New sw dev tool for safe local AI usage
Think docker compose up for AI-agent-safe development: your agent gets what it needs to work, nothing more. Why Running an AI agent against your codebase means giving it a shell. That shell can curl, git push, aws s3 cp, and read every .env on your disk. sde draws the boundary in the right place: Egress allowlist by default — the workspace can only reach the domains you list.
- ▪Think docker compose up for AI-agent-safe development: your agent gets what it needs to work, nothing more.
- ▪Why Running an AI agent against your codebase means giving it a shell.
- ▪That shell can curl, git push, aws s3 cp, and read every .env on your disk. sde draws the boundary in the right place: Egress allowlist by default — the workspace can only reach the domains you list.
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,686 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
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/alexs60/safe-sde |
| Publication time | Wed, 29 Jul 2026 01:53:45 +0000 |
| Retrieval time | 2026-07-29T02:31:19.838Z |
| Last seen | 2026-07-29T02:31:19.838Z |
| 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 | frBDSffQLAmh · 1 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
sde Role-separated container isolation for AI-assisted development on macOS. sde is a single-binary CLI that boots a private, network-isolated environment for your project — a workspace container where your code (and AI agents) run, role-separated data services, an egress firewall, and a credential broker that keeps secrets on the host and out of the container filesystem. Think docker compose up for AI-agent-safe development: your agent gets what it needs to work, nothing more. Why Running an AI agent against your codebase means giving it a shell. That shell can curl, git push, aws s3 cp, and read every .env on your disk. sde draws the boundary in the right place: Egress allowlist by default — the workspace can only reach the domains you list.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.