Свой ИИ-чат на вашем ПК в один клик: подбирает модель под железо, ставит Ollama и модель. Windows. / One-click local AI chat for Windows: picks a model for your hardware, installs Ollama.
GitHub repository with 11 stars and 6 forks.
Language: JavaScript
Topics: llm, local-llm, ollama, pywebview, windows
Trending score 0.39, freshness score 0.00, stars gained +0, forks gained +0.
2026-11-15: 11 stars and 6 forks.
在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap.
GitHub repository with 75,091 stars and 2,099 forks.
Trending score: 6.38; stars gained: +3,019; forks gained: +131.
Language: JavaScript
Topics: ai-agents, deepseek, deepseek-harness, developer-tools, dsh, dsh-plugin
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
GitHub repository with 72,824 stars and 4,870 forks.
Trending score: 6.01; stars gained: +1,428; forks gained: +122.
Language: JavaScript
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
GitHub repository with 115,820 stars and 7,776 forks.
Trending score: 5.81; stars gained: +1,366; forks gained: +71.
Language: JavaScript
Topics: agent-skills, ai-agents, anti-slop, claude-code, codex, cursor
dsh-purge Community · DeepSeek Harness 社区维护版：宿主兼容、状态诊断、提示词管理、更新与本机备份回滚。基于小杨 / YuJunZhiXue 的 dsh-purge。
GitHub repository with 8,662 stars and 3,772 forks.
Trending score: 5.78; stars gained: +849; forks gained: +298.
Language: JavaScript
Topics: agent-tools, backup, deepseek, deepseek-harness, dsh, dsh-plugin
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
GitHub repository with 303,428 stars and 44,733 forks.
Trending score: 5.77; stars gained: +1,022; forks gained: +127.
Language: JavaScript
Topics: ai-agents, anthropic, claude, claude-code, developer-tools, llm
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
GitHub repository with 191,089 stars and 10,686 forks.
Trending score: 5.71; stars gained: +1,128; forks gained: +97.
Language: JavaScript
Topics: agent-skills, ai-agents, claude, claude-code, claude-code-plugin, cursor-rules
Nipmod package intelligence, Codex plugin, MCP workflows and public agent safety tooling.
GitHub repository with 0 stars and 0 forks.
Trending score: 0.00.
Language: TypeScript
Topics: ai-agents, cli, codex, codex-plugin, developer-tools, mcp
re!think it. System prompt teaching LLMs to execute two core tasks: complex answers without hallucinations, and creative ideas without clichés. Written in math-like logic, which LLMs parse better than plain language. Built for mid-to-high complexity tasks, featuring a Bypass branch to execute simple prompts directly without added cognitive overhead
GitHub repository with 14 stars and 0 forks.
Trending score: 0.00.
Topics: ai-agents, chatgpt-prompts, claude-prompts, cognitive-architecture, gemini-prompts, hallucination-prevention
Source repo for the blog post Stop Stuffing Your System Prompt: Build Scalable Agent Skills in LangGraph
GitHub repository with 14 stars and 1 forks.
Trending score: 0.00.
Language: Python
Topics: agent-skills, ai-agents, ai-systems, claude-code-skills, langchain, langgraph