Skip to content
TakoAPI
Back to skills

engram

by dannydvm

DevOps & Cloud
1.5kDownloads reported by clawskills.sh
1Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Persistent semantic memory layer for AI agents.

Description

What This Skill Does

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.

When to Use It

  • 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

Example Workflow

INPUT

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

AGENT
  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

OUTPUT

"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."

Requirements

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

Installation

clawhub install dannydvm/engram

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links