👁 106 次阅读
HackerNews 今日热榜
GitHub 热门AI项目
| rank | repo | stars | description |
|---|---|---|---|
| 1 | PromptPartner/agentsmith | 314 | Universal, model-agnostic operating harness for AI agents (C |
| 2 | livetennisapi/livetennisapi-mcp | 249 | MCP server for the Live Tennis API — give Claude, Cursor and |
| 3 | CyberSunil/LLMVault | 220 | An intentionally vulnerable OWASP LLM Top 10 training platfo |
| 4 | KlaatAI/klaatcode | 178 | Open-source AI coding agent for the terminal. Claude Code-gr |
| 5 | lofty14/restaurant-digitalization-blueprint | 119 | 餐饮连锁数字化 + AI 全景蓝图:原串(平价烤串连锁)的架构决策、业务口径、踩坑实录与可直接喂给 AI 的复刻指令。纯 |
| 6 | MemTensor/memmy-agent | 64 | One Agent. One memory. Shared by every AI. 🍙 |
| 7 | smixs/mentor | 54 | mentor — a session-insights skill for AI coding agents. This |
| 8 | bbarit/bbarit-agent-oss | 39 | Open-source AI coding agent for your terminal — one Rust bin |
| 9 | Prism-Shadow/penguin-harness | 32 | Efficient Self-Improving Harness for 1000+ Models |
| 10 | wassermanproductions/scriptbreak | 29 | Screenplay breakdown & AI prompt-pack studio — import a scri |
Arxiv 最新AI论文
| rank | title | authors |
|---|---|---|
| 1 | Automated Discovery Has No Universally Superior Harness | Akshat Gupta, Jermaine Lei, Alexander Lu |
| 2 | Logical Judgments Under Pressure: Diagnosing Syllogistic Sta | Brian K Chen |
| 3 | Do Language Models Dream of Binding Molecules? Benchmarking | Thomas MacDouga, Maksim Kuznetso, Roman Schutski |
| 4 | O-VAD: Industrial Video Anomaly Detection through Object-Cen | Mei Yuan, Qi Long, Qifeng Wu |
| 5 | How Does Alignment Tuning Shape Representations of Sycophanc | Prakhar Gupta, Terry Jingchen , Florent Draye |
| 6 | WorldCupArena: Fine-Grained Evaluation of Language Models an | Zhaokai Wang, Tianlin Gui, Jiayuan Rao |
| 7 | MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for | Martino M. L. P, Cuong Xuan Chu, Evgeny Kharlamo |
| 8 | Self-State Attacks on Self-Hosted AI Agents: How Far Can OS | Yimeng Chen, Nathanaël Denis, Roberto Di Piet |
| 9 | DeLIVeR: Decomposed Learning for Information-grounded Veraci | Cong Hoan Nguye, Thomas Hoang, Hieu Minh Duong |
| 10 | Zero Hallucination, by Construction: Hallucination-Aware Lay | Bogdan Raduta, Horia Velicu, Alexandru Preda |
自动采集于 2026-07-21
🔗 相关阅读（你可能还想看）
📄 2026年8月AI对话模型三强横评：ChatGPT vs Claude vs Kimi，谁更值得订阅？
📄 AI工具日报：今日值得关注的新工具与更新
📄 AI行业日报：2026年8月6日——DeepMind高层巨变、Cloudflare OS开源、开源模型100倍成本叫板GPT-5.6 Sol
📄 AI每日热点 – 2026-08-06
📄 AI每日热点 – 2026-08-05
📄 AI 工具日报 — 2026年8月5日
📄 AI 工具日报 — 2026年8月4日
📄 AI行业日报：2026年8月4日 — OpenAI数学突破、Cloudflare模型优化、MiniMax开源视频模型
📄 AI每日热点 – 2026-08-04