Current graph state: nodes, links, health, configuration. Safe first call to see if the memory holds anything. New to Neuron? The core workflow is a 2-step loop each substantive turn: pre_turn (before) then store_turn (after); call help or skill(name='playbook') for the full playbook.

MEMORY LOOP — STEP 2 (after replying). Call this AFTER you answer a substantive turn, to persist what is new into long-term memory. Curate for a clean graph: topic = 3-5 words; keywords = 3-5 CONCEPT nouns / entities / tech (never verbs or filler like 'use', 'make'); links = typed edges between keywords (never link a keyword to itself). This is the preferred way to save — cleaner than auto(). Skip on trivial turns (greetings, acknowledgements, yes/no).

Retrieve related nodes and links for a topic/keyword — what the memory already knows. Call BEFORE answering when a question may have prior context worth recalling. For the normal start-of-turn load, prefer pre_turn (one shot: status + compact context).

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 a Python cosine fallback (384-dim fastembed embeddings, NS_EMBED_MODEL).

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

Consolidate the graph: merge near-duplicate concepts (cosine) and archive low-salience orphans to a recoverable _graveyard. Keeps the memory clean; safe to run periodically.

Toggle keyword deduplication

Toggle semantic flashbacks

Reset the graph and start over

Automatic semantic extraction from text: keyword, topic, domain, intent, sentiment, entities. Heuristic (0 token) — no LLM extraction.

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.

MEMORY LOOP — STEP 1 (before replying). Call this FIRST on any substantive turn to load relevant past context in one shot (status + get_context in compact form). Fold what it returns silently into your answer; do not announce it. Then reply, then call store_turn (step 2). Skip only on trivial turns or when the graph is empty. Ideal for clients without automatic context-injection hooks.

Show every Neuron command (one line each) plus how to use Neuron well. Call once at the start if unsure; full playbook: call skill(name='playbook').

Return the FULL text of a Neuron skill/playbook on demand — token-cheap, fetch it only when you need the details. Use after the compact opener to load the complete workflow or curation rules.