Community code plugin. Review compatibility and verification before install.
Latest release: v0.2.2Download zip
Capabilities
Compatibility
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The requested capabilities match the stated purpose: a persistent memory plugin needs to record, recall, and store memories, and the code uses Spark/Zellin API endpoints for recall, record, status, and insights. The apiKey, orgId, autoCapture, autoRecall, and apiUrl settings are all related to the advertised cloud-backed memory function.
Instruction Scope
The SKILL.md content stays within the memory-plugin purpose: it describes installation, configuration, automatic capture, recall, and cloud-backed reflection. The visible code captures conversation-derived preferences, decisions, corrections, and business facts, includes prompt-injection checks, and redacts several categories of sensitive data before storing captured memories. No unrelated files, local credentials, or unrelated external services are referenced.
Install Mechanism
There is no custom install script, download URL, archive extraction, or nonstandard binary installation. However, this is not purely instruction-only despite the no-install-spec metadata: it includes TypeScript plugin code and a normal package dependency on @sinclair/typebox. That is not inherently suspicious, but users should understand executable plugin code is present.
Credentials
The credentials/configuration requested are proportionate to the purpose: a Spark API key and organization ID are expected for a cloud memory service. There is a minor metadata/documentation mismatch: the registry lists no required environment variables, while the README/SKILL.md suggests SPARK_API_KEY and SPARK_ORG_ID, and the plugin schema requires apiKey and orgId in config. The visible code reads plugin config rather than process environment variables.
Persistence & Privilege
The skill does not set always: true, does not request broad system persistence, and there is no visible evidence that it modifies other skills or system-wide agent settings. Automatic capture/recall is expected for a memory plugin and is configurable via autoCapture and autoRecall.
Assessment
This plugin is coherent with its description: it is designed to remember information across sessions using Zellin’s cloud API. The main thing to consider is privacy, not mismatch: auto-capture is enabled by default, memories are org-scoped, and conversation-derived facts or summaries may be uploaded to https://zellin.ai/api unless you change the API URL. Review whether you are comfortable sending that information to this service, and consider disabling autoCapture if you only want manual memory storage. Confidence is medium because the provided index.ts content was truncated, so the full runtime behavior could not be completely reviewed.index.ts:703
Sensitive-looking file read is paired with a network send.
About static analysis
These patterns were detected by automated regex scanning. They may be normal for skills that integrate with external APIs. Check the VirusTotal and OpenClaw results above for context-aware analysis.Verification
Tags
🧠 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
| Feature | memory-core | memory-lancedb | Spark |
|---|---|---|---|
| Store memories | ✅ (files) | ✅ (vectors) | ✅ (vectors) |
| Semantic search | ❌ | ✅ | ✅ |
| Importance scoring | ❌ | Static 0.7 | Dynamic (1-10) |
| Nightly reflection | ❌ | ❌ | ✅ Synthesizes patterns |
| Recency × Relevance scoring | ❌ | ❌ | ✅ Stanford formula |
| Cross-session learning | ❌ | ✅ | ✅ + reflection |
| Episode types | ❌ | Basic categories | 7 types |
| Multi-user support | ❌ | ❌ | ✅ Org-scoped |
| Survives device loss | ❌ | ❌ | ✅ Cloud-backed |
| Selective capture | ❌ | Trigger-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
- Session starts → Spark recalls relevant memories from previous sessions
- During conversation → Spark records important facts, preferences, decisions
- Session ends → Spark saves a conversation summary
- Every night → Spark reflects on accumulated memories, synthesizes patterns, detects recurring behaviors
- 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
- 100 episodes/month
- Basic recall
- Nightly reflection included
- Sign up at zellin.ai
License
MIT