BLOG

Field notes on running agents.

How we build, secure, and run a fleet of self-hosted AI agents.

AI Coding Agent Dashboard for Claude Code and Codex

An AI coding agent dashboard becomes necessary the moment one developer stops running one assistant in one visible terminal. Once Claude Code, Codex, OpenCode,…

Multi-Provider Coding Agent Fallback Workflow

A coding agent does not fail only when the model is down. It fails when the team hits a usage limit at 4 p.m., when a pricing surprise pauses an account, when…

Durable Agent Team Messaging for Coding Agents

A platform engineer starts the morning with three useful coding agents and one very human problem. Claude Code has a terminal full of investigation notes.…

Claude Code Hooks Performance: Keep Agents Fast

If your Claude Code setup feels slower after adding dashboards, safety checks, formatters, and plugins, start with the hooks. Claude Code hooks performance…

Scan Claude Code Skills Plugins MCP Security Risks

How to scan Claude Code skills plugins MCP security risks before approval, including hooks, OAuth scopes, runtime drift, and supply chain dependency review.

Codex Claude Code Remote Development Environment Guide

Compare Codex Claude Code remote development environment options across local CLI, CDE, cloud, and self-hosted models for safer agent execution at scale.

MCP notifications background agent wake without polling

MCP notifications background agent wake without polling means streams plus durable state, not magic agent resume. Here is the production pattern, safely.

Claude Code Hooks Org Policy for Platform Security

Build a Claude Code hooks org policy that governs sources, rollout, telemetry, cloud coverage, and review before local scripts become a new hidden risk.

Coding agent sandbox Docker vs microVM vs devcontainer

A practical guide to coding agent sandbox Docker vs microVM vs devcontainer choices for teams weighing isolation, secrets, egress, and trust boundaries.

Claude Code Plugin Security Checklist for Team Review

The short answer: do not approve a Claude Code plugin because the marketplace looks familiar or the README sounds harmless. Use a Claude Code plugin security…

Run Claude Code in Docker: Safer Agent Workflows

If you want to run Claude Code in Docker, use a dev container pattern with a bind-mounted repository, a non-root user, per-project Claude state, minimal host…

Local Guardrails for Claude Code and Codex Projects

Local guardrails for Claude Code and Codex should stop harmful but plausible changes: weakening auth, rewriting old migrations, editing generated files, hiding…

Background AI Agent Approval Inbox: Team Design Guide

A background AI agent approval inbox starts to matter the first time your team has more than one unattended agent waiting on a human. One wants network access.…

Portable AI Coding Agent Sessions: Build or Buy Guide

Portable AI coding agent sessions are becoming a platform problem, not a convenience feature. Engineers now start work in one agent, hit a usage limit, switch…

Headless Claude Code Permissions Without Job Hangs

The answer: make unattended approval impossible to miss Headless Claude Code permissions should be explicit, narrow, and non-blocking. In practice, that means…

Designing an MCP Permission Gateway for Claude Code

The short answer: put MCP policy behind a gateway An MCP permission gateway gives Claude Code one approved MCP endpoint, then enforces policy before the agent…

Claude Managed Agents vs Self-Hosted Coding Agents

If you are choosing between Claude Managed Agents, self-hosted execution, and owned open-source agent runtimes, the decision is not mainly about which agent…

Prevent AI Coding Agents From Deleting Files

To prevent AI coding agents from deleting files, do not rely on a prompt that says "never delete." Run agents in isolated workspaces, limit writes to the repo…

Open Source Claude Code Alternatives for Self Hosting

For most platform teams evaluating open source Claude Code alternatives, the practical shortlist is OpenCode or Aider for terminal-first work, OpenHands for…

Best MCP Servers for Coding Agents

The best MCP servers for coding agents are the few that give agents high-signal engineering context under enforceable controls: source control, browser…

Engineering

Codex vs Claude Code cost and usage limits for teams

For engineering leaders and platform teams deciding policy, the practical answer on Codex vs Claude Code cost is not to standardize blindly on one tool. Run a…

Engineering

Coding-Agent Observability: Harness Traces That Matter

You are a platform or security engineer deciding whether a coding agent can touch private repositories. The answer is yes only if coding-agent observability…

Engineering

MCP Tool Allowlist: Stop Tool Drift Before Agents Use It

For platform engineers and security engineers responsible for MCP governance, the answer is direct: an MCP tool allowlist should approve specific servers and…

Engineering

Claude Code auto mode vs skip permissions for teams

For staff engineers, platform-security leads, and team governance owners, the answer to Claude Code auto mode vs skip permissions is practical: make auto mode…

