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.

基于麦当劳 MCP 的点餐人格测试：12 道题测出你的点餐人格，按性格给预算、出套餐、换配菜，并真实下单

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).

跑在 Android 的 AI Agent 智能体（Android / Kotlin / Compose）：可以做到模型直连加工具调用，读写文件、执行命令、跑 Ubuntu 全在设备上完成。消息分支、永久记忆、角色卡与技能包、MCP、定时任务、三档执行权限，Linux 沙箱等。官网 agent.ai.baiccb.cn

Open-source AwwO agent canvas: typed agent graphs, orchestration skills and hot-plug runtime workers

Brier, by Mangaba AI: typed, calibrated decisions (choice/score/noul) for Portuguese text, on your own servers. Decisões tipadas e calibradas em português. Brier v5 e Brier-0 (Qwen3-4B + LoRA); API /v1/decide. Licença comercial desde 5.0.0; v2 e v3 seguem Apache-2.0.

信息早餐：每天 7 点自动生成的个人 AI 资讯早餐 —— LLM 加工 + 偏好学习 + 三道入库闸门，全链路零成本

Agent Skills 把 X Space 变成中文干货笔记：下载 → 带说话人转写 → LLM 蒸馏 → 分享图 / Turn X Spaces into distilled Chinese notes with speaker labels & share cards.

Zero-compile runner and terminal Cockpit for 1-bit / 1.58-bit ternary LLMs on CPU. Real-time wattage telemetry, 70+ t/s on laptops, and 8B model support (macOS, Windows, Linux)

Ternary Bonsai 2: New 0.4GB Vision AI With 310 Tokens/Sec Speed! - 100% private visual document scanner and PII redactor running locally.

An evolving AI brain for Home Assistant

A home for your favorite AIs. An open-source Android app for individual and group conversations with multiple AI models.

把你的麦当劳账单跑一遍 diff —— 在「同等预算 ∩ 同等热量」约束下把历史订单重新点一遍，算出本可以省下多少钱、少吃多少热量。基于麦当劳 MCP，只读、零第三方依赖、完全确定性。非麦当劳官方产品。

🚀 High-performance OpenAI & Anthropic compatible API gateway and React 19 control plane for OpenCode Zen free tier with 100% resilience.

A live status board your AI agent writes while it works. Send a JSON board spec over MCP, HTTP or the CLI; a browser renders it live over SSE.

Rust rewrite of TelegramHelper: userbot + control bot (grammers), localhost dashboard, Zig SIMD helpers

Codex-style context window auto-management for DeepSeek Harness — lossless zero-model context rollover

Make your AI show its work. Yantra turns a description, from you or your coding agent, into interactive step-by-step diagrams, answer pages and books: laid out automatically, validated, and easy to share. CLI, MCP server, playground and Python SDK.

LayerMap MCP: a layered map of your codebase for coding agents: callers, callees and the impact of a change, for TypeScript, JavaScript, Go, Python and Java. MCP server, CLI, and plugins for Claude Code and Codex.

Group MCP tools by purpose, not by server — one switch per pack. Reference implementation + the seven design notes that only show up after you ship it.

Local-first research agent harness for deep learning: literature → reading → ideas → GPU experiments → papers & publication figures. DeepSeek-powered, custom OpenAI-compatible LLMs, SSH GPU orchestration.

Disposable cloud sandboxes for humans and AI agents

Turn a GitHub issue into a verified pull request: reproduces the bug with a test that must fail first, proves the fix in a Docker sandbox and opens the PR. Local-only (LangGraph + Ollama).

Lom (麓鸣) — AI agent workspace for one-person companies: a desktop commander leads Codex, Claude Code, Gemini CLI and your Android phones as one team. Built on AionUi and OpenMinis, thanks to both projects.

A simple-looking, not-so-simple lecture transcription and translation tool. Maybe more. ｜ 一个简约但不太简单的讲座听写与翻译工具，或许还有更多。

RAG chat assistant for MITRE ATT&CK, OWASP Top 10 and CISA KEV with citations, guardrail and evals

Real Google Search for AI agents, over MCP. Self-hosted, no API key. Real URLs, AI Overview and People also ask as typed JSON. Uses a real Firefox (Camoufox) on your IP or any proxy.

Open-source infrastructure benchmark for real-world performance, physical behavior, and true unit economics of AI workloads on accelerators

An Orca best practice built around Matt Pocock's engineering skills. His chain stays: grill-with-docs, to-spec, to-tickets, then implement or implement-spec, closing with code-review. Orca supervises each step in its own worktree, with gates and merge. Not affiliated with or endorsed by Matt Pocock.

LangChain.js 中文入门电子书 · 9 章 38 个可运行示例。本书适合：会 JavaScript / TypeScript，但没接触过 LangChain；想用 JS/TS 构建 AI 应用：聊天机器人、知识库问答、智能体……；希望边读边跑代码，而不是只看理论。另有 VitePress 站点：https://cleversnail.github.io/lang-chain-js-cn/