#llm
AWS Bedrock Bridge for Copilot Chat
abhimanyus1997
Access AWS Bedrock models (Claude, Llama, Nova, DeepSeek) inside GitHub Copilot Chat with streaming, tool calling, and custom model support.
Markdown2Anything — 一篇 Markdown 一键发到微信/知乎/小红书/Twitter
marsggbo
写完一篇 Markdown，一键发布到微信公众号、知乎、小红书、Twitter(X)：自动截长图、AI 生成平台文案与串推、自动传图填字。支持 LaTeX 公式、10 套主题、实时预览。
Claude Code Turn Usage Monitor
shivaraj-arch
Real-time status bar monitor for Claude Code — context fill %, cache hit rate, and per-turn API-equivalent cost after every response.
MicroDegree Labs
MicroDegree
Guided hands-on GenAI practice, inside VS Code.
cv4vs Agents
Corsinvest
Claude Code inside Visual Studio — agentic coding with a rich chat pane and an interactive terminal, wired into the editor, solution and debugger through an in-process MCP server.
Prompt Foundry
sdevries
Forge complex AI prompts and specs from a library of evolving blocks.
AI Code Assistance
dataaialexmendes89
Six specialist agents in one chat — coding, data analytics, data science and AI engineering. 16 real tools, 16 slash commands, and a planner that splits the work. Your keys or fully local; you pick the model per agent.
Snake Agent
ClaudioRodrigues
Local AI agent for VS Code — run LLMs locally with Ollama and get a Copilot-like experience without the cloud.
LLM Local Router
Shoferdev
VSCode extension providing direct access to multiple LLM providers with composite model failover — no external router service required
Claude Prompt Meter
ryukenshin546-a11y
Per-prompt token & cost for Claude Code — live status-bar meter + dashboard with spend heatmap. Reads local logs only: no API key, no network. Thai/English.
Chutes AI Provider for GitHub Copilot Chat
mikesoft
Integrate Chutes.ai open-source models (DeepSeek, Qwen, GLM, Kimi and more) into VS Code's GitHub Copilot Chat — auto-discovered, with streaming, tool calling and vision.
Shofer Router
Shoferdev
VSCode extension providing direct access to multiple LLM providers with composite model failover — no external router service required