DeepSeek GitHub · 实时热榜
| 热搜话题 | 最高排名 | 首次上榜 | 离榜时间 | 在榜时长 | 上榜次数 |
|---|---|---|---|---|---|
01 Codex CLI 0.163 Update: Mid-Response Steering by Default - https://tech-insider.org/ Codex CLI 0.163 Update: Mid-Response Steering by Default https://tech-insider.org/ | #100:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
02 Community-Built DS Bot Plugin Turns DeepSeek Harness Into a Team of Long-Lived Bots - Pandaily Community-Built DS Bot Plugin Turns DeepSeek Harness Into a Team of Long-Lived Bots Pandaily | #200:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
03 Huawei and DeepSeek release open source AI tools in a bid to lower Nvidia exposure — but will programmers make the switch? - TechRadar Huawei and DeepSeek release open source AI tools in a bid to lower Nvidia exposure — but will programmers make the switch? TechRadar | #300:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 6小时52分累计在榜 | 2重入 1 次 |
04 Huawei and DeepSeek release open source AI tools in a bid to lower Nvidia exposure — but will programmers make the switch? - Yahoo Tech Huawei and DeepSeek release open source AI tools in a bid to lower Nvidia exposure — but will programmers make the switch? Yahoo Tech | #303:46 达到 | 03:46首次观测上榜 | 12:33观测离榜 | 8小时47分累计在榜 | 1无重入 |
05 DSH 0.2 and DeepSeek V4.1 Pro: What the Record Says - OrcaRouter DSH 0.2 and DeepSeek V4.1 Pro: What the Record Says OrcaRouter | #400:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
06 DeepSeek Harness v0.2 Brings Official Desktop Apps to Its Open-Source Agent Harness - MarkTechPost DeepSeek Harness v0.2 Brings Official Desktop Apps to Its Open-Source Agent Harness MarkTechPost | #407:54 达到 | 07:54首次观测上榜 | —结束时仍在榜 | 7小时14分累计在榜 | 2重入 1 次 |
07 DeepSeek Harness Desktop Preview Version Officially Launched – Now Available - 36Kr DeepSeek Harness Desktop Preview Version Officially Launched – Now Available 36Kr | #500:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
08 Claude Code Fully Open-Source & Integrated with AGENTS.md – Complete Guide - eu.36kr.com Claude Code Fully Open-Source & Integrated with AGENTS.md – Complete Guide eu.36kr.com | #600:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
09 Tencent Open-Sources WeKnora With Official DeepSeek Harness Plugin - Pandaily Tencent Open-Sources WeKnora With Official DeepSeek Harness Plugin Pandaily | #700:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
10 DeepSeek Open-Sources Harness Agent Runtime With Everything-Is-a-Plugin Design - Pandaily DeepSeek Open-Sources Harness Agent Runtime With Everything-Is-a-Plugin Design Pandaily | #800:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
11 Detecting and countering misuse of AI: September 2026 - Anthropic Detecting and countering misuse of AI: September 2026 Anthropic | #900:00 达到 | 00:00首次采集时已在榜 | 09:27观测离榜 | 9小时28分累计在榜 | 1无重入 |
12 Xiaolong Bypasses the Office Agent: Step-by-Step Guide & Practical Tips - 36Kr Xiaolong Bypasses the Office Agent: Step-by-Step Guide & Practical Tips 36Kr | #1000:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
13 Hugging Face Acquired for $86.7 Billion: Landmark AI Industry Deal Details & Implications - 36 Kr Hugging Face Acquired for $86.7 Billion: Landmark AI Industry Deal Details & Implications 36 Kr | #1100:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
14 The Open-Sourcing of DeepSeek Harness Opens the Door to Modular, Unbundled AI Agent Infrastructure - infoq.com The Open-Sourcing of DeepSeek Harness Opens the Door to Modular, Unbundled AI Agent Infrastructure infoq.com | #1200:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
15 Crash Course to Master DeepSeek Harness from Scratch, Take You to Tinker with Cyber Lego - 36Kr Crash Course to Master DeepSeek Harness from Scratch, Take You to Tinker with Cyber Lego 36Kr | #1300:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
16 DeepSeek Harness Turns the AI Agent Into a Box of Swappable Parts - Kingy AI DeepSeek Harness Turns the AI Agent Into a Box of Swappable Parts Kingy AI | #1409:27 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
