Havuz

A Lean backend framework whose authorization safety is formally proven. The developer writes only a Cedar schema and policies; handlers are

Capability delegation and authorization for AI agents: scoped, attenuable tokens bound to SPIFFE workload identity and verified fully offlin

📊 Modern full-stack bookkeeping and financial control dashboard built with ASP.NET Core, Blazor, and PostgreSQL.

Runtime security for AI agents: discover agents, map their permissions, and enforce what they can do.

The control layer for agentic AI. A protocol-aware proxy that applies identity, policy, trust and payment controls to A2A, MCP and DIDComm t

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open

Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they exe

Fast, Keycloak-compatible IAM with DPoP and CIBA

Self-hosted multi-user DeepSeek Harness on Kubernetes, with OIDC sign-in and persistent user environments.

AgentSafe, agent veya API isteklerini hedefe iletmeden önce yetkilendirme kontrolünden geçiren bir HTTP execution gateway’idir.

Neden yükseliyor · 45 günlük yaşına karşılık 589 yıldız ve son 28 günde 126 commit dikkat çekiyor; ancak commit’lerin yalnızca 3 farklı yazardan gelmesi, aktivitenin geniş bir katkıcı tabanına yayıldığını göstermiyor. Yıldızların nedeni verilerden kesin olarak çıkarılamaz.

Runtime enforcement boundary for AI agents: a local sidecar that gates every outbound call against Cedar policies you own. Deterministic, ca

OAuth 2.1 Authorization Server for the Model Context Protocol (MCP)

Privacy and security guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and tool authorization

Praxis Policy Engine (PPE)

Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gatew

Open protocol for AI agent work contracts and verifiable execution — authorization, evidence, and acceptance for multi-agent systems

Purpose-bound authorization reference: RBAC + ABAC + ReBAC, row/field controls, fidelity gates, lifecycle governance, and a tested 100K synt

Mini decentralised auth. Gives an existing auth system a key nobody holds, with governance over who can decrypt.

Trace-backed Agent Authorization Reviews for tool-using AI agents. Staging-only evidence for payment, record-change, access, and export acti

Identity and Access Management for SELISE Blocks: accounts, roles, permissions, organizations, authentication, SSO/OIDC, MFA and CAPTCHA.

A modern, open-source full-stack SaaS starter built with Next.js, TypeScript, MongoDB, and shadcn/ui a solid foundation for building scalabl

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human a

Extensions providing OAuth and OpenID primitives for authentication and authorization for the DuckDB quack server.

Intent-bound action authorization for AI agents — deterministic, per-action approval a prompt injection can't re-point, with a signed, tampe

Runtime authorization for AI agents — Node.js SDK

Production-inspired authentication API with Spring Boot, JWT, Refresh Tokens, RBAC, PostgreSQL, Docker, tests and CI/CD.

Framework agnostic user management system for Python applications.

A secure and production-oriented FastAPI authentication system with JWT, RBAC, session management, HttpOnly cookies, token rotation, device

A local, open-source capability gateway for AI agents — one AI-native self-describe endpoint so any agent can discover, understand, be grant

A secure way to run enterprise AI agents. Building blocks with per-action authorization, prompt-injection containment, least privilege, and

Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-chec