Tag
Trellis is an open-source project that provides team-level engineering standards and a project memory framework for AI coding agents. It supports multiple platforms and enhances agent development efficiency and quality by persisting specifications and task context to code repositories.
Trellis has reached 9000+ GitHub stars and 5000+ weekly downloads, growing rapidly. Praised as the closest thing to "letting AI remember a project", recommended for users of Claude Code or Codex.
Trellis introduces RadixAttention to optimize LLM inference prefill phase by caching prefix tokens using a radix tree, reducing redundant computation in chat and agentic sessions.
GenRecon introduces a method for 3D scene reconstruction that integrates generative 3D priors with multi-view image conditioning, achieving high-fidelity, editable mesh reconstructions of indoor environments and outperforming existing methods by 16%.