GitHub Trending 今日热榜 2026-09-05
🔥 GitHub Trending 今日热榜#
2026-09-05 · 每日更新开源项目趋势
mattpocock/skills#
真正工程师的技能。直接来自我的.agents目录。
Skills for Real Engineers. Straight from my .agents directory.
DietrichGebert/ponytail#
让你的人工智能代理像房间里最懒惰的高级开发人员一样思考。最好的代码是你从未写过的代码。
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
debpalash/VoiceStudio#
VoiceStudio是开源、完全本地的ElevenLabs替代品--语音克隆、语音设计、视频配音、听写、转录和有声读物创作,支持646种语言。
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transc
affaan-m/ECC#
座席线束性能优化系统。Claude Code、Codex、Opencode、Cursor等的技能、本能、记忆、安全和研究优先开发。
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude
blader/humanizer#
从文本中删除人工智能生成文字的迹象的代理技能
Agent skill that removes signs of AI-generated writing from text
bannedbook/fanqiang#
翻墙-科学上网
JuliusBrussee/caveman#
🪨 为什么在很少令牌欺骗时使用许多令牌— Claude Code技能通过像穴居人一样说话来削减65 %的令牌
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
cathrynlavery/diagram-design#
Claude Code、Codex和Pi的38种编辑图类型。独立的HTML + SVG。没有阴影,没有美人鱼粪便。
38 editorial diagram types for Claude Code, Codex, and Pi. Self-contained HTML + SVG. No shadows. No Mermaid slop.
magnitudedev/magnitude#
开源推理服务器,为您的硬件运行最佳本地模型,插入到您已经使用的代理中。适用于Pi、OpenCode、Hermes、OpenClaw、Codex、Claude Code、Oh My Pi和Cline。
Open source inference server that runs the best local models for your hardware, plugged into the agent you already use. Works with
google-research/timesfm#
TimesFM (时间序列基础模型)是由Google Research开发的用于时间序列预测的预训练时间序列基础模型。
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series f
bikini/exploitarium#
公共漏洞利用PoC和漏洞研究报告的单一存档。在我发布这些信息时,还没有收到任何报告。如果发放了lulz ,您可以自行报告,并记入CVE。请勿滥用。我这样做是为了吸引人们进入这个领域,我一直发现这是最有效的方法。
A single archive of public exploit PoCs and vulnerability research writeups. At the time I post these, none have been reported. Fe
radixark/miles#
Miles是一个面向企业的强化学习框架,用于LLM和VLM培训后,从SLIME分叉并与SLIME共同进化。
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with sli