17 DeepSeek AI Releases DeepSeek Harness in Developer Preview: An MIT-Licensed Agent Harness Where Everything is a Plugin - MarkTechPost DeepSeek AI Releases DeepSeek Harness in Developer Preview: An MIT-Licensed Agent Harness Where Everything is a Plugin MarkTechPost | #1400:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
18 DeepSeek Harness, What It Actually Is and What the Critics Say - Pasquale Pillitteri DeepSeek Harness, What It Actually Is and What the Critics Say Pasquale Pillitteri | #1509:27 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
19 DeepSeek Harness Explained: DSH 0.2 Desktop App, Presets - OrcaRouter DeepSeek Harness Explained: DSH 0.2 Desktop App, Presets OrcaRouter | #1700:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
20 Cordiverse Cordis Hit GitHub Trending, but DeepSeek Is the Real Story - remio Cordiverse Cordis Hit GitHub Trending, but DeepSeek Is the Real Story remio | #1800:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
21 AI Week in Review 26.08.15 - by Patrick McGuinness - Substack AI Week in Review 26.08.15 - by Patrick McGuinness Substack | #1900:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
22 DeepSeek Harness Is Open Source, but Its Plugin Bet Still Needs Proof - remio DeepSeek Harness Is Open Source, but Its Plugin Bet Still Needs Proof remio | #2000:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
23 DeepSeek Harness launches as open source rival to Claude Code, alongside V4-Pro on API with higher prices - VentureBeat DeepSeek Harness launches as open source rival to Claude Code, alongside V4-Pro on API with higher prices VentureBeat | #2100:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
24 DeepSeek Just Open-Sourced Its Answer to Claude Code — And Developers Noticed Fast - Binance DeepSeek Just Open-Sourced Its Answer to Claude Code — And Developers Noticed Fast Binance | #2200:00 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
25 After Thoroughly Experiencing DeepSeek Harness: Why I Fully Accept Its Price Hike - 36 Kr After Thoroughly Experiencing DeepSeek Harness: Why I Fully Accept Its Price Hike 36 Kr | #2300:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
26 DeepSeek open sources an agent harness where everything is a plugin - The New Stack DeepSeek open sources an agent harness where everything is a plugin The New Stack | #2300:00 达到 | 00:00首次采集时已在榜 | 00:40观测离榜 | 41分累计在榜 | 1无重入 |
27 DeepSeek Harness v0.1: Open-Source MIT Rival to Claude Code - Pasquale Pillitteri DeepSeek Harness v0.1: Open-Source MIT Rival to Claude Code Pasquale Pillitteri | #2303:46 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
28 DeepSeek Harness Stunningly Open-Sourced Now: Everything Becomes a Plugin - 36Kr DeepSeek Harness Stunningly Open-Sourced Now: Everything Becomes a Plugin 36Kr | #2400:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
29 China-based hacker employs DeepSeek in autonomous threat campaign - Cybersecurity Dive China-based hacker employs DeepSeek in autonomous threat campaign Cybersecurity Dive | #2600:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
30 Validating Distributed LLM Serving Benchmarks with NVIDIA srt-slurm, SLURM Recipes, Parameter Sweeps, and Pareto Analysis - MarkTechPost Validating Distributed LLM Serving Benchmarks with NVIDIA srt-slurm, SLURM Recipes, Parameter Sweeps, and Pareto Analysis MarkTechPost | #2712:33 达到 | 12:33首次观测上榜 | —结束时仍在榜 | 3小时6分累计在榜 | 1无重入 |
31 DeepSeek has released 'DSpark,' which can improve the speed of AI language model generation by up to 85%. - GIGAZINE DeepSeek has released 'DSpark,' which can improve the speed of AI language model generation by up to 85%. GIGAZINE | #2700:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
32 DeepSeek V4 is Now up to 85% Faster With New Inference Technique - Analytics India Magazine DeepSeek V4 is Now up to 85% Faster With New Inference Technique Analytics India Magazine | #2800:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
33 Crimes exploiting the AI boom are surging; Microsoft analyzes methods used to steal authentication credentials using ChatGPT and Claude names. - GIGAZINE Crimes exploiting the AI boom are surging; Microsoft analyzes methods used to steal authentication credentials using ChatGPT and Claude names. GIGAZINE | #2900:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
