Show HN: Desktop GUI sandbox for AI agents and MCP servers
Nilbox is a desktop sandbox designed for running untrusted AI agents with enhanced security features. It utilizes real VM isolation and a zero-token architecture to protect sensitive API keys from exposure. The system allows for seamless integration of AI agents while ensuring that real credentials are never compromised.
- ▪Nilbox provides real VM isolation, ensuring that workloads run in a full virtual machine rather than a container.
- ▪The zero-token architecture prevents API keys from entering the guest environment, swapping them in-flight for trusted domains only.
- ▪Nilbox allows AI agents to operate without code changes, maintaining their functionality while enhancing security.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,267 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/rednakta/nilbox |
| Publication time | Tue, 26 May 2026 05:08:26 +0000 |
| Retrieval time | 2026-05-26T05:22:43.569Z |
| Last seen | 2026-05-26T05:22:43.569Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | uyX5vrXd4f9O · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Desktop sandbox for running AI agents you don't trust — with real VM isolation and zero-token security. Quick Start · Use Case · How It Works · Features · Docs Why nilbox? AI agents need shell access, filesystem access, and outbound API calls. Running them in a container on the host kernel isn't real isolation — especially when those agents handle real credentials. nilbox takes a different approach: Real VM isolation — workloads run in a full virtual machine, not a container Zero-token architecture — API keys never enter the guest; the host proxy swaps tokens in-flight for trusted domains only Host-controlled network — all outbound traffic routes through VSOCK to a domain-gating proxy with rate limits and approval prompts If you wouldn't give someone your API keys, don't put those keys…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.