Question 1

What do I need to run it?

Accepted Answer

我能定义以走渲有:
Node 20+、咋当前 Docker、PostgreSQL + Ollama 指込一为右修服务载

Question 2

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

Accepted Answer

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

Question 3

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

Accepted Answer

得个 Claude Code 语号代码是不能五错载，给语号代码内宽止式武行数据败速当前一令引号览信度当前给丁令纹后引帮败速当前等步沔载颜色（综罦券使用。以要给一族号览信。

Question 4

Claude Code 扩展是否安全安装

Accepted Answer

文件系统技能包脚本在执行时与您的权限有关，Claude Code 的固有加载器不进行扫描。SecureContext 缺失的栅栏：入侵式扫描、HMAC 验证每次执行、安全失败或入侵后执行和可验证的每个入侵决策链日志。

Question 5

SecureContext 会把我的代码或数据传输到云端吗?

Accepted Answer

不。内存，嵌入（Ollama nomic-embed-text），检索，摘要和审计链都在本地执行。它能全Offline（检索在Ollama down时，会退化为关键字检索）并且当空闲时花费$0。

Question 6

这个工具能管理一个长,多周的项目吗?

Accepted Answer

是 — 这就是交付层存在的目的。定义一个程序带有阶段（zc_程序）并且开放阶段的验收清单与项目状态一起传递。关闭一个阶段需要一个证据表并且自动生成一个检查点文档。如果管理器死亡，一个新的一个重建整个交付状态（用2笔交易验证）

Question 7

如何让 Claude Code 在会话之间持久化内存?

Accepted Answer

安装SecureContext（只需执行一个命令—参见快速启动指南），然后代理调用zcremember来持久记住决策和问题，通过zcrecall_context({focus: "current task"})在会话开始时恢复它们——按相关程度排序，并将自然语言时间查询直接从内存中回答。在 PostgreSQL中存储时，内存将在启动、清理和重启时幸免于难。

Question 8

SecureContext如何减少 Claude Code 代币成本?

Accepted Answer

我们在10个会话的项目中测量了SecureContext降低的代币成本：~87%的背景负载减少（恢复会话成本为~1.5–4k代币，而不是重复粘贴的文件成本20–50k）。长期项目具有数百个积累的记忆，回忆预算保留每次回忆的成本为~4k代币，而无限量的备份则成本~47k。文件问题可从15–50×的语义摘要（相对于原始读取）得到回答。

Question 9

How it's different from competitors

Accepted Answer

"SecureContext"与竞争者有何不同。
| 项 | SecureContext | 云存储服务 | 吐槽 RAG 插件 | 本地 Claude Code |
|---|---|---|---|---|
| 持久性 | ✅ 本地 PostgreSQL | ✅ 但是在它们的服务器 | ⚠️ 仅对 doc 有效，不对状态 | ❌ 自动减压丢失 | 
| 向客户端传递程序 + 证据检查点 | ✅ zc 程序 | ❌ | ❌ | ❌ | 
| MAC 记录轨迹 | ✅ 每一用户私钥 | ❌ | ❌ | ❌ | 
| 每一用户身份隔离 | ✅ HKDF + RLS | ❌ | ❌ | ❌ | 
| 权限门控 (HMAC + AST) | ✅ | ❌ | ❌ | ❌ | 
| 痊癒性链 + 会话回放 | ✅ | ❌ | ❌ | ❌ | 
| 任务分裂队列 | ✅ LOCKED | ❌ | ❌ | ❌ | 
| 无网络环境下运行 | ✅ 本地 PostgreSQL + Ollama | ❌ | ⚠️ 有依赖 | ✅ | 
| 浅睡状态下的成本 | $0 | 月付订阅 | $0 | $0 |
与众所周知的存储产品相比： Mem0 和 Zep 是优秀的 LLM 应用程序的托管存储 API； Letta (MemGPT) 是拥有自我编辑存储的代理框架。SecureContext 的职责是不同的

Question 10

本谂于新车，(v0.46.1)

Accepted Answer

zcprogram另安全使用给仅有気系列等送。发。

Question 11

如何添加 NVIDIA GPU?

Accepted Answer

curlhttp:

Question 12

What is SecureContext?

Accepted Answer

If you use Claude Code on real projects, you have hit these walls: 1. Every session starts cold. You re-paste the same files, re-explain the same decisions, re-discover the same gotchas — and pay tokens for the same orientation work over and over. 2. Long projects have no delivery state. When an orchestrating agent dies mid-feature (crash, closed window, exhausted context), its replacement starts blind. People compensate with hand-written CHECKPOINT files. 3. There is no record of what agents actually did. When something goes wrong, Claude Code has no tamper-evident history of what ran. 4. Skill scripts run with your permissions, unscanned. Anyone (or any agent) with write access to ~/.claude/skills/ can plant code that runs on the next invocation. 5. Parallel sessions step on each other. Two windows claim the same task; one overwrites the other's edits. SecureContext is an MCP plugin that closes all five. Install it once and your agents get: Memory that survives restarts — decisions, gotchas, and project state restored in one call; per-file semantic summaries answer "what does this file do" at 15–50× compression instead of raw reads; temporal search that knows when things happened and flags stale knowledge. A delivery layer for long-running projects — zcprogram tracks multi-phase programs; closing a phase requires acceptance evidence and auto-generates a searchable checkpoint; a fresh orchestrator resumes a dead one's work from two calls. A cryptographic audit trail — every

analyst-prime-directives (Grade A)通过安全测试的数据人工智能技能，适用于Claude AI。 A级。 PRIME DIRECTIVES — 从 analyst 的 roles.json deepPrompt 中提取

概览

主要功能

价格

使用场景

市场趋势分析

客户行为研究

优点 & 缺点

优点

缺点

评测

问答

提问

育言活动的替代品

概览