Skip to content
Back to search

glassbox

An AI agent you can see inside: .NET 10 agent loop, MCP tools and a live trace panel. Runs on a Jetson Nano.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nexusframe--glassbox/badge.svg)](/listings/nexusframe--glassbox)

HTML

<a href="/listings/nexusframe--glassbox"><img src="/api/listings/nexusframe--glassbox/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 69 lines
  1. # Glassbox
  2. Glassbox is an AI agent you can see inside. You chat with it in the browser. Next to the chat, a live panel shows each step the agent takes: the guards, the model calls and the tool calls. The agent loop is our own code, and the tools run on a separate MCP server.
  3. Demo: <https://glassbox.wasyluk.pl>
  4. ## What the visitor sees
  5. ```text
  6. ┌─ Chat ─────────────────────┐┌─ How the agent works ───────────────┐
  7. │ You: Time in Tokyo, and ││ [1] question 0 ms │
  8. │ 17% of 240? ││ [2] L0 OK budget 12% of day │
  9. │ ││ [3] model ▶ 2 tools 410 ms │
  10. │ Agent: 23:14 in Tokyo. ││ ├─ get_datetime(Tokyo) 4 ms ✓ │
  11. │ 17% of 240 is 40.80. ││ └─ calculate(240*0.17) 3 ms ✓ │
  12. │ ││ [4] model ▶ answer 520 ms │
  13. │ [sample questions] [PL|EN] ││ [5] end 2 turns, 1140 tok, $0.002 │
  14. └────────────────────────────┘└─────────────────────────────────────┘
  15. ```
  16. ## Where it runs
  17. ```text
  18. user's browser
  19. │ opens page │ chat: fetch POST (stream)
  20. ▼ ▼
  21. ┌──────────────────┐ ┌───────────────────┐
  22. │ Cloudflare Pages │ │ Cloudflare Tunnel │ no open
  23. │ chat page, video │ └─────────┬─────────┘ inbound
  24. └──────────────────┘ ▼
  25. ┌─ small arm64 server (Docker) ──────┐
  26. │ ┌────────────┐ MCP ┌──────────┐ │
  27. │ │ Api + loop │ ─────▶ │ Tools │ │
  28. │ └─────┬──────┘ └──────────┘ │
  29. └───────┼────────────────────────────┘
  30. ▼ HTTPS
  31. ┌──────────────────┐
  32. │ OpenRouter ──▶ │
  33. │ cheap cloud LLM │
  34. └──────────────────┘
  35. ```
  36. ## Run locally
  37. You need Docker. Steps:
  38. ```sh
  39. cp deploy/.env.example deploy/.env # then set OPENROUTER_API_KEY
  40. curl localhost:8080/health
  41. ```
  42. Serve the page:
  43. ```sh
  44. python3 -m http.server 5500 -d web
  45. ```
  46. `web/config.js` points to port 8090. To use it, set `API_PORT=8090` in `deploy/.env`.
  47. ## Privacy
  48. Prompt text is not written to disk or logs.
  49. A public instance must name its data controller (RODO/GDPR): set `GLASSBOX_OPERATOR` and `GLASSBOX_CONTACT` (an e-mail or an `https://` URL) in `web/config.js` at deploy time. The first-view notice shows them.
  50. ## How it is built
  51. The code is written with AI coding agents; I read, review and accept every change, and I decide the direction. The ADRs in `docs/` show that work.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.