GitHub

Claude Managed Agents: Self-Hosted Sandboxes and MCP Tunnels — Anthropic's May 2026 enterprise deployment pattern keeps the agent orchestration loop on Anthropic's infrastructure while moving tool execution into customer-controlled sandboxes; combined with MCP tunnels for private-network tool access, it's the reference architecture for data-residency-conscious production harnesses.
AgentCgroup: Understanding and Controlling OS Resources of AI Agents — February 2026 empirical study of sandboxed coding-agent workloads finding that OS-level execution accounts for 56–74% of end-to-end latency and memory is the real concurrency bottleneck (15.4× peak-to-average spikes driven by tool calls). Proposes an intent-driven eBPF controller aligned with tool-call boundaries — essential for anyone running multi-tenant agent sandboxes where coarse container limits waste resources or let agents starve each other.
AI Agent Scaling Gap: Pilot to Production (March 2026) — Analysis showing 72% of Global 2000 companies operate agents beyond experimental phases, but only 14% successfully scaled organization-wide. Scaling success correlates strongly with operations infrastructure (monitoring, evaluation harnesses, incident response) rather than technology choices. Documents the shift from engineering-focused to operations-focused agent deployment.
builderz-labs/mission-control — Self-hosted orchestration dashboard for agent task dispatch, multi-agent workflow coordination, and spend monitoring across gateways. The zero-external-dependency design (SQLite, single pnpm start) makes it the most practical open-source control plane for teams that need governance and cost visibility without building infrastructure from scratch.
5 Production Scaling Challenges for Agentic AI in 2026 — Data infrastructure prioritized before deployment; successful scalers appoint AI operations function pre-expansion; multi-agent distributed systems with load balancing and auto-scaling. Essential reading for understanding infrastructure prerequisites for agent deployment at scale.

Beyond Permission Prompts — The authoritative resource on moving from prompt-level permission grants to structured authorization in the harness.
How we contain Claude across products — Anthropic's May 2026 cross-product containment write-up: why environmental isolation must be the primary boundary, how model-layer defenses alone miss ~17% of overeager actions, and concrete sandbox architectures for chat, terminal, and autonomous workspace products. The exfiltration-through-allowlist case study is a stark reminder that the weakest link is often custom harness plumbing, not the sandbox itself.
Model Context Protocol — Authorization — MCP's specification for OAuth-based authorization flows when agents access external services.
AI Harness Scorecard — Scores repositories on AI harness safeguards. Useful checklist for auditing your own harness's security posture.
E2B — Firecracker microVM sandboxes purpose-built for agent tool loops: ~150ms cold start, Python/JS SDKs, open source. The clearest reference implementation of "code execution as a harness primitive" rather than a CI system bolted on.
tldrsec/prompt-injection-defenses — The most complete catalog of practical prompt injection defenses (input validation, tool output sanitization, canary tokens, etc.). Functions as a design checklist for hardening trust boundaries in any agent harness.

awesome-harness-engineering

What the docs cover

Keep exploring from this skill

Related Skills

ECC

n8n

gemini-cli