Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
Python agent-harnessagent-memoryagent-orchestrationai-agent-harnessai-agentsawesome-listcontext-engineeringharness-engineeringmcp
Add mcpguard-dynamic to Security, Sandbox & Permissions section
ai-boost1137680222ce
diff --git a/README.md b/README.mdindex b9a5faa..365fa44 100644--- a/README.md+++ b/README.md@@ -453,6 +453,7 @@ Real repositories worth studying — each with a note on *why* it's worth your t- [Sandbox Agents | OpenAI API Docs](https://developers.openai.com/api/docs/guides/agents/sandboxes) — OpenAI's authoritative April 2026 guide to sandbox architecture in the Agents SDK. The core principle is strict separation between the harness control plane (auth, billing, orchestration) and the sandbox compute plane (files, shell, ports), with manifest contracts, resumable session state, and sandbox-native memory.- [NVIDIA OpenShell](https://github.com/NVIDIA/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 itself, so even a compromised agent cannot override them. Supports Claude Code, Codex, Cursor, and OpenCode inside the sandbox. - [Microsoft Agent Governance Toolkit](https://github.com/microsoft/agent-governance-toolkit) — 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 communication), and Agent Runtime (dynamic execution rings). Hooks into LangChain callbacks, CrewAI task decorators, Google ADK plugins, and Microsoft Agent Framework middleware. +- [mcpguard-dynamic](https://github.com/facebook/mcpguard-dynamic) — Meta's kernel-level eBPF sandbox for MCP tool calls: a transparent proxy that enforces capability policies through a policy engine, argument validator, and BPF LSM hooks (file, network, process, fork), so a compromised or malicious MCP server cannot bypass restrictions at the application layer. Includes a 14-server, 82-case benchmark showing the full defense stack achieves 68.9% attack prevention with zero false positives. - [Cloudflare Dynamic Workers](https://blog.cloudflare.com/dynamic-workers/) — V8 isolate-based sandboxing for AI-agent-generated code execution, now in open beta. Isolates start in milliseconds using megabytes of memory — 100x faster and up to 100x more memory-efficient than containers. The sandbox intercepts outbound HTTP requests for credential injection so agent code never touches secrets directly. A fundamentally different architectural option from container-based sandboxes (E2B, Daytona).- [Kubernetes Agent Sandbox](https://github.com/kubernetes-sigs/agent-sandbox) — K8s-native Sandbox CRD (under SIG Apps) providing declarative, standardized APIs for managing isolated, stateful, singleton workloads for AI agent runtimes. Supports gVisor and Kata Containers for kernel-level isolation; v0.2.1 introduced "Secure by Default" networking architecture enforcing strict isolation with a shared policy model. The right choice when agents must run inside existing Kubernetes infrastructure. - [Alibaba OpenSandbox](https://github.com/alibaba/OpenSandbox) — General-purpose sandbox platform for AI agents (8.7K+ stars, March 2026) with multi-language SDKs (Python, Java, TypeScript, Go, C#), unified APIs across Docker/Kubernetes runtimes, and support for secure container runtimes (gVisor, Kata Containers, Firecracker). Covers coding agents, GUI agents, agent evaluation, and RL training in a single abstraction layer — the most runtime-flexible sandbox option when you need to choose isolation levels per workload. 