Nucleus: Enforced permissions for AI agents – policy+enforcement in one stack
Nucleus introduces a system to enforce permissions for AI coding agents, preventing untrusted input from combining with privileged actions. It utilizes two primitives, join and flows_to, to ensure information flow control and maintain session integrity. The framework includes features for tracking data provenance and blocking unsafe operations, enhancing security for AI-assisted coding tasks.
- ▪Nucleus prevents AI coding agents from combining untrusted input with privileged actions.
- ▪The system employs two primitives, join and flows_to, to enforce information flow control.
- ▪It tracks data provenance and blocks dangerous combinations, ensuring safe coding practices.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,312 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/coproduct-opensource/nucleus |
| Publication time | Wed, 20 May 2026 06:38:07 +0000 |
| Retrieval time | 2026-05-20T06:45:00.443Z |
| Last seen | 2026-05-20T06:45:00.443Z |
| 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 | Xt5gAHp0x-Vt |
| 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
Nucleus Nucleus prevents AI coding agents from combining untrusted input with privileged actions, and proves what was and wasn't allowed. Two primitives — join and flows_to — enforce information flow control with four algebraic laws. Once web content enters a session, it cannot silently reach git push. That property is machine-checked, not hoped. let mut state = FlowState::bottom(); // clean session state.join_operation(Operation::WebFetch); // tainted by web content assert!(!state.flows_to(SinkClass::GitPush)); // can't push tainted data Quick Start cargo install --git https://github.com/coproduct-opensource/nucleus nucleus-cli nucleus audit # scan agent configs (Tier 0, no runtime) nucleus run --local "your task" # run with enforced permissions (Tier 1) Every tool call flows through the…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.