# Outpostkrewhirl86/Capri-AI > Capri is a local-first desktop AI agent for Windows with a cyberpunk HUD. It plans and executes tasks on your machine using files, apps, terminal, and browser, powered by pluggable backends like Claude Code, Codex, or Antigravity. - Magnitude: 1.5 out of 10 — Steady - Stars: 346 total · +1 star measured 2026-11-16, 00:28–09:42 UTC, ≈ 2 by evening - Star trust: star growth looks organic - Category: AI agents · License: MIT · Created: 2026-11-14 · Last push: 2026-11-15 - GitHub: https://github.com/Outpostkrewhirl86/Capri-AI · Page: https://gitnova.dev/en/r/Outpostkrewhirl86/Capri-AI ## Useful for - Automate file operations like batch renaming or moving folders using natural language commands. - Run terminal commands and capture output in a sandboxed session with audit logs. - Delegate code refactoring or bug hunting to a connected coding backend like Claude Code. ## Why it’s here - Star-counter measurements on 2026-11-16 (UTC), 00:28–09:42: 345 → 346 stars (+1). This is the change over that interval. - Estimated end-of-day forecast: about +2 stars, using observed gains and the previous day. - The repository is 2 days old and already has 346 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - Top new repositories this week: #126. - About 126 forks a day — people are taking the code. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 54 - Issues and pull requests: 0 - Watchers: 11 - Average over the last week: 116 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 1 - Latest release: 1.0.1 (2026-11-15) ## Stars per day, last 3 days (oldest → newest, today is partial) 2026-11-14 … 2026-11-16: 345, 0, 1 ## Magnitude by day, last 3 days 11-14 1.3, 11-15 7.2, 11-16 1.5 ## Spotted in now - Top new repositories this week: #126 ## More in this category 1. **Tencent/LoopForge** — 8.8 · Breakout · AI agents · Go · +592 stars measured 2026-11-16, 00:28–09:35 UTC, ≈ 1,260 by evening Self-hosted workspace for delivering software with coding agents: a Main Bot opens Docker sandboxes, delegates to project roles, and runs SOPs (agent, script and human-gate nodes) to produce PRs with review built in. Full card: https://gitnova.dev/en/r/Tencent/LoopForge.md 2. **deepseek-ai/chat-demo** — 8.4 · Breakout · AI agents · TypeScript · +753 stars measured 2026-11-16, 00:28–09:35 UTC, ≈ 1,799 by evening A static chat demo powered by the DeepSeek API that runs entirely in the browser without a backend; users enter their own API key to chat with streaming replies, attachments, and speech features. Full card: https://gitnova.dev/en/r/deepseek-ai/chat-demo.md 3. **hitkeeen/blender-ai-mcp-addon** — 8.4 · Breakout · AI agents · +765 stars measured 2026-11-16, 00:28–09:35 UTC, ≈ 1,725 by evening AI assistant and MCP server for Blender: visual chat, scene tools and multi-agent workflows with ChatGPT, Claude, Gemini, Ollama and other models. Full card: https://gitnova.dev/en/r/hitkeeen/blender-ai-mcp-addon.md 4. **GoogleChrome/modern-web-guidance-src** — 8.0 · Breakout · AI agents · TypeScript · +461 stars measured 2026-11-16, 00:28–09:35 UTC, ≈ 1,155 by evening A set of skills and a CLI that embed modern web platform APIs, best practices, and browser compatibility data into coding agents so they stop generating legacy code. Full card: https://gitnova.dev/en/r/GoogleChrome/modern-web-guidance-src.md 5. **ag-ui-protocol/ag-ui** — 7.9 · Breakout · AI agents · TypeScript · +405 stars measured 2026-11-16, 00:28–09:35 UTC, ≈ 892 by evening An open event-based protocol connecting AI agents to user-facing applications: it standardizes agent events and inputs and works over SSE, WebSockets and other transports. Full card: https://gitnova.dev/en/r/ag-ui-protocol/ag-ui.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-11-16 09:47 UTC, updated every 30 minutes.