Showing 30 of 5,094 · Category: LLM
Local desktop launcher for LLM inference on Intel Arc Pro B70 — rootless, stdlib-only, one-command install
Two-rank tensor-parallel LLM serving over USB4v2 between AMD Strix Halo hosts: a custom Linux thunderbolt stream transport, self-healing link, and gufo TP2 integration
Production-grade Model Context Protocol (MCP) server for Bale Messenger with 32 tools for LLMs (Claude, Cursor, Antigravity) to interact with user accounts.
Open-source NotebookLM alternative. Chat with your sources with citations, and turn them into reports, flashcards, quizzes, mind maps and slide decks, with your own OpenAI, Anthropic or Gemini key or local Ollama / LM Studio models. Local-first, no account.
Implementation of EmbeddingGemma 2, Google DeepMind's 740M parameter multimodal embedding model, in Pytorch
Self-hosted AI code generator for long files & projects — contract-driven dual-end generation, zero-token quality gate, auto-continue. Bring your own DeepSeek key.
AI-powered website builder that uses multi-agent orchestration to generate production-ready websites from natural language prompts.
Open-source AI assistant that lives in your MacBook notch, with Ledge, a 3D desktop companion. Native Swift agent, private by design.
A code reviewer that reports only what it can prove: a test that shows the bug, or the data that confirms the risk. Open source, built by a fleet of AI agents with Saphan Studio for the Open Agent Hackathon 2026.
11 家 AI 同桌玩你画我猜与画画接龙：高清 Live2D、角色互怼、OpenRouter 与自定义 API、可重构视频的对局记录。
A Claude Code mod that keeps your cache warm, so you pay 96% less to re-read your conversation
A private macOS virtual machine on your Mac, operated by an AI agent. You chat; it clicks, types and hands back checked results. Also a CLI and MCP server for coding agents.
Catalog of silent failures in RAG systems and AI agents, with reproduce, detect and mitigate code
Build a small model for your task, on hardware you control. Bring labeled examples. Fine-tune locally, compare against simple baselines, and export to GGUF or safetensors. Pause and resume supported training runs across Mac and Linux.
Known open bugs in your exact dependency versions, put where your coding agent reads them (AGENTS.md/CLAUDE.md, pre-edit hook for 20 agents, MCP).
把一本长篇（小说/剧本/系列文）加工成两份文件喂给大模型：整书总结（事实圣经）+ 例子集（文风语料）。一片一个任务，可开几十路子代理并行；文风部分从语料自身拟合，含搭配表 / 零频黑名单 / 逐句 z / 0 频探针。
One-click AI chat handoff and full-fidelity export (PDF, Markdown, Word, HWPX…) for ChatGPT, Claude, Gemini and Grok — Chrome MV3 extension
一个基于 twikit 实现的 X (Twitter) MCP 服务端，轻量级工具。支持AI调用X平台功能，包含发推、回复评论、读取推文回复、私信收发、抓取用户主页详细信息、查看推文互动数据、推文搜索、点赞、转推、删推等多项工具。适用于 Claude Desktop、Cursor 等支持 MCP 协议的客户端。
每天读完心理学和精神医学的新研究，挑出值得看的几条。期刊、预印本、学会和媒体 94 个信源，模型精选与中文日报。基于 AIHOT 开源框架。
Second brain for your AI: a self-hosted memory vault your AI agents read and write over MCP. Install with npm, Docker or one command.
A private AI assistant that runs open LLMs (Gemma 4, Qwen) entirely on your Android phone: chat, photos, documents, voice, cited web research and phone actions, with no account or server.
Tell your Mac what to do with your files in plain English. Review the exact plan, approve, and undo anything. Fast, private, and fully local.
Self-hosted multi-model agent with JitRL memory, auditable council runs, SSH operations, live server screen, and macOS/Windows desktop client
Desktop IDE to run Claude Code, Codex, OpenCode and Gemini CLI as a team: a conductor agent plans the work, the agents code in parallel in isolated worktrees and talk to each other, and you review and merge the result.
AI Judge: Jira/Markdown story -> acceptance-criteria gate -> AI-designed test cases -> executed in Chrome by an AI senior test engineer -> pass/fail with evidence -> human-approved Jira defects
Masks API keys, secrets and personal data (PII) on your machine before your AI coding agent sees them. Works with Claude Code, Codex CLI and Gemini CLI.
Voice dictation for macOS and Linux: hold a key, speak, and clean text appears in any app. Offline by default. Free and open source (MIT).