Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
Skill Claude CodeCodex
ZettelForge v2.0.0 — Production CTI agentic memory system. Hybrid TypeDB (STIX 2.1 ontology) + LanceDB (vector search). Zero external AI dependencies: fastembed for embeddings, llama-cpp-python for LLM. 75% accuracy on CTI queries, 18% on LOCOMO. Use when agents need persistent memory, threat intel retrieval, entity…
Skill Claude CodeCodex
ZettelForge CTI Memory — Store, recall, and synthesize threat intelligence. Use when agents need persistent CTI memory, threat actor attribution, CVE lookups, STIX graph traversal, or RAG synthesis over threat reports. Triggers on: remember intel, recall threats, what tools does X use, CVE lookup, threat actor…
Skill Claude CodeCodex needs its repo
ZettelForge v2.0.0 — CTI agentic memory system. Hybrid TypeDB (STIX 2.1) + LanceDB (vectors). Zero external AI. 75% CTI accuracy, 111ms p50. Use for: storing/recalling threat intel, entity extraction, graph traversal, RAG synthesis, OpenCTI sync.