Skip to content

Entry

Agent Governance Toolkit

Appears in 5 awesome lists

🟢 — Multi-language toolkit for policy-enforced agent tool calls and audit records, with optional identity, MCP-gateway, sandboxing, reliability, and compliance components. (Microsoft) — note: official public preview; APIs and deployment patterns may change before general availability. · updated…;…

Open github.commicrosoft/agent-governance-toolkit

Found in these lists

Awesome AI Security Tools

Section: Frameworks, Rule Standards & Benchmarks · 🟢 — Multi-language toolkit for policy-enforced agent tool calls and audit records, with optional identity, MCP-gateway, sandboxing, reliability, and compliance components. (Microsoft) — note: official public preview; APIs and deployment patterns may change before general availability. · updated…;…

FreshScore 91

Awesome Harness Engineering

Section: Security, Sandbox & Permissions · Seven-package, multi-language (Python, Rust, TypeScript, Go, .NET) runtime security toolkit that addresses all 10 OWASP Agentic AI risks with deterministic, sub-millisecond policy enforcement. Includes Agent OS (policy engine intercepting every action), Agent Mesh (secure agent-to-agent…

FreshScore 93

Awesome Open Source AI

Section: 10. AI Safety, Alignment & Interpretability · Security and compliance toolkit for autonomous agents with policy enforcement, zero-trust identity, and sandboxed execution to reduce operational risk. MIT licensed.

FreshScore 87

Awesome Prompts

Section: Red Team & Security · 7 packages (Python/Rust/TS/Go/.NET) — policy enforcement (<0.1ms), zero-trust agent identity (Ed25519 + SPIFFE), sandboxed execution; covers all OWASP Agentic Top 10; adapters for LangChain/CrewAI/ADK/OpenAI Agents SDK (Apr 2026)

FreshScore 96

awesome-python

Section: LLM and Inference · AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

FreshScore 79

E2B

Open-source sandboxed code execution for AI agents — Firecracker microVMs with dedicated kernels per sandbox (~150 ms cold start), fork/snapshot primitives (pause/resume with full memory state), Python/JS SDKs + MCP server, self-hostable via Terraform on AWS/GCP; used by Perplexity, Hugging Face,…

In 9 listsDetails

InterpretML

InterpretML implements the Explainable Boosting Machine (EBM), a modern, fully interpretable machine learning model based on Generalized Additive Models (GAMs). This open-source package also provides visualization tools for EBMs, other glass-box models, and black-box explanations.

In 8 listsDetails

Guardrails AI

🟢 — Python framework for adding input/output guards, validators, structured-output controls, and Guardrails Hub checks to LLM applications. (Guardrails AI) · updated 2026-08-26); Related: NeMo Guardrails · LLM Guard · Pydantic AI Shields integration (README recommends a successor)

In 7 listsDetails

NeMo Guardrails

NVIDIA's programmable guardrails toolkit: define input, dialog, retrieval, execution, and output rails that intercept the agent loop at five distinct layers using the Colang DSL. The execution rail layer specifically governs what tools the LLM can invoke and what their inputs/outputs may contain —…

In 6 listsDetails

Tencent/aig-agent-redteam

🟢 — Full-stack AI red-teaming platform covering OpenClaw security scan, agent scan, skills scan, MCP scan, AI-infra vulnerability scan, and LLM jailbreak evaluation. (Tencent Zhuque Lab) · updated 2026-10-13); Related: agent-audit · aguara · Cisco AI Defense – skill-scanner · Cisco AI Defense –…

In 5 listsDetails

AgentOps

Open-source agent engineering platform (YC W24) with session replay, cost tracking, and failure detection across 10+ frameworks including CrewAI, LangGraph, and OpenAI Agents SDK. The step-by-step execution graph and cross-session metrics make it the most practical debugging layer for multi-agent…

In 6 listsDetails

microsandbox

Rust/Apache-2.0 local-first microVM runtime for untrusted agent workloads: <100ms boots, OCI-image compatible, fork-and-snapshot of live sandboxes, and an embeddable library API that spawns VMs in-process with no daemon. The distinguishing designs are secret handling — keys never enter the VM, so…

In 5 listsDetails

OpenShell

Open-source policy-driven sandbox runtime for autonomous AI agents, announced at GTC 2026. Enforces security constraints at the kernel level via Landlock LSM (filesystem), seccomp BPF (syscalls), and an OPA/Rego-evaluated HTTP CONNECT proxy (network) — constraints are enforced on the environment…

In 5 listsDetails