Compare skills
Pick 2–4 skills and compare what really matters: fit, risk, install effort, and community signal.
Selected skills (3/4)
Comparison matrix
Highlights show current best; tooltip explains diff/best rules.
Score-basis diff rules / risk tag notes
Start with the matrix. Open this section when you need to understand audit grades, top threats, control gaps, and best-value highlights.
Suggested baseline
Repository: haystack
Author: deepset-ai · Source status: Clear source
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
Search to add skills, or paste 2–4 comma-separated slugs.
How differences are detected
A row is marked different when selected skills have distinct values. Only-differences mode hides rows that are identical.
How best values are highlighted
Pre-install score, evidence completeness, and community signal prefer higher values; execution risk and install friction prefer lower values.
How to read risk tags
Risk tags come from SAS-v2.1 public-evidence signals and point to command, network, secret, context, or supply-chain items to review before install.
Selected audit signals
MemOS
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, memory context poisoning
Control gaps：missing license, broad permissions, shell without guardrails
create-an-asset
Execution risk：High
Threat tags：data exfiltration, memory context poisoning, human approval gap
Control gaps：missing license, broad permissions, network without allowlist
agent-memory-systems
Execution risk：High
Threat tags：data exfiltration, memory context poisoning, human approval gap
Control gaps：missing license, network without allowlist, no human approval
| Dimension | MemOS | create-an-asset | agent-memory-systems |
|---|---|---|---|
| Pre-install decision | |||
Pre-install score | 79 · Manual review | 80 · Manual review | 79 · Manual review |
Score basis | Clear source, High execution risk, Universal | Clear source, High execution risk, Claude | Clear source, High execution risk, Claude |
Execution risk | High | High | High |
Threat tags | unexpected code execution, data exfiltration, memory context poisoning | data exfiltration, memory context poisoning, human approval gap | data exfiltration, memory context poisoning, human approval gap |
Control gaps | missing license, broad permissions, shell without guardrails | missing license, broad permissions, network without allowlist | missing license, network without allowlist, no human approval |
Permission summary | Permission review, Network, Command | Network, Command | Network, Command |
Evidence completeness | 67% | 67% | 65% |
| Source & provenance | |||
Provenance | MemTensor/MemOS | anthropics/knowledge-work-plugins/tree/main/sales/skills/create-an-asset | davila7/claude-code-templates/tree/main/cli-tool/components/skills/ai-research/agent-memory-systems |
Category | Knowledge & RAG | Knowledge & RAG | Knowledge & RAG |
Freshness | |||
| Risk & permission signals | |||
Audit signals | No explicit signals | No explicit signals | No explicit signals |
Permission hints | repository clone, local runtime dependencies | registry access, remote metadata pull, runtime dependencies may be required | registry access, remote metadata pull, runtime dependencies may be required |
| Install & compatibility | |||
Supported tools | Universal | Claude, Codex, Cursor, Universal | Claude, Codex, Cursor, Universal |
Install method | script-backed | registry-install | registry-install |
Install friction | |||
| Community | |||
Stars | 8.2K | 6.6K | 19.9K |
Repository: OpenViking
Author: volcengine · Source status: Clear source
OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw).
Score basis：Clear source · High execution risk · Universal · Evidence completeness 69%
Repository: openclaw/skills
Author: lookupmark · Source status: Clear source
Semantic search over local files using all-MiniLM-L6-v2 embeddings and ms-marco-MiniLM-L-6-v2 cross-encoder reranking with ChromaDB and parent-child chunking.
Score basis：Clear source · High execution risk · OpenClaw · Evidence completeness 69%
Repository: MemOS-Cloud-OpenClaw-Plugin
Author: MemTensor · Source status: Clear source
Official MemOS Cloud plugin for OpenClaw.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
Repository: cortexgraph
Author: prefrontal-systems · Source status: Clear source
Temporal memory system for AI assistants with human-like forgetting curves.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 67%
2026-04-08 |
2026-02-04 |
2026-02-04 |
40 |
50 |
50 |