Coding Agent Session History Needs Clear UX Design

Coding agent session history should be designed as operational state, not as chat history. The user needs a readable transcript, the model needs a controlled…

Coding Agent Prompt Injection in READMEs and Comments

Coding agent prompt injection is a trust-boundary failure: untrusted repository text reaches the same reasoning path as trusted instructions, and the agent's…

Coding Agent Session Manager for Agent Fleets

A coding agent session manager is useful when your problem is no longer "resume the last chat" but "supervise a fleet of agents without losing control of…

Claude Code GitHub Actions Security Checklist

A safe Claude Code GitHub Actions workflow separates untrusted analysis from privileged execution. Treat it as an agentic CI workload with code access, prompt…

Engineering

Self-hosted Coding Agent Runtime Comparison Guide

The right self-hosted coding agent runtime is the one that matches your trust boundary. For most security-conscious teams, that means per-task isolated…

Engineering

Persistent Memory for AI Coding Agents: Governance

Persistent memory for AI coding agents should be treated as platform infrastructure, not as a bigger prompt. The useful design is layered: small repo…

Engineering

MCP Context Bloat: How to Govern Tool Growth

MCP context bloat is the hidden tax of giving coding agents too many tools at once. Each enabled MCP server can add tool names, descriptions, input schemas,…

Engineering

AI Coding Agent Secrets: Protect .env and Tokens

AI coding agent secrets should not rely on .env files, ignore rules, or tool permissions as the main boundary. The workable pattern is layered containment:…

Engineering

Multi-Agent Coding Orchestration Is Ops Now

Multi-agent coding orchestration works when agents run in parallel but review, isolation, approvals, and merge decisions stay controlled.

Engineering

Coding Agent Dependency Security: Privileged Installs

Coding agent dependency security starts by treating package installs as privileged operations, with policy approval, lockfiles, and registry controls.

Engineering

Claude Code Hooks for Permissions: A Safer Pattern

Claude Code hooks for permissions can reduce approval fatigue when paired with narrow allowlists, sandboxing, managed settings, and audit logs.

Engineering

MCP Server Monitoring: What Reliability Requires

MCP server monitoring needs more than uptime checks. Track tool discovery, auth, latency, retries, timeouts, and per-tool safety controls.

Engineering

Cloud Coding Agent vs Local CLI Agent: Runtime Guide

Cloud coding agent vs local CLI agent is really a runtime decision: compare ownership, security, secrets, persistence, cost, and PR handoff before rollout.

Engineering

Coding Agent Cost Monitoring: Control Spend Early

Coding agent cost monitoring helps platform teams control token, credit, and workflow spend by combining budgets, telemetry, attribution, and policy.

Engineering

Securing Coding Agents in CI/CD: Practical Baseline

Securing coding agents in CI/CD starts with one rule: treat untrusted GitHub content as hostile, then limit secrets, tokens, network, and write access.

Engineering

Credential Proxy for AI Agents Without Secret Exposure

A credential proxy for AI agents lets agents call private repos, APIs, CLIs, and MCP tools without exposing raw secrets to runtimes, prompts, or logs.

Engineering

Agent Harness for Coding Agents: Runtime Architecture

An agent harness for coding agents controls sandboxes, state, permissions, tool execution, review flow, lifecycle, and cleanup around safe AI coding work.

Engineering

AI agent observability for safe coding agent rollouts

AI agent observability for coding agents: trace runs, commands, diffs, tests, costs, approvals, and risky side effects before code reaches production.

Engineering

Long-running background AI agents need durable workers

Long-running background AI agents need durable workers, queues, checkpoints, approvals, sandboxing, cost caps, observability, PR review, and control.

Engineering

Persistent AI Agent Workspace Architecture Guide

Design a persistent AI agent workspace with durable files, sandbox snapshots, memory boundaries, rollback, tenant isolation, and clear retention policy.

Engineering

Self-hosted coding agent runtime: build, buy, operate

A self-hosted coding agent runtime gives policy control and data residency, but shifts sandboxing, secrets, audit, cleanup, and capacity to your team.

Engineering

Production Workflows for AI Coding Agents That Scale

Production workflows for AI coding agents need isolated workspaces, reviewable diffs, CI controls, protected merge gates, and accountable human ownership.

Engineering

MCP Security for AI Agents: Production Controls

MCP security for AI agents needs token audience checks, sandboxed tools, schema pinning, approval UX, egress limits, and clear incident-ready audit trails.

Engineering

AI Agent Sandboxing: Secure Coding Agent Controls

AI agent sandboxing helps security leaders control source access, secrets, network egress, and coding agent execution risk before agents touch private code.