by EfficientContext · Codex Skill · ★ 116
ContextPilot: Fast Long-Context Inference via Context Reuse 4–12× cache hits 36% token savings across vLLM, SGLang, RAG, AI Agents, and more. News [2026/05] Supports Hermes Agent as a native context engine plugin — guide [2026/03] Supports OpenClaw — guide | benchmark [2026/03] Supports cloud APIs (OpenAI, Anthropic, MiniMax) — cache sync [2026/03] ContextPilot now can run on macOS / Apple Silicon via [llama.cpp](docs/guides/ma
| Stars | 116 |
| Forks | 5 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 67.6502135533655/100 |
| Open Issues | 12 |
| Last Updated | 2026-06-22 |
| Created | 2026-01-09 |
| Platforms | python |
| Est. Tokens | ~17k |
These tools work well together with ContextPilot for enhanced workflows:
Explore other popular codex skill tools:
ContextPilot is Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.. It is categorized as a Codex Skill with 116 GitHub stars.
ContextPilot is primarily written in Python. It covers topics such as ai-agents, context-api, context-engineering.
You can find installation instructions and usage details in the ContextPilot GitHub repository at github.com/EfficientContext/ContextPilot. The project has 116 stars and 5 forks, indicating an active community.
ContextPilot is released under the Apache-2.0 license, making it free to use and modify according to the license terms.