LLM Lounge
Color
Ocean
Forest
Rose
Midnight
Warm Ember
Nord
Light
Monochrome
Style
Developer
Clean Minimal
Terminal
Editorial
Home
1Get Running2Choose Wisely3AHow Models Think3BHow Models Fit4What Can You Do With This?5Agents6Build Custom Tools7Local + Cloud8Supercharge Your Setup9Go Further10What's Next
Model ReferenceHardware ReferenceBenchmarks ReferenceTools & UIs ReferenceFrontier Models ReferenceAgent Ecosystem ReferenceExtensions & Ecosystem ReferenceSources
Hardware CalculatorUseful Projects
NewsResearchFlashcardsBlog
ToolsUseful Projects

Useful Projects

Open-source projects that cut token costs and add memory to your coding agents, whether the model runs locally or in the cloud.

headroomlabs-ai/headroom
78k
headroom

Compresses tool outputs, logs, files, and RAG chunks before they reach the model, cutting tokens by 20% for coding agents and 60-95% for JSON. Runs as a library, proxy, or MCP server.

PythonMCPtoken-optimization
rtk-ai/rtk
85k
rtk

A CLI proxy shipped as a single Rust binary with no dependencies. It cuts LLM token use by 60-90% on common dev commands.

RustCLItoken-optimization
cwinvestments/memstack
430
memstack

Adds persistent memory to Claude Code with a session diary and fact recall, plus 87 free skills and an MCP skill loader.

PythonClaude Codememory
LLM Loungeby Skrunch Technologies Inc.
Privacy Policy|Terms of Service

No cookies. No tracking. No data collection. This site is fully static and runs entirely in your browser.

© 2026 Skrunch Technologies Inc. All rights reserved.