Showing 30 of 5,048 · Category: LLM
Deep, self-verifying React Native & Expo engineering skills for AI coding agents — 79 skills with checkers that prove the work: architecture, Expo Router, Zustand, TanStack Query, testing, i18n/RTL, accessibility, EAS releases & more. Agent Skills open standard; works with Claude Code, Cursor, Codex & 70+ agents.
Ultra-lightweight, safe macOS lid-closed stay-awake CLI tool for AI agents, local LLMs, and background jobs
DeepSeek Harness 中文使用指南与资源大全：dsh 安装教程、模型与 API Key 配置、插件、Skills、MCP、报错排查
Бьёрн — ИИ-компаньон-викинг для Valheim: ходит следом, дерётся, рубит лес и разговаривает голосом (Claude Haiku, macOS)
The Virtual Filesystem Interface for AI Agents
Self-hosted email MCP server & REST gateway: give each AI agent its own IMAP/SMTP mailbox with sender/recipient allow lists, HTML-to-Markdown, attachments and calendar invites. One Docker container.
Give cold emails the cold shoulder. Auto-archives cold sales emails in Gmail. Runs securely in your own Google account for free.
面向外贸团队的 WhatsApp、LINE 与 Telegram 工作台：公司号码统一对外，客户分配给业务员；AI 通过 RAG（全文检索 + 内置向量库）从知识库检索依据、起草回复，经人工确认后发送。Self-hosted WhatsApp, LINE & Telegram workspace for export sales teams: shared company accounts, customers assigned to each salesperson, and AI reply drafts grounded in your knowledge base via RAG (full-text + built-in vector search).
Look inside any local LLM (GGUF from Ollama, LM Studio, Hugging Face, Jan, llama.cpp): layers, heads, vocabulary, chat template, weights. Explore it as a 3D graph, follow a token through every layer, edit it live (ablate, steer, ban, patch), diff two models, then bake or slim a new GGUF that still runs. CLI, web UI, browser demo. Runs 100% offline
AI agents write tested code for your project, test-first; you approve the key steps. Dashboard, terminal app, Android app, MCP server, code review and a supervisor. Claude, Codex, Copilot, Vertex AI or local models (Ollama). One Docker image.
AI 智能投标系统（开源基础版）：定时采集政府采购公告，按企业资质筛选标讯，AI 按招标文件要求组装标书、起草技术方案，交标前合规体检提示常见废标风险。支持 Mac、Windows 和 Docker。
monitor for a local LLM runtime (llama-swap, NInfer, Strata, more) -- metrics ported to berth.
Continual Learning Exam: evaluating how AI agents acquire, retain, and reuse experience.
AIが書いた日本語を、意味を変えずに読みやすく整える、指示欄に貼る400〜500字の指示文
한국어 단톡방 여론 시뮬레이션 엔진 — Korean group-chat public-opinion simulation for LLM personas (EXAONE · A.X · HyperCLOVA X · Solar · Kanana)
A macOS input method with AI commands in every text field: @improve polishes, @translate translates, @question answers, @claude hands off to Claude Code. Also a full pinyin input method.
[NeurIPS2026] Official implementation of Virtual Head Attention (VHA) for efficient large language model architecture and training optimization.
面向 Windows 11 双 Tesla V100 的本地 Qwen 推理项目：原生 C++/CUDA、中文便携启动器、TP2 通信优化、实验 MTP/DFlash、OpenAI/Anthropic 兼容 API 与 TCC/WDDM 切换。基于 NInfer 上游独立维护。
Supply-chain auditor for (abliterated) GGUF & .safetensor models: chat-template tamper detection, tensor fingerprints, plain-language reports
A beautiful Rust TUI for Codex and Claude Code token throughput — four views, local logs, honest metrics.
One native app for every AI coding agent. Rust + GPUI.
Explainable phishing email analysis combining email forensics, threat intelligence and LLM-assisted reasoning.
Statistical linter that finds the words, phrases and constructions that make text read as LLM output, measured against billions of words people wrote before 2022. CLI plus an Agent Skill for coding agents.
Panels, guardrails and quality-of-life mods for Claude Code: context, usage, live activity, notifications, safety rules, prompt coach, command hub.
ACRYL Blends - the extracted Cordis-based agentic framework: plugins, live extension, blueprints
arXiv LaTeX 源码 → LLM 段落级翻译 → ctex 双语中文 PDF：hjfy.top 开源复现，BYOK 任意 OpenAI 兼容端点，含 Web 阅读器与 Zotero 插件
Windows DFIR pipeline: from a KAPE collection, a memory image and network captures to an evidence-backed incident response report, with an LLM agent.
An Obsidian plugin that keeps track of your novel; where every character is and what they know, chapter by chapter. Bring your own AI.
Native Swift implementation of OpenJev, the Jev-compatible typed-decision server: yes/no, choice and score answers read from model probabilities, on Apple silicon Macs and in iPhone apps. Serves Verdict, Laya, DiffusionGemma and JevK5. Apache-2.0.