34 AI brands as bait: How threat actors are using the AI hype in social engineering - Microsoft AI brands as bait: How threat actors are using the AI hype in social engineering Microsoft | #3000:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
35 Hackers Use Fake DeepSeek TUI GitHub Repositories to Deliver Malware - CyberSecurityNews Hackers Use Fake DeepSeek TUI GitHub Repositories to Deliver Malware CyberSecurityNews | #3100:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
36 DeepSeek V4 Is Here—Its Pro Version Costs 98% Less Than GPT 5.5 Pro - Decrypt DeepSeek V4 Is Here—Its Pro Version Costs 98% Less Than GPT 5.5 Pro Decrypt | #3200:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
37 Malicious OpenClaw DeepSeek Skill Exploits Agentic AI Workflows to Deliver RAT and Stealer - CyberSecurityNews Malicious OpenClaw DeepSeek Skill Exploits Agentic AI Workflows to Deliver RAT and Stealer CyberSecurityNews | #3201:42 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 7小时54分累计在榜 | 3重入 2 次 |
38 Open Repositories Replace Closed Studios As GitHub Drives Game Innovation - Open Source For You Open Repositories Replace Closed Studios As GitHub Drives Game Innovation Open Source For You | #3300:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
39 DeepSeek Reportedly Prepares New Flagship AI Model Ahead of Lunar New Year - TechNode DeepSeek Reportedly Prepares New Flagship AI Model Ahead of Lunar New Year TechNode | #3400:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
40 DeepSeek V4 Leaked: The Engram Architecture That Changes the Rules of AI Coding - Medium DeepSeek V4 Leaked: The Engram Architecture That Changes the Rules of AI Coding Medium | #3500:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
41 DeepSeek Unveils Engram: A New "Memory vs. Computation" Architecture for More Efficient AI - finance.biggo.com DeepSeek Unveils Engram: A New "Memory vs. Computation" Architecture for More Efficient AI finance.biggo.com | #3600:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
42 DeepSeek AI Releases DeepSeekMath-V2: The Open Weights Maths Model That Scored 118/120 on Putnam 2024 - MarkTechPost DeepSeek AI Releases DeepSeekMath-V2: The Open Weights Maths Model That Scored 118/120 on Putnam 2024 MarkTechPost | #3700:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
43 Comparing the Top 6 OCR (Optical Character Recognition) Models/Systems in 2025 - MarkTechPost Comparing the Top 6 OCR (Optical Character Recognition) Models/Systems in 2025 MarkTechPost | #3800:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
44 Breaking news: DeepSeek opens source again. Vision is compression. 100 tokens outperform 7000 tokens. - 36 Kr Breaking news: DeepSeek opens source again. Vision is compression. 100 tokens outperform 7000 tokens. 36 Kr | #3900:40 达到 | 00:40首次观测上榜 | —结束时仍在榜 | 10小时20分累计在榜 | 4重入 3 次 |
45 DeepSeek launches 3 billion parameter vision-language model - YourStory.com DeepSeek launches 3 billion parameter vision-language model YourStory.com | #4000:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
46 AI Week in Review 25.08.23 - Substack AI Week in Review 25.08.23 Substack | #4100:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
47 GitHub Spark in public preview for Copilot Pro+ subscribers - The GitHub Blog GitHub Spark in public preview for Copilot Pro+ subscribers The GitHub Blog | #4200:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
48 Deploying Kimi K2 with PD Disaggregation and Large-Scale Expert Parallelism on 128 H200 GPUs - LMSYS Org Deploying Kimi K2 with PD Disaggregation and Large-Scale Expert Parallelism on 128 H200 GPUs LMSYS Org | #4300:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
49 Understanding DeepSeek AI: The Mixture-of-Experts Technique and Its Impact on Resource Optimization - remio Understanding DeepSeek AI: The Mixture-of-Experts Technique and Its Impact on Resource Optimization remio | #4400:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |
50 GitHub Models now supports moving beyond free limits - The GitHub Blog GitHub Models now supports moving beyond free limits The GitHub Blog | #4500:40 达到 | 00:00首次采集时已在榜 | —结束时仍在榜 | 15小时39分累计在榜 | 1无重入 |