🚀 TradingView Agent — Web Top

Run TradingView Agent inside a browser-based Linux desktop with free LLM support through ModelRelay.

Chart Analysis and Pine Script coding will never be the same ...

TradingView-Agent gives you a fully functional TradingView AI assistant in your browser with Hermes-CLI or Claude Code CLI in under 10 minutes — no powerful PC, no Docker on your machine, no GPU required.

Just open this repo in a GitHub Codespace, start the container and you will get:

• All the goodness of Hermes-Webtop because it is a copy clone of it plus...
• A preconfigured and installed TradingView Desktop with CDP enabled in Ubuntu MATE desktop (WebTop) for agentic automation
• Just open the webtop at port 3000 and following the prompts from these repositories:
  • https://github.com/LewisWJackson/tradingview-mcp-jackson#one-shot-setup
  • https://github.com/jackson-video-resources/claude-tradingview-mcp-trading

Will be interested to see how you might automate research and analysis of trade with this.

🚀 Quick Start (5-10 minutes)

1. Open this repository in a GitHub Codespace (big green "Code" button → Codespaces → New)

   It is recommended that you use 4 cpu core and 16G codespace.

   

2. In the Codespace terminal run:

   make start

   

3. Wait ~60 seconds after first launch. It takes about 5-7 minutes if docker image is not loaded yet. When the web desktop URL appears in the Codespace Ports tab, click it.

   

   Demo on pre-installed WebApps

   

4. Open WebTop on a browser - port 3000

   • Open a terminal and use your favorite agent CLI. It could hermes or claude
   • Type in your prompts as per the youtube/github instructions and start from there.

🔧 Features

• Zero local install — everything runs in browser via GitHub Codespaces
• Free-tier friendly — uses ModelRelay, Ollama daily cloud credits or NVIDIA Build API fallback
• Persistent config — docker volume backup and restore after Codespace recreation
• Easy backup/restore — make backup / make restore
• One-command everything — powerful Makefile + clean docker-compose.yml
• Auto-start ModelRelay — Default configuration for Free LLM API to Hermes
• Auto-start OmniRoute — You need some configuration before it work but it is flexible and powerful
• Auto-start Ollama — custom init script on WebTop boot
• Colima / local Docker support ready
• Built-in code-server IDE — browser-based VS Code on port 8888
• Multiple AI VSCode Extension preinstall/config with ModelRelay - Cline, Hermes and ClaudeCode
• Mnemon as default memory provider - a knowledge store for Hermes with intent-aware recall, importance decay, and auto-deduplication

🔒 Security: Protected by GitHub Authentication

The WebTop URI is automatically protected — no one else can reach it.

GitHub Codespaces forwards ports privately by default (this is the setting the make start command uses). According to official GitHub documentation:

"All forwarded ports are private by default, which means that you will need to authenticate before you can access the port." "Privately forwarded ports: Are accessible on the internet, but only the codespace creator can access them, after authenticating to GitHub."

How the protection actually works

• The URL you click in the Ports tab (https://<your-codespace>-3000.app.github.dev) is guarded by GitHub authentication cookies.
• These cookies expire every 3 hours — you'll simply be asked to log in again (super quick).
• If someone tries to open the link in an incognito window, via curl, or from another computer without being logged into your GitHub account, they are redirected to the GitHub login page or blocked.
• You (and only you) can access the full Ubuntu desktop, the browser inside it, Ollama, Hermes, and everything else.

Extra security layers built-in

• The entire environment runs in an isolated GitHub-managed VM — not on your laptop.
• Codespaces are ephemeral: delete the codespace and everything disappears (except the backed-up volume you control).
• TLS encryption is handled automatically by GitHub.
• The GITHUB_TOKEN inside the codespace is scoped only to this repo and expires when you stop/restart.
• We never set the port to "Public" or even "Private to Organization" — it stays strictly private to you.

Bottom line: This is actually more secure for experimentation than running Docker locally on your personal machine (no accidental exposure, no firewall holes, no persistent processes on your hardware).

For production use we still recommend moving the same Docker image to your own VPS or server with additional hardening (firewall, HTTPS reverse proxy, strong secrets, etc.). This Codespace version is perfect for safe testing and development.

💾 Backup & Restore

Your configuration and settings are persisted in a Docker volume. The project includes convenient make targets to back up and restore this data in codespace:

make backup          # creates backup/hermes_config_backup.tar.gz
make restore         # restores from backup/hermes_config_backup.tar.gz

When to Use It

• Migrating from GitHub Codespaces to a local machine or VPS
• Testing experimental changes without risking your current setup
• Quickly cloning your working environment into a fresh Codespace or container

How to Migrate to a New Environment

• In your current environment, run make backup.
• Download the generated file: backup/hermes_config_backup.tar.gz.
• Place the file in the backup/ folder of the new environment.
• Run make restore.

💡 Tip: Always back up before making significant changes. The restore process will overwrite the existing volume data, so test in a separate environment first if you're unsure.

🛠️ Advanced Usage

Run locally (no Codespaces)

make build-local             # especially if you modified the ./docker/Dockerfile
make start-locally-baked     # start from your local baked image

🤝 Contributing

This is a community project — every star, issue, or PR helps enormously! Feel free to open issues for bugs or feature requests.

📄 License

MIT — see LICENSE