Перейти к содержимому
TakoAPI
Назад к навыкам

engram

от dannydvm

DevOps & Cloud
1.5kЧисло загрузок по данным clawskills.sh
1Звёзды
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Persistent semantic memory layer for AI agents.

Описание

Что делает этот навык

Engram is a local-first persistent memory layer for AI agents, backed by SQLite and LanceDB with Ollama embeddings. It stores typed memories (facts, decisions, preferences, events, relationships) across sessions and surfaces them via semantic search and context-aware recall. Memory decay, deduplication, agent scoping, and graph relations are built in.

Runs entirely local with no token cost and no cloud dependency, so memory persists through context compaction and session crashes without sending data to an external service.

Когда его использовать

  • Recalling a client's communication preferences from a session three weeks ago
  • Storing a database architecture decision so future agents don't revisit it
  • Ingesting a meeting transcript to automatically extract structured memories
  • Searching past project milestones before drafting a status update
  • Keeping memories isolated per agent so two bots don't share unrelated context

Пример сценария

ВВОД

User asks: What did we decide about the deployment setup for the new client?

АГЕНТ
  1. 1

    Run engram recall "client deployment setup" --limit 10 to surface the most relevant past memories

  2. 2

    Review returned memories ranked by semantic similarity, recency, and salience

  3. 3

    Identify the stored decision memory: "Chose Docker Compose over Kubernetes for simplicity on small clients"

  4. 4

    Check related memories via engram relations <memory-id> to find linked facts or follow-up events

  5. 5

    Return the decision with full context to the user

ВЫВОД

"We decided on Docker Compose over Kubernetes for this client (stored 2026-01-15). Related: client prefers minimal ops overhead, deployment target is a single VPS."

Требования

  • Ollama installed with the nomic-embed-text model pulled

Установка

clawhub install dannydvm/engram

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки