GitHub repo leaderboard by stars, growth rate and activity.
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.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
The Cyber Swiss Army Knife - a web app for encryption, encoding, compression and data analysis
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
An android image compression library.
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | 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. | Python | 71,128 | last pushed 23 hours ago | |
| 2 | DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective. | Python | 43,083 | last pushed 23 hours ago | |
| 3 | The Cyber Swiss Army Knife - a web app for encryption, encoding, compression and data analysis | JavaScript | 35,796 | last pushed Yesterday | |
| 4 | Easy-to-use and powerful LLM and SLM library with awesome model zoo. | Python | 12,971 | last pushed 4 months ago | |
| 5 | The macOS & iOS file archiver | PHP | 7,319 | last pushed 2 months ago | |
| 6 | An android image compression library. | Kotlin | 7,225 | last pushed 6 months ago | |
| 7 | SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal | Python | 3,752 | last pushed 2 months ago |
All · 11,474