v1.7.20
southwellmedia/velocityv1.7.20Sep 22, 2026by Ed1s0nZ
Upgrading?
AI Summary
CyberStrikeAI integrates TypeSafe Jev as a human-in-the-loop (HITL) audit backend to handle tool calls. It replaces chat model JSON output with structured pass/block scoring and supports custom organizational policies.
Key Highlights
- Integration of TypeSafe Jev for HITL auditing
- Structured scoring (pass/block) instead of chat JSON
- Parallel risk assessment for destructive vs. authorized intent
- Custom policy overlay support
New Features
- TypeSafe Jev HITL backend integration
- Parallel risk assessment logic
- Custom policy overlay evaluation
- OpenAI protocol compatibility
Full Release Notes
CyberStrikeAI 现已接入 TypeSafe Jev 作为人机协同审批引擎：Agent 每次非白名单工具调用，会把工具名、参数和策略一次性交给 Jev 做结构化放通/拦截，不再依赖聊天模型输出 JSON。Jev 并行判断破坏性风险与授权渗透意图，本地规则合成 approve/reject；默认放行授权渗透，只拦截打挂业务、毁数据、改账号权限或改线上配置的操作。自定义审批策略会作为组织规则叠加，OpenAI 协议小模型仍可选用。 --- CyberStrikeAI now supports TypeSafe Jev as a HITL audit backend. Each non-allowlisted tool call is sent to Jev in one System One request, which returns structured pass/block scores instead of chat JSON. Built-in rules approve authorized pentest activity and reject live-system destruction, irreversible data loss, account/ACL changes, and config tampering. Custom org policy is evaluated as an overlay; the OpenAI-compatible reviewer remains available.
Related Repositories
feyninc/mandex★ 35
📑 The best way to have your Agents read the documentation! 🤖
public-apis/public-apis★ 491,193
A collective list of free APIs
openclaw/openclaw★ 392,715
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap★ 370,095
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/rea★ 360,219
Reverse engineer anything with agents, from app behavior down to native binaries.