Spark Memory

v0.2.2

Intelligence layer that compounds. Records decisions, reflects overnight, detects patterns, captures sessions automatically — your agent gets smarter every day.

@zellin/spark-memory·runtime spark-memory·by @zellinun
Code Pluginsource linkedCommunity code plugin. Review compatibility and verification before install.

README

🧠 Spark Memory — Persistent Intelligence for OpenClaw Agents

Your agent forgets everything when the session ends. Spark fixes that.

Spark gives your OpenClaw agent a memory that compounds. Not flat storage — a brain that reflects, learns patterns, and gets smarter every day.

What Makes Spark Different

Featurememory-corememory-lancedbSpark
Store memories✅ (files)✅ (vectors)✅ (vectors)
Semantic search
Importance scoringStatic 0.7Dynamic (1-10)
Nightly reflection✅ Synthesizes patterns
Recency × Relevance scoring✅ Stanford formula
Cross-session learning✅ + reflection
Episode typesBasic categories7 types
Multi-user support✅ Org-scoped
Survives device loss✅ Cloud-backed
Selective captureTrigger-based✅ Intelligence-based

Install

openclaw plugins install @zellin/spark-memory

Then configure in your OpenClaw settings:

{
  plugins: {
    slots: { memory: "spark-memory" },
    entries: {
      "spark-memory": {
        config: {
          apiKey: "your-spark-api-key",
          orgId: "your-org-id"
        }
      }
    }
  }
}

Setup

Set these environment variables (or add to your OpenClaw config):

export SPARK_API_KEY="your-api-key"    # Get one at https://zellin.ai
export SPARK_ORG_ID="your-org-id"       # Created when you sign up

How It Works

  1. Session starts → Spark recalls relevant memories from previous sessions
  2. During conversation → Spark records important facts, preferences, decisions
  3. Session ends → Spark saves a conversation summary
  4. Every night → Spark reflects on accumulated memories, synthesizes patterns, detects recurring behaviors
  5. Next session → Your agent is smarter than yesterday

Day 1: knows nothing. Day 30: knows your preferences, your clients, your patterns. Day 365: knows more about your operations than you remember yourself.

Architecture

Based on Stanford's "Generative Agents" paper with extensions:

  • Memory Stream (episodes) → Reflection (synthesis) → Patterns (recurring behaviors)
  • Retrieval scored by Recency × Importance × Relevance
  • Org-scoped: multiple users feed one shared memory
  • Cloud-backed: memories survive device changes

Free Tier

License

MIT

Capabilities

configSchema
Yes
Executes code
Yes
HTTP routes
0
Plugin kind
memory
Runtime ID
spark-memory

Compatibility

Built With Open Claw Version
2026.3.24
Plugin Api Range
>=1.0.0

Verification

Tier
source linked
Scope
artifact only
Summary
Validated package structure and linked the release to source metadata.
Commit
93d4d13
Tag
main
Provenance
No
Scan status
clean

Tags

latest
0.2.2