Current graph state: nodes, links, health, configuration

Save a conversation turn: keyword, topic, domain, intent, sentiment, entities, tags, references, and links

Given a topic or keyword, returns related links and nodes from the graph

Feedback signal: confirm that context retrieved from the graph was useful. Boosts salience of specified keywords so they surface more prominently in future get_context calls. Call this when retrieved context directly influenced your response. Skipping is safe — it only affects future retrieval quality.

Screening: find existing similar keywords (vector search). Call BEFORE store_turn.

Semantic vector search. Find similar keywords via Turso vector_distance_cos or Python fallback (256-dim feature hashing).

Textual graph summary: top keywords, recent links, health, forgotten concepts

Find keywords not touched in N turns (decaying salience). Useful for rediscovering lost concepts.

Force prune inactive tangential links

Toggle keyword deduplication

Toggle semantic flashbacks

Reset the graph and start over

Automatic semantic extraction from text: keyword, topic, domain, intent, sentiment, entities. Uses LLM (if configured) or heuristic.

POST fallback (0-token): one-shot extract + topic-shift + auto-link + save. Prefer a curated store_turn when you can pick the concepts yourself; use auto only for throwaway turns.

Export the complete graph as JSON

Merge duplicate or near-duplicate nodes. Moves all links from aliases into canonical, sums salience, then deletes the aliases. Use after find_candidates reveals near-duplicates (e.g. 'spring boot' / 'Spring Boot' / 'Spring Boot 3.2').

Switch active context (creates if new). E.g. 'java/spring', 'python/django'.

List all available contexts with metadata.

Call at the START of each turn to load context in one shot. Equivalent to status + get_context(format='compact'). Returns active context summary and knowledge for the given topic. Ideal for providers without automatic injection hooks.

Show every Neuron command (one line each) plus how to use Neuron well. Call once at the start if unsure; full playbook: resource neuron://skill/auto-context.