill123
codex-token-skills

⚡ Cut 60-80% token cost for DeepSeek V4 Pro on Codex CLI. token-saver + memory skills with prefix-cache optimization.

Score
87
★ 95 ⑂ 10 +3/day
avilum
avilum
minrlm

A small Recursive Language Model: let any LLM run code on its context instead of stuffing it into the prompt.

Score
80
★ 72 ⑂ 5 +1/day
Python
egorfedorov
egorfedorov
claude-context-optimizer

Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware suggestions — all local, zero config.

Score
26
★ 71 ⑂ 11 +1/day
JavaScript
pivanov
pivanov
ctx-wire

ctx-wire runs your commands, compresses the output with declarative filters, scrubs secrets, and hands your agent a short result. The full log stays on disk for when something actually fails. Cut the noise on the wire.

Score
0
★ 70 ⑂ 1
Go
KbWen
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.

Score
29
★ 65 ⑂ 17 +11/day
Python
sbsaga
sbsaga
toon

TOON — Laravel AI package for compact, human-readable, token-efficient data format with JSON ⇄ TOON conversion for ChatGPT, OpenAI, and other LLM prompts.

Score
73
★ 65 ⑂ 8
PHP
castnettech
castnettech
mnemosyne

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

Score
24
★ 58 ⑂ 9
Python
Tuntii
Tuntii
RustAPI

A high-performance, ergonomic web framework for Rust with native AI/LLM support.

Score
21
★ 56 ⑂ 3 +1/day
Rust
elevanaltd
elevanaltd
octave-mcp

OCTAVE protocol - structured AI communication with 3-20x token reduction. MCP server with lenient-to-canonical pipeline and schema validation.

Score
67
★ 53 ⑂ 4 +1/day
Python
TaewoooPark
TaewoooPark
Agent-Blackbox

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.

Score
18
★ 45 ⑂ 6 +45/day
TypeScript
Anuj7411
Anuj7411
sipcode

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.

Score
15
★ 44 ⑂ 4 +44/day
TypeScript
houseworthe
houseworthe
house-agents
Score
3
★ 43 ⑂ 5 +1/day
hunhee98
hunhee98
pluck

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Score
53
★ 38 ⑂ 0 +1/day
Rust
JacobHuang91
JacobHuang91
prompt-refiner

🚀 Lightweight Python library for building production LLM applications with smart context management and automatic token optimization. Save 10-20% on API costs while fitting RAG docs, chat history, and prompts into your token budget.

Score
40
★ 37 ⑂ 3
Python
AgusRdz
AgusRdz
chop

CLI output compressor for Claude Code. Reduces token consumption by 50–90% by compressing verbose command output before it enters the context window. Supports 52+ commands — git, docker, kubectl, npm, terraform, and more.

Score
12
★ 37 ⑂ 2
Go
alexandephilia
alexandephilia
clov-ai

Context Limiter & Output Vetter for context bloat. It is a highly specialized, structure-aware JSON built specifically to intercept and compress MCP responses before they annihilate your LLM's context window.

Score
6
★ 35 ⑂ 3
Rust
web-werkstatt
web-werkstatt
ai-context-optimizer

💰 Save money on AI API costs! 76% token reduction, Auto-Fix token limits, Universal AI compatibility. Cline • Copilot • Claude • Cursor

Score
0
★ 31 ⑂ 1
Sagargupta16
Sagargupta16
claude-cost-optimizer

Save 30-60% on Claude Code costs -- proven strategies, real benchmarks, copy-paste configs, and interactive tools

Score
47
★ 29 ⑂ 2
TypeScript
zx1160763849-hash
zx1160763849-hash
codex-cost-router-skills

Codex Cost Router Skills - preflight task routing skills for Codex to reduce token waste, choose model tiers, reasoning effort, permissions, and execution prompts.

Score
27
★ 23 ⑂ 0 +1/day
HTML
pleasedodisturb
pleasedodisturb
awesome-llm-token-optimization

A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.

Score
33
★ 21 ⑂ 6 +6/day
GabrielBarberini
GabrielBarberini
laconic

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

Score
13
★ 17 ⑂ 0
Python
l0z4n0-a1
l0z4n0-a1
cognitive-claude

The meta-architecture behind a high-leverage Claude Code setup. Installed by the very tool it optimizes.

Score
60
★ 17 ⑂ 16
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
20
★ 14 ⑂ 3 +1/day
JavaScript
AndyShaman
AndyShaman
senior-fable

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.

Score
7
★ 14 ⑂ 1 +14/day
warrenth
warrenth
ctxcraft

Evaluate and optimize your AI agent context. Save tokens, save money.

Score
0
★ 12 ⑂ 0
Shell
Related Topics
#developer-tools#claude-code#llm#mcp#claude#cli#ai#anthropic#prompt-engineering#ai-agents#rust#productivity

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly