# Junction > Junction Panel is the local-first control panel for AI coding agents. - Canonical site: https://junctionpanel.dev/ - Hosted app: https://app.junctionpanel.dev - Last updated: 2026-06-03 ## Core entities - Junction - Junction Panel - Switchboard - Junction daemon - Junction relay ## What Junction does - Monitor and control AI coding agents from anywhere - Connect multiple Junction daemons across your machines - Stream live agent output, tool calls, and progress - Use Switchboard to turn issues into branches and pull requests - Review diffs, branches, and pull requests from one workspace - Keep code local on your own machines with privacy-first remote access ## Supported agent workflows highlighted on the site - Claude Code - Codex - OpenCode ## Pricing - Free: $0/month — core app access, 1 daemon, 2 open chats, no Switchboard automation - Junction Core: $10/month — unlimited daemons and chats for the core control plane - Switchboard: $15/month — everything in Core plus Linear-driven automation - Paid pricing stays locked in for life for early adopters ## Install `npm i -g @junctionpanel/junction-daemon` - Setup guide: https://junctionpanel.dev/setup/ - Pricing: https://junctionpanel.dev/pricing/ - Contact: https://junctionpanel.dev/contact/ ## Legal - Terms of Service: https://junctionpanel.dev/terms/ - Terms of Service for Junction, including account use, local daemon responsibilities, subscriptions, 7-day trials, cancellations, and no guaranteed refunds after payment. - Privacy Policy: https://junctionpanel.dev/privacy/ - Privacy Policy for Junction, including local-first agent control, account data, billing, analytics, relay encryption, notifications, Switchboard, feedback, and data rights. ## Evergreen organic pages - An AI coding agent dashboard for real local work: https://junctionpanel.dev/ai-coding-agent-dashboard/ - Monitor Claude Code, Codex, OpenCode, branches, approvals, diffs, and notifications from one local-first Junction workspace. - Control AI coding agents from your phone without moving code: https://junctionpanel.dev/control-ai-coding-agents-from-phone/ - Use Junction to monitor and steer local Claude Code, Codex, and OpenCode runs from your phone without moving your repository. - A Claude Code UI for supervising local sessions: https://junctionpanel.dev/claude-code-ui/ - A local-first Claude Code UI for monitoring output, approvals, branches, and mobile review without replacing your terminal setup. - Monitor and steer Codex CLI runs from your phone: https://junctionpanel.dev/codex-cli-mobile-control/ - Monitor Codex CLI runs from a phone, keep execution local, and review blockers, branches, and PR state in Junction. - A control surface for OpenCode and local agent runs: https://junctionpanel.dev/opencode-control-surface/ - Use Junction as a local-first OpenCode control surface for live output, multi-machine visibility, mobile checks, and review workflows. - AI agent orchestration for developers with real repositories: https://junctionpanel.dev/ai-agent-orchestration/ - Coordinate local AI coding agents across machines, repositories, branches, approvals, and pull requests with Junction. - Local-first AI coding agents deserve a control surface: https://junctionpanel.dev/local-first-ai-coding-agents/ - Run AI coding agents where your repositories, credentials, and tools already live while Junction adds remote visibility and control. - Turn Linear issues into pull requests with local agents: https://junctionpanel.dev/switchboard-linear-to-pr/ - Use Switchboard to turn well-written Linear issues into branches and pull requests while keeping agent execution on your machines. - Compare AI coding agent workflows before you scale them: https://junctionpanel.dev/ai-coding-agent-comparisons/ - Compare Claude Code, Codex, OpenCode, cloud sandboxes, remote desktops, and local-first control surfaces for AI coding work. ## Topic hubs - AI Coding Agent Workflows: https://junctionpanel.dev/blog/topics/ai-coding-agents/ - Field notes on running, supervising, approving, and reviewing AI coding agents with local-first control. - Claude Code Guides: https://junctionpanel.dev/blog/topics/claude-code/ - Guides for monitoring Claude Code, comparing Claude Code with Codex, and keeping Claude sessions reviewable. - Codex Workflow Guides: https://junctionpanel.dev/blog/topics/codex/ - Practical notes on Codex CLI, local-first Codex workflows, mobile monitoring, and side-by-side agent use. - OpenCode Control Surface Notes: https://junctionpanel.dev/blog/topics/opencode/ - Writing on what OpenCode users need from a control surface and how OpenCode fits mixed agent stacks. - Mobile AI Agent Control: https://junctionpanel.dev/blog/topics/mobile-development/ - Articles on monitoring, reviewing, approving, and stopping AI coding agents from a phone or tablet. - Local-First AI Coding Agents: https://junctionpanel.dev/blog/topics/local-first/ - Local-first Junction notes on keeping code, credentials, agent execution, and project tooling on your machines. - Switchboard Automation Guides: https://junctionpanel.dev/blog/topics/switchboard/ - Guides for routing Linear issues into agent runs, pull requests, analytics, and gradual automation rollout. - AI Agent Review and Approval Workflows: https://junctionpanel.dev/blog/topics/reviews-and-approvals/ - Field notes on diff review, mobile PR review, safe approvals, branch hygiene, and stopping bad agent runs. - Multi-Agent Orchestration Notes: https://junctionpanel.dev/blog/topics/multi-agent-orchestration/ - Guides for coordinating multiple AI coding agents across machines, repositories, branches, and MCP workflows. ## Blog - Blog index: https://junctionpanel.dev/blog/ - RSS feed: https://junctionpanel.dev/blog/rss.xml - Run a Multi-Repo AI Agent Ops Review: https://junctionpanel.dev/blog/multi-repo-agent-ops-review/ - Use a weekly checklist to spot stale sessions, noisy prompts, and branch drift before multi-repo agent work becomes chaos. - Detect Prompt Regressions in AI Coding Agents: https://junctionpanel.dev/blog/prompt-regression-detection-for-agents/ - Compare old and new prompts with fixed tasks so Claude Code and Codex do not drift into broader or noisier behavior. - Shift Handoff for AI Agents: A Developer's Playbook: https://junctionpanel.dev/blog/shift-handoff-for-ai-agents/ - Hand off active Claude Code and Codex work between people without losing context, ownership, or review history. - How to Build an AI Agent Escalation Policy: https://junctionpanel.dev/blog/ai-agent-escalation-policy/ - Create a simple rule set for when an agent should continue, pause, ask for approval, or hand work back to a human. - How to Route AI Agent Work by Task Severity: https://junctionpanel.dev/blog/task-severity-routing-for-agents/ - Route low, medium, and high-risk Claude Code and Codex work to different approval paths and supervision levels. - How to Handle Security-Sensitive AI Agent Work Safely: https://junctionpanel.dev/blog/security-sensitive-agent-workflow/ - Keep Claude Code and Codex away from risky edits unless the task, approval path, and diff are tightly scoped. - How to Write a Destructive Command Policy for AI Agents: https://junctionpanel.dev/blog/ai-agent-destructive-command-policy/ - Define when rm, reset, migration, and deployment commands need human approval so Claude Code and Codex stay bounded. - How to Run a Docs-Only AI Agent Workflow: https://junctionpanel.dev/blog/docs-only-agent-workflow/ - Use Claude Code or Codex for docs-only tasks with tight scope, fast review, and fewer unnecessary approvals. - How to Roll Out Switchboard Gradually Without Automating Everything: https://junctionpanel.dev/blog/how-to-roll-out-switchboard-gradually-without-automating-everything/ - Introduce Switchboard with a phased rollout that starts small, protects review quality, and expands only after routes and issues are proven. - Flaky Test Fixes With AI Agents: A Safe Debugging Workflow: https://junctionpanel.dev/blog/flaky-test-fix-with-ai-agents/ - Separate real regressions from flaky tests, then use Claude Code or Codex to repair the test or the code with a tighter review loop. - How to Supervise a Long-Running Refactor With AI Agents: https://junctionpanel.dev/blog/long-running-refactor-supervision/ - Keep a Claude Code or Codex refactor on track with checkpoints, diffs, approvals, and explicit stop points. - Turn a Bug Report Into an AI Agent Runbook: https://junctionpanel.dev/blog/bug-report-to-agent-runbook/ - Convert a vague issue into a bounded Claude Code or Codex run with scope, checks, and a clear stop condition. - Why a Browser Control Surface Beats Remote Desktop for Claude Code and Codex: https://junctionpanel.dev/blog/why-a-browser-control-surface-beats-remote-desktop-for-claude-code-and-codex/ - Compare browser-based agent control with remote desktop when supervising local Claude Code and Codex sessions from phones or laptops. - How to Run Overnight Bug-Fix Queues with Switchboard: https://junctionpanel.dev/blog/how-to-run-overnight-bug-fix-queues-with-switchboard/ - Use Switchboard to keep a bounded Linear bug queue moving overnight while preserving review gates, routing discipline, and pull request quality. - How to Structure One Junction Account for a Small Team: https://junctionpanel.dev/blog/how-to-structure-one-junction-account-for-a-small-team/ - Plan a small-team Junction setup with clear daemon ownership, provider auth boundaries, plan limits, review habits, and Switchboard timing. - How to Triage AI Agent Runs During Your Commute: https://junctionpanel.dev/blog/commute-ai-agent-triage/ - Use short commute check-ins to review Claude Code and Codex progress, block risky work, and keep useful runs moving. - AI Coding Agent Incident Response: A Practical Playbook: https://junctionpanel.dev/blog/ai-coding-agent-incident-response/ - Respond to production incidents with Claude Code or Codex using tighter scope, live monitoring, and a clean handoff from diagnosis to patch. - How to Turn Handoff Notes into Agent Instructions: https://junctionpanel.dev/blog/how-to-turn-handoff-notes-into-agent-instructions/ - Convert repeated human handoff notes into reusable Claude Code and Codex instructions, templates, and review guidance inside Junction. - How to Prevent Claude Code and Codex Cross-Talk on the Same Repo: https://junctionpanel.dev/blog/how-to-prevent-claude-code-and-codex-cross-talk-on-the-same-repo/ - Run Claude Code and Codex on the same repository without mixing branches, prompts, context, approvals, or review paths. - How to Run an On-Call AI Agent Workflow: https://junctionpanel.dev/blog/on-call-ai-agent-workflow/ - Build a calm on-call routine for Claude Code and Codex with scoped approvals, notifications, and mobile review. - How to Recover from a Bad Branch or Workspace Drift: https://junctionpanel.dev/blog/how-to-recover-from-a-bad-branch-or-workspace-drift/ - Recover from AI agent branch drift by stopping the run, preserving evidence, separating changes, and restarting from a reviewable state. - How to Keep One Junction Account Clean When Machines Come and Go: https://junctionpanel.dev/blog/how-to-keep-one-junction-account-clean-when-machines-come-and-go/ - Keep your Junction account understandable as laptops, workstations, and servers are added, retired, renamed, or repurposed. - How to Run AI Coding Agents During a Release Freeze: https://junctionpanel.dev/blog/ai-agent-release-freeze-workflow/ - Use a release-freeze policy to keep Claude Code and Codex moving on safe work while protecting release-critical branches and approvals. - How to Keep Long-Running Agent Work Unblocked Across Time Zones: https://junctionpanel.dev/blog/how-to-keep-long-running-agent-work-unblocked-across-time-zones/ - Build a time-zone handoff routine for long-running Claude Code and Codex work using session state, notes, notifications, and review gates. - How to Review Agent PRs on Mobile Without Slowing Yourself Down: https://junctionpanel.dev/blog/how-to-review-agent-prs-on-mobile-without-slowing-yourself-down/ - Use mobile review for fast triage of AI agent pull requests while saving risky diffs, broad changes, and final merges for desktop. - How to Build an After-Hours Approval Routine for Agent Runs: https://junctionpanel.dev/blog/how-to-build-an-after-hours-approval-routine-for-agent-runs/ - Create a safer after-hours routine for Claude Code and Codex approvals using notifications, risk checks, and mobile review discipline. - How to Use Switchboard Analytics to Find Automation Friction: https://junctionpanel.dev/blog/how-to-use-switchboard-analytics-to-find-automation-friction/ - Use Switchboard run analytics and activity patterns to spot bad routes, unclear issues, flaky repos, and automation that needs review. - How to Tell Whether a Repository Is Ready for Switchboard: https://junctionpanel.dev/blog/how-to-tell-whether-a-repository-is-ready-for-switchboard/ - Evaluate tests, branch hygiene, instructions, review paths, and daemon setup before routing a repository into Switchboard automation. - How to Design Linear Statuses for Agent Automation: https://junctionpanel.dev/blog/how-to-design-linear-statuses-for-agent-automation/ - Shape Linear statuses so Switchboard automation has clear pickup, running, review, blocked, and done states for AI agent work. - How to Decide Which Issues Belong on Switchboard: https://junctionpanel.dev/blog/how-to-decide-which-issues-belong-on-switchboard/ - Use a practical selection rubric to decide which Linear issues are ready for Switchboard automation and which should stay manual. - How to Organize Multiple Repositories in One Junction Workspace: https://junctionpanel.dev/blog/how-to-organize-multiple-repositories-in-one-junction-workspace/ - Keep multiple repositories understandable in Junction with clear working directories, session names, Git state, and review habits. - How to Run an AI Agent Hotfix Queue: https://junctionpanel.dev/blog/ai-agent-hotfix-queue/ - Build a tight hotfix queue for Claude Code and Codex so urgent fixes get fast attention without turning into an uncontrolled backlog. - How to Route Claude Code and Codex Jobs to Different Machines: https://junctionpanel.dev/blog/how-to-route-claude-code-and-codex-jobs-to-different-machines/ - Use task shape, repo location, credentials, and machine availability to decide where Claude Code or Codex should run. - How to Separate Personal and Work Daemons in Junction: https://junctionpanel.dev/blog/how-to-separate-personal-and-work-daemons-in-junction/ - Keep personal projects and work repositories cleanly separated with daemon boundaries, provider auth, Git identity, and plan choices. - When to Put Claude Code or Codex on a Headless VPS: https://junctionpanel.dev/blog/when-to-put-claude-code-or-codex-on-a-headless-vps/ - Decide when a headless VPS is the right execution host for Claude Code or Codex, and when your laptop should stay the agent machine. - Set a Session Retention Policy for AI Agents: https://junctionpanel.dev/blog/session-retention-policy-for-agents/ - Keep useful Claude Code and Codex history without letting old sessions, branches, and notes take over the active surface. - Use a Dedicated Agent Box for Claude Code and Codex: https://junctionpanel.dev/blog/use-a-dedicated-agent-box-for-claude-code-and-codex/ - Build a cleaner local AI agent workflow by running Claude Code and Codex on one stable machine while controlling them from any browser. - How to Clean Up Branches After AI Agent Runs: https://junctionpanel.dev/blog/branch-cleanup-after-agent-runs/ - Decide when to merge, delete, prune, or keep agent branches so worktree cleanup stays reviewable and your repo stays readable. - How to Search AI Agent Session History for Useful Context: https://junctionpanel.dev/blog/search-ai-agent-session-history/ - Find the right prior Claude Code or Codex run faster by searching sessions for branch, repo, outcome, and failure mode. - Use Agent Transcripts as an Audit Trail: https://junctionpanel.dev/blog/agent-transcript-audit-trail/ - Keep Claude Code and Codex sessions reviewable by capturing output, approvals, diffs, and the reason a run changed direction. - How to Write AI Coding Agent Runbooks That Actually Help: https://junctionpanel.dev/blog/ai-coding-agent-runbooks/ - Turn common Claude Code and Codex tasks into short repo-local runbooks that reduce drift and make supervision easier. - How to Name AI Coding Agent Sessions So They Stay Findable: https://junctionpanel.dev/blog/ai-coding-agent-session-naming/ - A naming scheme for Claude Code and Codex sessions that makes search, handoff, and cleanup faster across devices and worktrees. - How to Route Human Approvals for AI Agent Work: https://junctionpanel.dev/blog/human-approver-routing/ - Build a simple approver map so Claude Code and Codex ask the right person at the right time for risky changes. - How to Triage Morning Agent Runs Before You Start Work: https://junctionpanel.dev/blog/morning-agent-run-triage/ - Use a repeatable morning pass to check Claude Code and Codex runs, clear blockers, and decide what deserves deeper review. - Agent Session Taxonomy: A Practical Way to Label and Search Runs: https://junctionpanel.dev/blog/agent-session-taxonomy/ - A practical taxonomy for naming AI agent sessions by intent, risk, and lifecycle so you can search, route, and archive them later. - Automation Candidate Grooming: How to Pick the Right AI Work: https://junctionpanel.dev/blog/automation-candidate-grooming/ - A practical filter for deciding which agent tasks are worth automating, and which should stay manual because the blast radius is too wide. - One Agent, One Task: The Discipline That Keeps Runs Reviewable: https://junctionpanel.dev/blog/one-agent-one-task-discipline/ - A simple rule for keeping AI agent runs reviewable: one run, one outcome, one branch, and one stop point. - Parallel Agent Experimentation: Compare Claude Code and Codex Fairly: https://junctionpanel.dev/blog/parallel-agent-experimentation/ - How to run the same task with Claude Code and Codex in parallel so you can compare diffs, risk, and review effort without guesswork. - Stop Before Shared State Damage: A Better Rule for Agent Runs: https://junctionpanel.dev/blog/stop-before-shared-state-damage/ - A stop rule for AI agent runs that touch shared branches, migrations, or other repo state before a small mistake becomes expensive. - Weekly Agent Ops Checklist: Keep Claude Code and Codex Tidy: https://junctionpanel.dev/blog/weekly-agent-ops-checklist/ - A weekly sweep for cleaning up runs, branches, notifications, and daemon state before small bits of drift become busywork. - Configure Switchboard Route Settings for Team and Repo Routing: https://junctionpanel.dev/blog/configure-switchboard-route-settings-for-team-and-repo-routing/ - Learn how Switchboard route settings map Linear teams and repositories to daemons, agents, models, branches, and automation rules. - Send Conflict-Fix Instructions Back to Agents: https://junctionpanel.dev/blog/send-conflict-fix-instructions-back-to-agents/ - Turn merge conflicts and branch drift into a focused follow-up task for Claude Code or Codex instead of manually restarting work. - Use File Mentions and Image Attachments to Give Agents Better Context: https://junctionpanel.dev/blog/use-file-mentions-and-image-attachments-to-give-agents-better-context/ - Give Claude Code and Codex better starting context with file mentions, screenshots, and focused prompts in Junction. - Use Plan Mode Before Edits Start: https://junctionpanel.dev/blog/use-plan-mode-before-edits-start/ - Use plan mode in Junction to make Claude Code and Codex explain risky work before edits, commands, and pull requests begin. - Archive AI Agent Sessions Without Losing History: https://junctionpanel.dev/blog/archive-ai-agent-sessions-without-losing-history/ - Keep active Claude Code and Codex chats manageable while preserving transcripts, review context, and useful handoff details. - Choose Models Per Chat for AI Coding Agents: https://junctionpanel.dev/blog/choose-models-per-chat-for-ai-coding-agents/ - Learn why per-chat model selection helps match Claude Code and Codex runs to task risk, cost, speed, and review expectations. - Keep Claude Code and Codex Auth Separate on Each Daemon: https://junctionpanel.dev/blog/keep-claude-code-and-codex-auth-separate-on-each-daemon/ - Learn how daemon-scoped Claude Code, Codex, GitHub, and model settings keep local AI coding workflows easier to route and debug. - Use CLAUDE.md and AGENTS.md to Steer Local Agent Runs: https://junctionpanel.dev/blog/use-claude-md-and-agents-md-to-steer-local-agent-runs/ - Write durable repository instructions that help Claude Code and Codex follow project rules while Junction keeps execution local. - Resume AI Agent Sessions Across Devices: https://junctionpanel.dev/blog/resume-ai-agent-sessions-across-devices/ - Learn how to keep Claude Code and Codex context available when you move between desktop, browser, phone, and archived history. - Stop and Steer Live AI Agent Runs Before They Drift: https://junctionpanel.dev/blog/stop-and-steer-live-ai-agent-runs-before-they-drift/ - Learn when to stop, redirect, or continue Claude Code and Codex runs before a small mistake turns into a large diff. - Use the Terminal and File Browser as an Agent Control Surface: https://junctionpanel.dev/blog/use-the-terminal-and-file-browser-as-an-agent-control-surface/ - See how terminal output, workspace files, diffs, and agent transcripts work together when supervising Claude Code and Codex. - Plan Around AI Coding Agent Rate Limits: https://junctionpanel.dev/blog/plan-around-ai-coding-agent-rate-limits/ - Learn how to plan Claude Code and Codex workflows around usage windows, quotas, local telemetry, and review timing without guessing. - Use Branch Suggestions to Keep Agent Runs Reviewable: https://junctionpanel.dev/blog/use-branch-suggestions-to-keep-agent-runs-reviewable/ - Keep Claude Code and Codex work reviewable by starting each local agent run on the right branch, worktree, and pull request path. - Use Live Output Streaming to Catch Agent Problems Early: https://junctionpanel.dev/blog/use-live-output-streaming-to-catch-agent-problems-early/ - Learn how real-time Claude Code and Codex output helps you catch drift, bad commands, and stalled agent runs before the diff grows. - Claude Code vs Codex for Local-First Development: https://junctionpanel.dev/blog/claude-code-vs-codex-for-local-first-development/ - Compare Claude Code and Codex for local-first agent workflows by task shape, context needs, review style, and Junction fit. - Track AI Coding Agent Costs Per Session: https://junctionpanel.dev/blog/track-ai-coding-agent-costs-per-session/ - Learn why per-turn and per-session cost visibility matters when Claude Code and Codex runs become long, parallel, or automated. - Turn Local AI Agent Runs Into Pull Requests: https://junctionpanel.dev/blog/turn-local-ai-agent-runs-into-pull-requests/ - A practical checklist for moving Claude Code or Codex work from a local agent run to a reviewable pull request. - Custom Prompt Templates for AI Coding Agents: https://junctionpanel.dev/blog/custom-prompt-templates-for-ai-coding-agents/ - Use custom prompt templates to make repeated Claude Code and Codex workflows clearer, safer, and easier to run from Junction. - Inspect AI Agent Runs Without Terminal Hunting: https://junctionpanel.dev/blog/inspect-ai-agent-runs-without-terminal-hunting/ - Learn what to inspect after Claude Code or Codex runs: status, output, logs, diffs, approvals, and review-ready handoffs. - MCP Server for AI Agent Orchestration: https://junctionpanel.dev/blog/mcp-server-for-ai-agent-orchestration/ - Learn how Junction's built-in MCP server lets local agents create, prompt, and inspect other agent runs without moving code. - How the Junction Daemon Keeps AI Agents Local: https://junctionpanel.dev/blog/how-the-junction-daemon-keeps-ai-agents-local/ - Understand how Junction's daemon, web app, relay, and agent sessions work together while Claude Code and Codex run locally. - Manual AI Agent Runs vs Switchboard Automation: https://junctionpanel.dev/blog/manual-ai-agent-runs-vs-switchboard-automation/ - Decide when to steer Claude Code or Codex manually and when to let Switchboard turn Linear issues into pull requests. - Why Junction Is a PWA for AI Coding Agents: https://junctionpanel.dev/blog/why-junction-is-a-pwa-for-ai-coding-agents/ - See why a PWA control surface fits local AI coding agents: installability, mobile review, push notifications, and local execution. - Codex CLI vs Codex Web for Local-First Workflows: https://junctionpanel.dev/blog/codex-cli-vs-codex-web-local-first-workflows/ - Compare Codex CLI and Codex web by execution location, local environment needs, review flow, and when Junction fits. - Use Claude Code and Codex Side by Side: https://junctionpanel.dev/blog/use-claude-code-and-codex-side-by-side/ - Run Claude Code and Codex in separate local sessions, keep context isolated, and compare results without mixing agent work. - Write Linear Issues Ready for AI Agent Automation: https://junctionpanel.dev/blog/write-linear-issues-ready-for-ai-agent-automation/ - Learn how to scope Linear issues so Switchboard can turn clear, bounded work into reviewable AI agent pull requests. - How to Review AI Agent Diffs from Your Phone: https://junctionpanel.dev/blog/review-ai-agent-diffs-from-your-phone/ - Learn when mobile diff review is useful, when to wait for desktop, and how to triage Claude Code or Codex changes safely. - Junction Pricing: Free vs Core vs Switchboard: https://junctionpanel.dev/blog/junction-free-vs-core-vs-switchboard/ - Compare Junction Free, Core, and Switchboard by workflow: one daemon, unlimited chats, or Linear issue-to-pull-request automation. - Set Up Junction for Claude Code and Codex: https://junctionpanel.dev/blog/set-up-junction-for-claude-code-and-codex/ - Install the Junction daemon, pair your browser, and start controlling Claude Code or Codex from a local-first web app. - Control AI Coding Agents from Your Phone Without Moving Your Code: https://junctionpanel.dev/blog/control-ai-coding-agents-from-your-phone/ - A practical guide to monitoring Claude Code and Codex from your phone while your code, terminals, and credentials stay on your own machine. - Git Worktree Isolation for AI Coding Agents: https://junctionpanel.dev/blog/git-worktree-isolation-for-ai-coding-agents/ - Keep parallel agent runs from colliding by giving each task its own worktree, branch, and review path instead of sharing one checkout. - How Switchboard Turns Linear Issues Into Pull Requests: https://junctionpanel.dev/blog/how-switchboard-turns-linear-issues-into-pull-requests/ - See how Junction's Switchboard watches Linear, spawns isolated worktrees, runs agents, and opens pull requests when the work is done. - How to Approve AI Agent Actions Safely Without Slowing Down: https://junctionpanel.dev/blog/how-to-approve-ai-agent-actions-safely/ - Use permission modes, scoped approvals, and local-first execution to keep AI coding agents productive without rubber-stamping risky changes. - How to Manage Multiple AI Coding Agents Across Machines: https://junctionpanel.dev/blog/how-to-manage-multiple-ai-coding-agents-across-machines/ - Learn the workflow for routing AI agent work across a laptop, workstation, and VPS without losing track of approvals, diffs, or status. - How to Monitor Claude Code from Your Phone Without SSH: https://junctionpanel.dev/blog/monitor-claude-code-from-your-phone/ - Keep a Claude Code session local, read live output on mobile, and decide when to approve, stop, or review the next step. - How to Monitor Codex from Your Phone Without a Cloud Sandbox: https://junctionpanel.dev/blog/monitor-codex-from-your-phone/ - Watch Codex runs on mobile, keep execution local, and review blockers, diffs, and PR state without handing the repo to a hosted workspace. - Junction Encrypted Relay, Explained: What It Protects and Why: https://junctionpanel.dev/blog/junction-encrypted-relay-explained/ - Understand what Junction's encrypted relay protects, what it does not, and why local-first remote access is safer than ad hoc SSH or port forwarding. - What AI Coding Agent Notifications Should Actually Tell You: https://junctionpanel.dev/blog/what-ai-coding-agent-notifications-should-actually-tell-you/ - Learn which agent notifications deserve attention, how to avoid alert spam, and why finish, approval, and error alerts matter most. - What an AI Coding Agent Dashboard Should Actually Do: https://junctionpanel.dev/blog/what-an-ai-coding-agent-dashboard-should-actually-do/ - A practical checklist for dashboards that supervise local AI agents well: live streams, approvals, diffs, notifications, and Git state. - What OpenCode Users Need From a Control Surface: https://junctionpanel.dev/blog/what-opencode-users-need-from-a-control-surface/ - OpenCode can run in the browser and attach to a terminal, but serious workflows still need remote approvals, notifications, and a broader dashboard. - Why Local-First AI Coding Agents Still Need a Control Surface: https://junctionpanel.dev/blog/why-local-first-ai-coding-agents-still-need-a-control-surface/ - Local execution protects your repo, but you still need a browser and phone-friendly way to watch runs, approve actions, and review diffs.