ArrowSpace Skills

Portable skill definitions for working with ArrowSpace — a spectral vector search library that goes beyond cosine similarity by incorporating graph Laplacian eigenstructure.

ArrowSpace adds a spectral dimension to vector similarity, enabling search that considers both semantic content and structural role in the dataset.

Quick Start

pip install arrowspace

Then:

from arrowspace import ArrowSpaceBuilder
import numpy as np

items = np.array([[0.1, 0.2, 0.3], [0.0, 0.5, 0.1], [0.9, 0.1, 0.0]], dtype=np.float64)
graph_params = {"eps": 1.0, "k": 6, "topk": 3, "p": 2.0, "sigma": 1.0}
aspace, gl = ArrowSpaceBuilder().build(graph_params, items)

query = np.array([0.05, 0.2, 0.25], dtype=np.float64)
hits = aspace.search(query, gl, tau=1.0)
print(hits)  # [(0, 0.99), (1, 0.76), (2, 0.22)]

Resources

Resource	Link
JOSS paper	doi:10.21105/joss.09002
Rust library	github.com/Mec-iS/arrowspace-rs
Python bindings	github.com/tuned-org-uk/pyarrowspace
PyPI package	pip install arrowspace
crates.io	cargo add arrowspace
Presentation 1	Spectral Indexing overview
Presentation 2	ArrowSpace deep-dive
Design article	tuned.org.uk — Part 2: Semantic Basins

Skills

This repo contains skill definitions that teach AI agents how to use ArrowSpace:

Skill	File	What it covers
ArrowSpace Core	skills/arrowspace-core.md	Builder, configuration, building signal graphs
Vector Search	skills/arrowspace-search.md	Querying, λτ scoring, search parameters
Spectral Analysis	skills/arrowspace-spectral.md	Spectral methods, graph characterisation, diffusion

Adding to an AI Agent

OpenCode — symlink or copy SKILL.md into .opencode/skills/:

cp SKILL.md .opencode/skills/arrowspace/SKILL.md

Claude Code — reference in CLAUDE.md or add to project instructions.

Copilot / Cursor — include the relevant skills/*.md content in your custom instructions.

Any agent — point it at this repo: "You have access to the ArrowSpace skills at skills/."

Python Package

Install the skill utilities directly:

pip install arrowspace-skills

from arrowspace_skills import (
    suggest_params,              # heuristic graph parameters
    build_index,                 # one-shot index builder
    tune_tau,                    # grid search over spectral gate
    search_with_recall,          # query with result cap
    item_lambdas,                # per-item lambda-tau scores
    sorted_lambdas,              # lambda-tau-ranked item list
    explain_spectral_properties, # eigendecomposition diagnostics
    spectral_summary,            # human-readable spectral report
)

See arrowspace_skills/ for reusable helper functions.

License

Apache 2.0 — same as arrowspace-rs.