cost-optimization repositories

Trending repositories tagged cost-optimization, ranked by trending score. Updated daily.

  1. 1
    microsoft/TokenEconomizer

    Experience-Driven Black-Box Cost Control for Coding Agents

    GitHub · Python · 7,805 stars · 534 forks · +284 stars in 24 hours · Trending score 4.88

  2. 2
    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 · 166 stars · 12 forks · +25 stars in 24 hours · Trending score 2.70

  3. 3
    skypilot-org/skypilot

    The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

    GitHub · Python · 10,862 stars · 1,360 forks · +6 stars in 24 hours · Trending score 2.09

  4. 4
    higress-group/HiRoute

    Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.

    GitHub · Rust · 480 stars · 56 forks · +7 stars in 24 hours · Trending score 2.04

  5. 5
    CommonstackAI/TwinRouterBench

    Per-step LLM routing benchmark with 970 static labels, live SWE-bench evaluation, an open data pipeline, and a public leaderboard.

    GitHub · Python · 35 stars · 4 forks · +14 stars in 24 hours · Trending score 2.01

  6. 6
    mralexivy/AutoMode

    Automatic model and effort router for Claude Code. A free plugin that picks Haiku, Sonnet or Opus for each prompt, adds risk floors and a review workflow, and shows cache and context state. No key, no server.

    GitHub · TypeScript · 79 stars · 0 forks · +2 stars in 24 hours · Trending score 1.44

  7. 7
    Netflix/metaflow

    Build, Manage and Deploy AI/ML Systems

    GitHub · Python · 10,354 stars · 1,395 forks · +3 stars in 24 hours · Trending score 1.43

  8. 8
    alexgreensh/token-optimizer

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

    GitHub · Python · 2,964 stars · 234 forks · 0 stars in 24 hours · Trending score 1.08

  9. 9
    BlockRunAI/ClawRouter

    The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.

    GitHub · TypeScript · 6,665 stars · 656 forks · +2 stars in 24 hours · Trending score 1.07

  10. 10
    muaaz9329/cheap-ag

    50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code & Codex.

    GitHub · TypeScript · 339 stars · 31 forks · +2 stars in 24 hours · Trending score 1.03

  11. 11
    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 · 236 stars · 9 forks · 0 stars in 24 hours · Trending score 1.01

  12. 12
    koordinator-sh/koordinator

    A QoS-based scheduling system brings optimal layout and status to workloads such as microservices, web services, big data jobs, AI jobs, etc.

    GitHub · Go · 1,782 stars · 495 forks · 0 stars in 24 hours · Trending score 0.97

  13. 13
    opencost/opencost

    Cost monitoring for Kubernetes workloads and cloud costs

    GitHub · Go · 6,824 stars · 934 forks · 0 stars in 24 hours · Trending score 0.95

  14. 14
    sustainable-computing-io/kepler

    Kepler lets you monitor the energy use of Kubernetes workloads. Kepler is a CNCF Sandbox project. Let's make every watt matter. ⚡

    GitHub · Go · 1,606 stars · 293 forks · +1 stars in 24 hours · Trending score 0.95

  15. 15
    infracost/infracost

    Cloud cost intelligence for engineers, AI coding agents, and CI/CD 💰📉 Shift FinOps Left!

    GitHub · Go · 12,621 stars · 701 forks · 0 stars in 24 hours · Trending score 0.92

  16. 16
    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 · 46 stars · 13 forks · +5 stars in 24 hours · Trending score 0.91

  17. 17
    ahwurm/localharness

    An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harness (detailed event steams, logs, and performance data) or quickly replace closed source one (featuring out of the box plugins for web search, image gen, memory, auto research and more in dev).

    GitHub · Python · 74 stars · 7 forks · 0 stars in 24 hours · Trending score 0.81

  18. 18
    ReliablyObserve/victoria-lakehouse

    S3-backed cold storage for VictoriaLogs and VictoriaTraces — 60-96% cost reduction with unlimited retention, disaster recovery, and open Parquet format for analytics.

    GitHub · Go · 9 stars · 2 forks · +1 stars in 24 hours · Trending score 0.79

  19. 19
    NadirRouter/NadirClaw

    Source-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor and OpenClaw. Self-hosted, no middleman.

    GitHub · Python · 666 stars · 78 forks · +2 stars in 24 hours · Trending score 0.73

  20. 20
    vantage-sh/ec2instances.info

    Amazon EC2 instance comparison site

    GitHub · TypeScript · 5,783 stars · 626 forks · 0 stars in 24 hours · Trending score 0.71

  21. 21
    cuihuan/awesome-ai-gateway

    ⚡ Awesome AI Gateway — pick an AI gateway from 240+ (LiteLLM, OpenRouter, Portkey, Kong, Higress, new-api, Bifrost) by cost, security & compliance, see what consolidated in 2026, learn how they actually work from an 8-chapter handbook, and verify every number yourself. Reproducible benchmarks, bilingual; stars & releases refreshed daily.

    GitHub · HTML · 158 stars · 152 forks · 0 stars in 24 hours · Trending score 0.69

  22. 22
    ojuschugh1/sqz

    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.

    GitHub · Rust · 678 stars · 43 forks · 0 stars in 24 hours · Trending score 0.63

  23. 23
    KrystalUnity/krystal-loop-protocol

    A low-cost model does the coding, a frontier model checks the exact result. 59 of 66 benchmark tasks solved at $0.046 each, against 56 at $0.721 for the heavy model alone. One-command runner with receipts you can recompute.

    GitHub · Python · 14 stars · 0 forks · +1 stars in 24 hours · Trending score 0.62

  24. 24
    edgee-ai/edgee

    Official Edgee CLI to interract with Edgee's Agent Gateway. Route Claude Code, Codex, Cursor, VS Code + Copilot, and more through Edgee's hosted gateway to cut token spend.

    GitHub · Rust · 144 stars · 23 forks · +1 stars in 24 hours · Trending score 0.55