interaction-nets
Lafont's interaction nets for optimal parallel λ-reduction. Graph rewriting
npx skills add majiayu000/claude-skill-registry --skill interaction-nets --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Interaction Nets Skill > *"The only model where parallelism is not an optimization but the semantics itself."* ## Core Concept Interaction nets are a graphical model of computation where: - **Nodes** (agents) have typed ports - **Wires** connect ports - **Reduction** happens when two **principal ports** meet - **No global control** — all reductions are local and can happen in parallel ``` ┌─●─┐ ┌───┐ ───┤ ├─── → ───┤ ├─── └─●─┘ └───┘ principal ports result meet ``` ## Why It's Strange 1. **No evaluation order** — unlike λ-calculus, no choice between CBV/CBN 2. **Optimal sharing** — work is never duplicated (Lamping's algorithm) 3. **Massively parallel** — every independent redex reduces simultaneously 4. **Linear by default** — resources used exactly once (linear logic connection) ## Interaction Combinators Lafont's universal basis (3 agents): ``` ε (eraser) δ (duplicator) γ (constructor) │ /│\ /│\ ● ● │ ● ● │ ● │ │ ● ● ``` ### Reduction Rules ``` γ ─● ●─ γ → cross-wire (annihilation) δ ─● ●─ δ → cross-wire (annihilation) γ ─● ●─ δ → duplication (commutation) ε ─● ●─ γ → erase both aux ports ε ─● ●─ δ → erase both aux ports ``` ## HVM / Bend Implementation [Bend](https://bend-lan
- Core Concept
- Why It's Strange
- Interaction Combinators
- Reduction Rules
- HVM / Bend Implementation
- Install & Run
- λ-Calculus Encoding
- Abstraction (λx.M)
- Application (M N)
- β-reduction as Interaction
- Optimal Reduction
- Symmetric Interaction Combinators
- Code Examples
- Minimal Interaction Net in Julia
Install Bend cargo install hvm cargo install bend-lang Run with parallelism bend run program.bend -p 8 # 8 threads
What does the interaction-nets skill do?
Lafont's interaction nets for optimal parallel λ-reduction. Graph rewriting
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill interaction-nets --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.