Showing 30 of 5,016 · Category: LLM
All-In 播客中文版：全部单集的官方音频、视频、文稿与 AI 中文精读 | Chinese companion site for the All-In Podcast
Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: System 1.5 decision models that think in loops, not tokens.
Crow: build your second brain from the documents on your computer. Downloads for macOS, Windows and Linux.
ASD-STE100 (Simplified Technical English, Issue 9) for Claude Code: /asd mod with an STE pane, agent skill, and linter. Inspired by Karpathy's "80% ASD-STE100" tip.
Desktop coding agent app for macOS and Linux. Any model, on your code and UI. Built on DeepSeek Harness.
data agent 从问数到数据开发治理，自然语言问数、SQL 查询、图表看板与多 Agent 专家团分析，支持 MCP 数据源、自带模型和本地 Ollama。
asmsense: a small model that names and describes functions in stripped x86-64 binaries. Open dataset, baselines, and LoRA experiments.
实时语音 agent 架构手册。四种链路形态（级联 / 半级联 / S2S / 全双工）的取舍；判停、打断、首音、工具回合、会话恢复、音频前处理、评测七个机制的设计空间；pipecat、livekit-agents、TEN、unmute、moshi、Qwen3-Omni、CosyVoice、FunASR、xiaozhi 等 28 个开源项目在这些机制上的实现，分析到文件和函数并标注 commit。附框架与模型对比矩阵、选型决策树。
把 FutureSearch 的异步任务 API 反代成 OpenAI 兼容端点 + 管理面板 + 两组 MCP（研究 / 本地文件）。号池、租户额度、本地预览。
Instinct: single-forward-pass decision models (choice / true-false / score) returning a probability per candidate
三菱 PLC 编程与工程助手。 MCP server and AI workbench for Mitsubishi PLC programming with GX Works2. Generate Ladder and Structured Text, edit native FBD, and review versioned projects with CPU-aware RAG and diagnostics.
OPENCODE APK ANDROID 📱 Native AI coding agent + On-device APP FACTORY + PERSISTENT MEMORY 🚀 PLUG & PLAY · FULL DEVICE CONTROL · NO ROOT REQUIRED · Crafted in Spain 🇪🇸.
Smart component library for AI apps. With Chai UI, every AI model is controlled from one place, through a unified interface.
一本开源的 AgentScope Java 中文教程：7 篇 44 章、839 页成书体量的完整 Markdown 源稿，由浅入深覆盖从第一个 Agent 到生产级 Agent 平台的全部主题。
TalkTact · 微信聊天助手（LSPosed 模块）：聊天页悬浮候选回复卡片（★最推荐+理由、单条改写），多套提示词 skill，角色关系档案；直通/模型分级双模式，本地代理让 API Key 不出 App 进程，会话白名单，以及本机离线的图片文字识别（OCR）。只填输入框，绝不自动发送。
DSH 防退化套件｜不止打断，还会清创：把退化的思考块从模型可见历史里折叠掉，下一轮不再回传。复读分两型——A 型同一句死磕、B 型短句轮换（最难抓，实测英文 8 块全漏）。两个插件一套闭环，缺一个都会漏。
Review what your coding agent changed, without leaving Rex. Think herdr-reviewr, but for Rex.
Native Android client for OpenCode Go. Chat with GLM, Kimi, DeepSeek, Qwen and more, with streaming Markdown, web search, thinking effort and usage limits. Kotlin + Jetpack Compose.
A production-grade reference implementation for LLM agent systems: flow declared as a LangGraph graph, Pydantic AI for typed agents, generated WebSocket and REST contracts, human approval on irreversible actions, tracing and evals.
把 OpenCode 的免费模型（big-pickle、LongCat、MiMo、Nemotron、Space Bunny 等）接进 DSH 的模型选择器，作为 opencode-xdbridge 分组使用，并在设置 → OpenCode-XD 里提供一个可视化的交互入口。
Open-source Ask AI for your docs, with an MCP server for agents: cited answers on your own model key, from one static index built with your site. No vendor, no vector database. Starlight, Docusaurus and VitePress plugins, Next.js, or one script tag.
Your own team of AI bots in one self-hosted binary: spaces, every account you have, handoffs, approvals and routines. Rust + React.
Voice I/O for LLM chat UIs: dictation, read-along and a voice-reactive aura, for any OpenAI-compatible speech engine.
An AI that plays Pokémon FireRed on a real Nintendo Switch: capture card in, emulated Bluetooth controller out. LLM strategist + deterministic skills, map localisation from the pret decomp, ACE toolkit.
Disciplined AI coding mode. Understand deeply, write minimally, never hallucinate, stay consistent. Based on Ponytail & LLM Wiki.
Measures how much code LLM agents waste. 5 tasks, sandboxed, weekly snapshots, contestable references.
Realtime dashboard for the Halogen LLM inference server
Self-hosted LLM gateway audit station: model fingerprint attribution, cache/tool/web/thinking evidence, IQ and integrity scores.
Open-source personal AI assistant that lives in your WhatsApp: email, calendar, group plans, reminders and errands. Self-hosted, and it asks before it sends anything as you.