Question 1

What do I need to run it?

Accepted Answer

You need Node 20+ and (recommended) Docker for the bundled PostgreSQL + Ollama stack. The one‑command installer sets everything up in about five minutes. A SQLite fallback is available for zero‑infrastructure environments.

Question 2

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

Accepted Answer

SecureContext degrades gracefully based on hardware: - Minimum: Any CPU with ~2 GB RAM runs `nomic-embed-text` for embeddings, providing hybrid BM25 + vector search, working memory, audit chain, and skill gating. - Mid tier: 8–16 GB GPU (or Apple Silicon 16 GB+) adds `qwen2.5-coder:14b` or `phi4:14b` for event extraction, contradiction adjudication, entity extraction, and semantic file summaries. - Full tier: 24 GB+ GPU (e.g., RTX 4090/5090) runs both `phi4:14b` and `gpt-oss:20b` concurrently, delivering full interactive latency across all features. Embeddings always use `nomic-embed-text`; event extraction defaults to `phi4:14b` due to its high recall and speed.

Question 3

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

Accepted Answer

Yes. Parallel sessions claim tasks atomically from a work‑stealing queue, coordinate through typed broadcasts (ASSIGN/STATUS/MERGE/REJECT), and maintain private per‑agent memory namespaces plus a shared pool. Hierarchical department‑style structures are also supported.

Question 4

Are Claude Code skills safe to install?

Accepted Answer

By default, Claude Code skills run with your permissions and are not scanned. SecureContext adds safety by performing an AST scan at admission, verifying each execution with HMAC, automatically quarantining failing or altered skills, and maintaining a verifiable chained log of all admission decisions.

Question 5

Does SecureContext send my code or data to the cloud?

Accepted Answer

No. All memory, embeddings (via Ollama `nomic-embed-text`), search, summarization, and the audit chain run locally. SecureContext works fully offline and incurs $0 cost when idle.

Question 6

Can it manage a long, multi‑week project?

Accepted Answer

Yes. The delivery layer lets you define a program with phases (using `zc_program`). Each open phase carries an acceptance checklist, and closing a phase generates a checkpoint document. If the orchestrating agent dies mid‑phase, a fresh agent can reconstruct the full delivery state from two calls and resume work.

Question 7

How much does SecureContext reduce Claude Code token costs?

Accepted Answer

In a typical 10‑session project SecureContext reduces context‑overhead by about 87 %, cutting session restore from 20–50 k tokens to roughly 1.5–4 k tokens. Long‑lived projects see recall budgets stay around 4 k tokens instead of 47 k, and file questions are answered from 15–50× compressed semantic summaries.

Question 8

How do I give Claude Code persistent memory across sessions?

Accepted Answer

Install SecureContext using the one‑command quick‑start installer. Then agents can call `zcremember` to persist decisions and gotchas, and `zcrecall_context({focus: "current task"})` at session start to restore them. Memory survives restarts, compactions, and reboots because it is stored in PostgreSQL, not the context window.

Question 9

How is it different from competitors?

Accepted Answer

SecureContext differs from other memory solutions by providing local, persistent PostgreSQL storage, delivery programs with evidence‑gated checkpoints, per‑agent HMAC audit trails, identity isolation, skill admission gating, tamper‑evident session replay, a work‑stealing queue for parallel sessions, and offline operation with $0 idle cost. Competitors typically rely on cloud storage, lack delivery checkpoints, do not offer cryptographic audit trails, and may require external services.

Question 10

What's new (v0.46.1)?

Accepted Answer

Version 0.46.1 adds temporal retrieval round 2 and the delivery‑tool kit. It introduces compound temporal questions, chronological timeline rendering, stale‑result warnings, and multi‑phase delivery programs with evidence‑gated checkpoints that survive orchestrator restarts. The embed lane now includes a watchdog with budgeted self‑healing. Earlier releases added team memory, session replay with cryptographic provenance, OTel Gen‑AI spans, CI/headless memory CLI, chunked embeddings, compliance report export, temporal fact supersession, durable PG task graph, token‑budgeted recall digest, focused recall, TTL memories, multimodal ingestion, and more.

Question 11

What is SecureContext?

Accepted Answer

SecureContext is an MCP plugin that provides persistent memory across Claude Code sessions, per‑file semantic summaries, temporal search, a delivery layer for long‑running projects, and a cryptographic audit trail. It stores data locally in PostgreSQL, runs offline, and eliminates the need to repeatedly re‑paste files or recreate project state.

devops-zeroclaw-coordination-rules (Grade A)Security-tested data-ai skill for Claude AI. Grade A. ZEROCLAW COORDINATION RULES — extracted from roles.json deepPrompt for devops

Overview

Key features

Pricing

Use cases

DevOps Infrastructure Setup

Collaboration on DevOps Tasks

Pros & Cons

Pros

Cons

Reviews

Q&A

Ask a question

Skills alternatives