惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - Franky
云风的 BLOG
云风的 BLOG
人人都是产品经理
人人都是产品经理
博客园 - 叶小钗
Engineering at Meta
Engineering at Meta
Vercel News
Vercel News
Y
Y Combinator Blog
B
Blog
Microsoft Azure Blog
Microsoft Azure Blog
C
Check Point Blog
M
MIT News - Artificial intelligence
Jina AI
Jina AI
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Apple Machine Learning Research
Apple Machine Learning Research
Hugging Face - Blog
Hugging Face - Blog
阮一峰的网络日志
阮一峰的网络日志
罗磊的独立博客
Stack Overflow Blog
Stack Overflow Blog
F
Fortinet All Blogs
博客园 - 司徒正美
I
InfoQ
Google DeepMind News
Google DeepMind News
GbyAI
GbyAI
U
Unit 42

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
GitHub - humancoreai/Gategraph: deterministic governance ...
humancore · 2026-05-18 · via Hacker News - Newest: "AI"

Release: v0.17.1_STABLE

Current release: v0.17.1_STABLE
Base: v0.17.0_STABLE
Base stable: v0.17.0_STABLE
Status: candidate
Version: 0.17.1
Phase: Promotion Status Drift Guard
Release focus: Promotion Status Drift Guard

GateGraph is a deterministic governance layer for AI-agent actions. It evaluates requested actions before execution, produces bounded governance decisions, and keeps execution authority outside the model.

What GateGraph is

GateGraph is designed to sit between an agent or operator workflow and an action surface.

It can:

  • evaluate action requests,
  • return allow/block/review/approval decisions,
  • issue bounded capability-token surfaces,
  • produce audit and explainability artifacts,
  • run deterministic evidence checks.

What GateGraph is not

GateGraph is not:

  • an autonomous agent,
  • a policy-learning system,
  • a production internet gateway,
  • an identity provider,
  • a KMS,
  • a multi-node trust fabric,
  • a replacement for human approval.

Current production boundary

Current scope is local, protected, single-node operation.

Out of scope for the current release:

  • public internet exposure,
  • built-in TLS/auth for hostile networks,
  • external agent-framework production integration,
  • multi-node consensus,
  • managed secret infrastructure,
  • autonomous policy mutation.

Quickstart

First verify the local package and supported command surfaces:

python tests\fresh_clone_reproducibility_evidence.py
python tests\single_node_cli_evidence.py

Then run the full evidence suite before treating a candidate as release-ready:

python tests\evidence_ci.py

Expected evidence result:

CI EVIDENCE REPORT
Passed: True

Review surfaces

Core public review files:

  • VERSION.md
  • RELEASE_STATUS.md
  • RELEASE_METADATA.json
  • RELEASE_MANIFEST.json
  • RELEASE_PROCESS.md
  • PRODUCTION.md
  • SECURITY.md
  • TRUST_MODEL.md
  • docs/SCOPE_BACKLOG.md
  • docs/RELEASE_v0.17.1_STABLE.md

Security posture

GateGraph uses fail-closed defaults and separates governance decision surfaces from execution authority. The current release does not add runtime authority, auto-promotion, auto-repair, autonomous policy mutation, or public deployment capability.

License

Apache-2.0.

Runtime namespace

Canonical runtime namespace: gategraph.

src/ package is the canonical runtime/governance surface. gategraph/context/ package is a bounded context-governance extension layer and must not become an alternative governance or execution path.

Security mapping

OWASP_AGENTIC_AI_MAPPING.md is a descriptive mapping from GateGraph evidence surfaces to agentic-AI risk categories. It is a review aid, not a compliance certification or normative policy source.