Harness-oriented agent system framework for production-grade LLM agent applications
Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks
本地优先 AI 小说创作工作台,提供 Windows/macOS 桌面版与 DeepSeek Harness 插件开发预览,支持角色、大纲、章节蓝图、审稿修稿和本地模型。
Building blocks for frontier OpenAI agents in Rust. Nanocodex empowers you with Codex-level performance anywhere.
The missing bridge between your ML models and your AI agents.
A tiny macOS app that turns Caps Lock into a physical keep-awake switch for closed-lid MacBook work.
Turn Codex threads into an organization of long-lived domain agents.
做企业 AI 视频项目逼出来的工具包 · 411 prompt · 15 模型 · 7 Claude Skill · 14 篇方法论
Browser-only Canva-style presentation studio, powered by local Web AI.
共 789 条 · 第 13 / 40 页