Local-first 代码智能图谱,面向 MCP 与 CLI。为代码库构建持久化映射,使 AI 编程工具只读取关键内容,在代码评审与大仓库工作流中实现可基准测试的上下文缩减。Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
仓库/Skill 库
6 个 · 评测集 · 快速增长
Qwen3.8-27B 在单卡 RTX 3090 上使用 vLLM 部署:64 并发下约 1,000 tok/s(int8 张量核心 GEMM、fp16 DeltaNet 状态),默认采样下单用户约 114 tok/s/贪心约 124 tok/s(MTP 草稿、自输出草稿词表、校准 int4 lm_head、split-KV 校验注意力),150k–262k 上下文;附带补丁、重新量化脚本与基准测试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
面向 Godot 的开源游戏编程 Agent 环境与基准An open-source game coding agent environment and benchmark for Godot.
提供 DeepSeek 与 Qwen 服务,运行按需模型库,并在 2 块 NVIDIA DGX Spark 上使用 Unsloth QLoRA 微调。TP=2 的 vLLM 通道汇聚于单一 OpenAI 兼容端点,供 OpenCode、Cursor 与 Hermes 使用。诚实的基准,已提交的工件。Serve DeepSeek and Qwen, run an on-demand model library, and fine-tune with Unsloth QLoRA on 2x NVIDIA DGX Spark. TP=2 vLLM lanes behind one OpenAI-compatible endpoint for OpenCode, Cursor, and Hermes. Honest benchmarks, committed artifacts.