👁 132 次阅读
HackerNews 今日热榜
GitHub 热门AI项目
| rank | repo | stars | description |
|---|---|---|---|
| 1 | arcships/aimux | 146 | 统一 LLM 服务接入层 — 一套 API 接入 172+ 家 AI 服务商 |
| 2 | simonlin1212/vibe-astock | 111 | A 股短线复盘看板：涨停池·连板梯队·龙虎榜·板块资金一屏看完，赚钱效应/晋级率/梯队断层/情绪周期等派生指标纯计算直出 |
| 3 | juxhinr/bindwidth | 95 | Evidence-aware on-prem LLM inference sizing and TCO calculat |
| 4 | liucongg/awesome-open-llms | 86 | 开源模型汇总，每月更新现在主流的开源模型。A monthly tracker for the latest and mo |
| 5 | alikon-art/DeterminFlow | 59 | A production-oriented AI workflow runtime for building, vali |
| 6 | CoordClaw/CoordClaw | 52 | CoordClaw: a multi-agent system that runs AI like a one-pers |
| 7 | priceisaacuwjh3036/ai-server-rust-llm-api | 39 | Rust-based AI inference server for Ollama-hosted large langu |
| 8 | wladimiravila/esp32s3-distributed-ai | 33 | Distributed 56M-parameter LLM inference across 3 ESP32-S3 bo |
| 9 | AFan4724/clone-chat | 31 | 用 AI 大模型复刻聊天对象的本地对话 Agent：导入真实聊天记录，LLM 学习 TA 的语气、表情和回复节奏并以人物 |
| 10 | rafcopy/auto-cut-agent | 30 | AI editing agent for Adobe Premiere Pro: silence removal, re |
Arxiv 最新AI论文
| rank | title | authors |
|---|---|---|
| 1 | FriendBench: Benchmarking Dyadic Familiarity Inference in Hu | Jeffrey M. Gira, Jason Z. Zheng, Jacqueline R. V |
| 2 | ARB: A Matched Authorship-Rewriting Benchmark Dataset for AI | Gaetano Perrone, Simon Pietro Ro |
| 3 | Cross-Lingual Transfer for Machine Translation in Turkic Lan | Omer Burak Cina, Mehmet Mert Dal, Cagri Toraman |
| 4 | Translation with Thought: Difficulty-Adaptive Reasoning via | Yongshi Ye, Biao Fu, Chongxuan Huang |
| 5 | CalibratedRubric: Task-Adaptive Rubric Banks for Open-Ended | Mengting Chen, Yanshu Sun, Wanting Liang |
| 6 | RecHarness: A Bandit-Routed Agentic Harness for Self-Evolvin | Haoran Ling, Yuecheng Li, Zeyu Song |
| 7 | Small Is Enough: Per-User Style Rewriting of AI-Edited Text | Antorweep Chakr |
| 8 | Semantics of Subterfuge: Benchmarking Legal Deception Detect | Theekshana Sama, Nisansa de Silv, George C. Lobb |
| 9 | Adjudicated Captioning: Multi-Agent Alignment Scoring and Co | Duy Tran Thanh, Thien-Phuc Doan, Long Nguyen-Vu |
| 10 | PARALLEL: A Prefrontal-Aligned Reinforcement inspired Approa | Namkyung Yoon, Sanghong Kim, Hwangnam Kim |
自动采集于 2026-08-03