devops-prime-directives (Grade A)Išmaniojo datos - AI talento patikrintas saugumas už Claude AI. Rangas A. PRIMOS DIRKTIVĖS — išimtos iš roles.json gylisPromt už devops

Which local models should I run, and how does hardware affect SecureContext?

SecureContext degrades gracefully by hardware tier — every LLM-powered layer fails closed (the feature quietly contributes nothing) rather than breaking ingest or search. What changes with hardware is how much of the intelligence stack is active: | Tier | Hardware | Models that fit | What you get | |---|---|---|---| | Minimum | Any CPU, ~2 GB RAM free | nomic-embed-text (embeddings only) | Hybrid BM25+vector search, working memory, audit chain, skills gating — the core. LLM layers (event extraction, entity extraction, contradiction adjudication) stay dormant. | | Mid | 8–16 GB GPU (or Apple Silicon 16 GB+) | + qwen2.5-coder:14b or phi4:14b (one at a time) | + Event-fact extraction at ingest (temporal reasoning), LLM contradiction adjudication, entity extraction, L0/L1 semantic file summaries. | | Full | 24 GB+ GPU (e.g. RTX 4090/5090) | + phi4:14b and gpt-oss:20b resident together | Everything, concurrently, at interactive latency — plus a strong local generator for QA/benchmarks. This is the configuration our published benchmark deltas were measured on. | Model-choice guidance (all measured, see bench/): Embeddings: nomic-embed-text — required, tiny, runs anywhere. Event extraction (ZCEVENTEXTRACTMODEL, default phi4:14b): our bakeoff scored phi4:14b at 100% event recall / 100% date accuracy, tying gpt-oss:20b at 2× the speed. On smaller GPUs qwen2.5-coder:14b is close behind (84.6% recall). Coder models ≠ better: qwen2.5-coder:32b scored worst (69.2%) despite being the large

Asked by Gideon Mwangi · Apr 8, 2026

What do I need to run it?

Node 20+ and (recommended) Docker for the bundled PostgreSQL + Ollama stack. The one-command installer does everything in about five minutes. A SQLite fallback runs with zero infrastructure.

Asked by Dmitri Volkov · Mar 19, 2026

Can multiple Claude Code sessions work on the same project without conflicts?

Yes — parallel sessions atomically claim tasks from a work-stealing queue (zero double-claims at 50 agents × 100 tasks in testing), coordinate through typed broadcasts (ASSIGN/STATUS/MERGE/REJECT), and keep private per-agent memory namespaces plus a shared pool. Department-style hierarchies (heads + workers, N-tier escalation) are supported for larger agent teams.

Asked by Nadia Petrova · Mar 14, 2026

Are Claude Code skills safe to install?

Filesystem skills bundle scripts that run with your permissions, and Claude Code's native loader does not scan them. SecureContext adds the missing gate: AST scan at admission, HMAC verification before every execution, automatic quarantine on failure or post-admission change, and a verifiable chained log of every admission decision.

Asked by Femi Adebayo · Mar 1, 2026

Does SecureContext send my code or data to the cloud?

No. Memory, embeddings (Ollama nomic-embed-text), search, summarization, and the audit chain all run locally. It works fully offline (search degrades gracefully to keyword-only if Ollama is down) and costs $0 when idle.

Asked by Yosef Mizrahi · Feb 17, 2026