R_REDDYX.XYZ

Cost Optimization: open-source projects on GitHub

17 repositories on Cost Optimization, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.

// RELATED TOPICS

LLM 2094Anthropic 452AI Agents 1319Claude Code 1595Openai 690Codex 849LLM Router 14Claude 978Developer Tools 620Token Optimization 33Cost Tracking 18Openclaw 241Deepseek 229Gemini 348
Netflix/metaflow

METAFLOW — ML MANAGEMENT

Metaflow simplifies building, managing, and deploying AI/ML systems on Python, allowing focus on data science.

★ 10,114 · Python
mnfst/manifest

Smart Model Router

Automatically selects the optimal model for each agent request, reducing inference costs by up to 70%.

★ 6,565 · TypeScript
BlockRunAI/ClawRouter

LLM Router for OpenClaw

An LLM router for OpenClaw supporting 41+ models, sub‑millisecond routing, and USDC payments on Base and Solana via the x402 protocol.

★ 6,550 · TypeScript
lemony-ai/cascadeflow

CASCADEFLOW SPEEDS UP AI AGENTS

Cascading runtime for AI agents that optimizes cost, latency, quality, and policy inside the agent loop.

★ 3,926 · Python
JayPokale/Chisle

REDUCE AI TOKEN COSTS

Chisle cuts AI-agent token usage: terse prose, YAGNI-first code, and tool-output compression. Works with Claude Code, Pi, Cursor, Codex, Gemini and four more, zero deps,

★ 1,072 · JavaScript
ojuschugh1/sqz

SQZ: COMPRESSION FOR AI AGENTS

SQZ compresses tool output before it reaches the LLM, replacing repeated fragments with short 13‑token references. Works with Claude Code, Cursor, Codex, Kiro, Zed and an

★ 677 · Rust
nudgebee/nudgebee

NUDGEBEE: AI IN CLOUDOPS

Unified CloudOps platform with AI‑SRE, AI‑FinOps, and AI‑K8sOps, plus an agentic automation builder — no fragmentation and no model lock‑in.

★ 524 · Go
NadirRouter/NadirClaw

NADIRCLAW: LLM Routing for Savings

Routes queries to cheap local models and premium LLMs, saving 40‑70% on API costs.

★ 504 · Python
higress-group/HiRoute

HIROUTE — SMART AI MODEL ROUTER

Local router routes routine tasks to cheap models, complex ones to powerful. Reduces Codex and Claude Code subscription costs while preserving quality. Written in Rust.

★ 465 · Rust
messkan/prompt-cache

PROMPT CACHE SAVINGS 80%

Intelligent semantic cache for LLM prompts, reduces costs up to 80% and delivers sub‑millisecond responses. Provider‑agnostic Go proxy.

★ 427 · Go
muaaz9329/cheap-ag

50X CLAUDE USAGE FOR $20

cheap-ag multiplies Claude limits 50x. A cheap model writes code, tests decide what merges. One MCP server for Claude Code, no $20 limits.

★ 331 · TypeScript
jia-gao/leanctx

COMPRESS PROMPTS BY 60%

leanctx — drop-in prompt compression for LLM applications. Reduces tokens by 40-60% without changing code.

★ 308 · Python
cnighswonger/claude-code-cache-fix

CLAUDE CODE SAVES YOUR MONEY

Fixes the prompt cache regression in Claude Code that caused costs to rise up to 20x when resuming sessions.

★ 270 · JavaScript
blendbunjaku/optimaizr

SAVE TOKENS IN CLI

Local CLI optimaizr finds wasted tokens in Claude Code, Codex, opencode and your API calls. Analyzes spending and shows where money is lost. Supports TypeScript projects

★ 243 · TypeScript
QuesmaOrg/awesome-ai-tokenomics

LLM TOKENOMICS: TOOLS TO SAVE

Curated list on AI token economics: costs, waste, and how to cut bills. Tools, benchmarks, papers, and ready configs for LLMs and coding agents. 206 stars on GitHub.

★ 219 · Python
Rodiun/frugon

FRUGON - LLM COST ANALYSIS

Free, local, and open LLM cost analyzer. See where your spend “leaks,” right on your machine.

★ 218 · Python
Chengjun023/agent-smith

Smith Adaptive Model Router

Agent Smith routes model calls adaptively, monitors Codex token usage in real time, and generates reproducible benchmark reports with verification receipts.

★ 9 · Python

New projects on this topic in Telegram

Telegram →
Cost Optimization — 17 open-source GitHub projects | REDDYX AI