by SparkEngineAI · Codex Skill · ★ 90
QuantClaw: Precision Where It Matters for OpenClaw 中文文档 QuantClaw is a plug-and-play task-type routing quantization plugin for OpenClaw. It classifies each incoming request, maps it to a precision tier (, , or ), and routes the request to the right model target so you can balance quality, latency, and cost without asking users to choose precision manually. 🔍 About QuantClaw QuantClaw is built from quantization studies on OpenClaw workloads rather than from fixed intuition. We evaluate quantized and high-precision models across 24 task types, 104 tasks, 6 models, and scales from 9B to 744B.
| Stars | 90 |
| Forks | 0 |
| Language | TypeScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66.6611550711523/100 |
| Last Updated | 2026-04-27 |
| Created | 2026-04-22 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~197k |
These tools work well together with QuantClaw-plugin for enhanced workflows:
Explore other popular codex skill tools:
QuantClaw-plugin is QuantClaw is a plug-and-play task-type routing quantization plugin for OpenClaw.. It is categorized as a Codex Skill with 90 GitHub stars.
QuantClaw-plugin is primarily written in TypeScript. It covers topics such as agents, claude, codex.
You can find installation instructions and usage details in the QuantClaw-plugin GitHub repository at github.com/SparkEngineAI/QuantClaw-plugin. The project has 90 stars and 0 forks, indicating an active community.
QuantClaw-plugin is released under the MIT license, making it free to use and modify according to the license terms.