#authorization
GitHub Topic「authorization」がついているAI関連リポジトリの集計。Topicはリポジトリ作者が自己申告するメタタグで、AI関連の文脈で何が「authorization」と分類されているかを可視化します。
REPOS #authorization のRepo (TOP 14 / Stars降順)
Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-checked by an SMT solver (cvc5), every decision independently verifiable offline. Pure Rust.
xmuruaga/bounded-agentsBounded Agents: Delegation Security for Multi-Agent AI Systems - Reference Implementation and Evaluation Artifact
Bobcatsfan33/PharosThe trust control plane for enterprise AI agents — real-time policy verdicts in under 800ms and litigation-grade evidence of every decision. Pharos decides. Pharos proves.
OpenOBA/rulsynor-coreERDL deterministic Guard engine — cryptographic audit chain for AI Agent decisions. Train, deploy, correct, prove.
bmendonca3/authzbench-saasBenchmark for AI agents proving multi-tenant SaaS authorization bugs
bharath31/nomineeThe pause is where tools break: approval out of band, token minted at execution, arguments bound to what a human saw, spent once, sealed in a hash-chained receipt.
ntholm86/agent-context-memorySpecification for governance-first context memory in autonomous AI agent systems. Defines the Mandate Gate: a pre-work mandate must exist before an agent session is valid.
mianjabbar-dev/AiResumeBuilder-GGCSF-projectA dynamic, AI-integrated web application for building, customizing, and exporting ATS-friendly professional resumes in real-time.
KarinLuni/aisvs-c9-accountability-gap-analysisEmpirical evidence that OWASP AISVS C9.2 has no accountability axis: an action an AI agent cannot be answerable for reaches human-owned execution only through a false input. By K. Lunina.
reva-ai/reva-copilot-threat-detectionExternal threat detection provider for Microsoft Copilot Studio. Authorizes every agent tool call at runtime against Reva policy. Runs in your own environment on Node or AWS Lambda, with zero runtime dependencies.
Aankirz/agentauthOAuth-style delegated authorization for AI agents and MCP servers — scoped, revocable, short-lived tokens.
themayursinha/authority-graph-simulatorCounterfactual authorization for agent actions: authority graph simulator enforcing reachable_authority(G_after) ⊆ mandate. Visor Trust Plane.
bhaveshdesale/AgentShieldSecurity and authorization layer for AI-powered commerce. AI proposes transactions, AgentShield validates them, humans approve, and Razorpay executes.
kanywst/whosentTUI for Mandatum delegation chains: who sent this agent, where trust breaks, and what it may still do
RELATED 他のTopicも見る · 全Topicランキング →
#claude-code
2,815#ai-agents
2,183#llm
1,690#claude
1,475#mcp
1,359#python
1,349#developer-tools
1,231#ai
1,028#codex
996集計対象: 各Repoの最新contentスナップショットの topics_json に小文字一致でマッチしたもの。 算出方法