vanar-neutron-memory
от naeemmaliki036
Search & ResearchКратко
Store and retrieve agent memory using Vanar Neutron API.
Описание
Что делает этот навык
Saves and retrieves agent memory using semantic search, so context persists across sessions. Manual commands let you store and query specific text; optional hooks automate capture and recall around each AI turn.
Semantic search finds relevant context by meaning rather than requiring exact keyword matches, which makes recall reliable even when you don't remember how something was phrased.
Когда его использовать
- Remembering user preferences set in a previous session
- Recalling a decision made days ago without re-explaining it
- Automatically injecting relevant past context before each AI response
- Storing project-specific conventions the agent should always follow
- Searching past conversations by meaning rather than exact keywords
Пример сценария
User asks: 'What font size did we decide on for the dashboard?'
- 1
Auto-Recall hook triggers before the AI turn
- 2
Sends the user message as a search query to POST /memory/search
- 3
Neutron API returns semantically matched memories about past font size decisions
- 4
Relevant context is injected into the AI turn as additional context
- 5
Agent responds with the recalled decision
Agent answers with the font size choice from a previous session, without the user repeating themselves
Требования
- API_KEY environment variable (free key at https://openclaw.vanarchain.com/, $20 free credits, no credit card required)
Установка
clawhub install naeemmaliki036/vanar-neutron-memoryВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.