Havuz

Proof-Carrying Messages: a protocol for AI agents whose claims carry evidence the receiver checks offline

Micro-VM sandbox for AI agents: isolated, gated and auditable, to prove what your agents did

Offline, read-only MCP config checkup for individual agent users. Zero dependencies, 28 rules incl. Chinese tool-description poisoning detec

Governed AI agents for sensitive data and business-critical apps. Agents never hold credentials: a gateway checks every call against per-res

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

Minimal Ed25519-signed activity receipts for verifiable AI agents — self-attested, offline-verifiable, no blockchain.

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

Adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression tes

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a clien

Agent Canary 3.0: open-source MCP, SDK, and CLI security toolkit with a guarded execution gateway, decoy signals, local tests, and public ac

Soup Wall: open-source security for AI agents and model traffic. Local Agent, Gateway, self-hosted Console. Apache-2.0.

Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky

The execution safety layer for AI agents.

DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Ten

Trust & security scanner for AI agents and MCP servers — OWASP-mapped findings, Trust Cards (A–F grades), SARIF + CI gate. Free CLI, zero te

Keep your sensitive credintials out of the agents you build and the coding agent you use. Test any agent with planted fake keys, or see whic

Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.

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.

Research artifacts for provenance-bound agent authorization, signed effect evidence, and reproducible security evaluation.

Static security review for AI agent configs (LangGraph, CrewAI, OpenAI Agents, MCP): maps source-to-tool flows and flags untrusted input tha

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.

Six security outcomes an enterprise must achieve to run AI agents, and the controls that evidence them. A draft for public comment.

Open-source runtime security and execution control for autonomous AI agents. ALLOW, BLOCK, ESCALATE at the execution boundary with auditable

Open-source local MCP runtime that checks AI-agent tool calls, gates risky actions on approval, verifies results, and avoids blind retries a

reconnaissance for agent attack surfaces

numbat, AI agent etkinliğini endpoint üzerinde izleyen, yerel kurallarla değerlendiren ve desteklenen durumlarda eylem öncesi engelleme sunan bir güvenlik aracıdır.

Neden yükseliyor · AI agent güvenliği ve görünürlüğü ilgi gören bir alan; endpoint izleme ile geriye dönük incelemeyi bir araya getirmesi dikkat çekebilir. Ancak 1074 yıldız 65 günlük repo için görünür ilgiye işaret etse de son 28 günde commit ve farklı yazar olmaması, ilginin güncel geliştirme faaliyetiyle desteklendiğine dair kanıt sunmuyor. Yıldızların hangi dönemde kazanıldığına ilişkin veri yok.

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

Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for

Agent interoperability and security, out of the box. The network layer underneath A2A: reachable, end-to-end sealed and payable agents witho

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI pe

Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a clai

Open-source AI agent identity & compliance platform — X.509 certificates via AWS KMS, behavioral risk scoring, auto-revocation, and MiCA / E

TypeScript SDK for AI agent identity & compliance — issue X.509 certificates, verify scope, and enforce them with drop-in middleware. Apache

Local credential control for AI coding agents.

Free NVIDIA DLI course: build, coordinate, and secure AI agents with NemoClaw and OpenShell. Browser-based, no GPU required. Available in En

Confine an AI coding agent to one directory with a BPF-LSM program, and watch every escape it tries.

The knowledge graph for APIs your agent can trust. Maps any API — even messy, paywalled, or on-chain ones — into a verified graph your agent

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation,

🦞 Local, read-only security audit for your OpenClaw agent. Finds config, prompt-injection and supply-chain risks, watches for drift, and ve

Framework-neutral control contract for AI agents: eight interception points, three verdicts, and a conformance kit.

See which external pull requests need context before code review. Deterministic, no login, no AI.

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc

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

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

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

An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.

A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.

Runtime security platform for LLM agent tool calls on Kubernetes