TranslatedMultimodal retrieval in practice: intent recognition, prompt engineering, Qwen LoRA, EmbeddingGemma 2, and InfoNCE contrastive learning. Includes real demos, integration of your own data, training and evaluation, and a learning guide to RAG retrieval components.
Give every page a soul.
The UI SDK and agent-ready developer toolkit for AI factories, robotics, and autonomous vehicles.
The repository host gives no description.
AI Agent Developer Interview Questions
Set up Claude Code once. Your whole company gets it. Self-hosted Claude Code and Codex with your company files, team skills, MCP and per-person folder permissions.
TranslatedMcCosmos · 麦门星图 (Maimen Xingtu, "McDonald's Star Map") | A Skill for meal nutrition comparison and alternative discovery based on McDonald's MCP, providing a standalone runnable package, explainable analysis, and a 3D star map.
CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework
Agent-first slide decks: comment under a slide, and your coding agent (Claude Code or Codex) makes the change and replies on the slide.
The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. Industrial protocols (OPC-UA, Modbus) on the roadmap.
A practical directory of agent loop skills, workflow automations, and cloud delivery recipes for DSH, Codex, Claude Code, and compatible agents.
Translated麦门双预算军师 (Maimen Dual-Budget Strategist) · McDonald's China MCP contest entry | Dual-budget (money + calories) McDonald's China MCP Agent Skill with 3-tier meal plans, coupon math and a holographic persona card. One budget for money and one for calories; a meal is only put together when it passes both gates at once: 88,788 combinations are exhaustively searched locally, giving best-value / most substantial / most balanced tiers and the price after coupons.
Custom elements catalog for all kind of projects and frameworks.
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
Inspect, evaluate, and stress-test an existing semantic layer. Runs fully offline.
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
Best Memory Plugins for AI coding agents: Claude Code, Codex, Cursor, OpenCode, Cline and more. Glen, claude-mem, Supermemory, Hindsight, agentmemory, Mem0, Cognee, MemPalace and others ranked on automatic capture vs tool calls, local vs hosted, team sharing, privacy and install steps, plus built-in agent memory compared.
Agent-ready video dubbing toolkit for Apple Silicon: local Chinese speech and bilingual subtitles. Single-speaker preview; human review required.
Senrelay · 续境 — Local-first macOS multi-Agent conversation relay, source-linked persistent memory, and unified host configuration workbench.
See what your AI coding agents are doing and what they cost. Live activity map, tokens, cost, context and quota for Claude Code, Codex and OpenCode, in VS Code and a terminal dashboard. Plus usage reports, account switching and an MCP server your agent can query.
Agent-native way to access any website. Bridging agent CLI and web GUI through API.
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
I can keep a SSHecret
- ssh
- ssh-agent
- ssh-agent-forwarding
- ssh-keygen
Self-hosted remote control for your coding agents: Claude Code and Codex chats, approvals, terminals, files, git and dev-server previews for every computer you own, from the browser or your phone. One Docker container on your own server.