paddler vs caveman
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| paddler | caveman | |
|---|---|---|
| Tagline | LLM load balancer and serving platform for self-hosting LLMs/VLMs | Cuts 65% of tokens in AI coding agent responses. |
| Stars | 1.6k | 86k |
| Forks | 89 | 4.8k |
| Open issues | 25 | 370 |
| Language | Rust | JavaScript |
| License | Apache-2.0 | MIT |
| Last pushed | Jul 7, 2026 | Jul 3, 2026 |
| Categories | Inference & Serving, LLM Frameworks | Developer Tools, LLM Frameworks |
paddler
Paddler is a Rust-based, open-source LLM/VLM load balancer and serving platform designed to facilitate the deployment and scaling of large language models on private infrastructure. It features built-in llama.cpp inference engine, simple dynamic model swapping, request buffering, and an integrated web admin panel for management tasks.
Rust
caveman
A skill/plugin for various AI agents, including Claude Code and other platforms, reducing output tokens for more concise, direct communication while maintaining accuracy.
JavaScript