Articles
Everything written so far.
Every Starkslab article: OpenClaw source reads, agent architecture, coding-agent workflows, and reviews of the tools around them.
- How to Rotate API Keys: A Checklist for Application RecoveryTo rotate an application's API key, you need to update every program that uses it and check the results. This checklist includes a non-secret tracking register, a routine rotation sequence and a separate path for urgent exposure.
- Infisical Secrets Management Explained: Agent Vault, Certificates, Keys and AccessInfisical raised $40M at a $600M valuation. This extended guide explains what its platform offers, how secret delivery differs from Agent Vault brokering, what pricing and self-hosting involve, and what a technical operator still needs to verify.
- API Key Rotation After the Railway Incident: My Apps Still Had the Old KeysOn 21 October 2026, app-hosting platform Railway disclosed a security incident and advised users to replace credentials. I did—but parts of my web application and background jobs still had the old keys. Here is what I changed to get those replacements into the software that needed them.
- Choosing a deterministic workflow harness for LLMs: an operator’s checklistChoose a workflow harness by checking who owns routing, persisted results, retry policy, approval and external writes. Compare one PR-review task across three execution patterns, then use concrete failure probes and a decision worksheet to record what is documented, observed or still unverified.
- Inside an AI agent's basic control loop: tools, state and stops in PythonInspect one execution of Federico Jan's Minimal Agent Framework at a pinned commit. Follow a local file read/write task from scripted model actions through tool validation, dispatch, state updates and final output; use trace events, deliberate halts and replay to build a worksheet readers can apply to another agent repository.
- AI Agent Frameworks: Choose the Control Surface Your Runtime NeedsA practical guide for technical solopreneurs comparing AI agent frameworks by the operating controls they need: tools, memory, schedules, traces, gateways, and review gates.
- How to Read an AI-Agent System’s Source Before You Configure or Operate It — Gate 7 live update 2 — Gate 7 live update 3A builder-readable walkthrough for mapping an AI-agent system from source: identify its architecture, tools, gateways, schedules, state, and review points, then use that map to configure, operate, and troubleshoot the system with a repeatable process.
- Anthropic Agent SDK: What It Ships, What It Leaves to You, and How a Solo Operator Fills the GapThe Anthropic Agent SDK gives you tool use, streaming, and single-agent loops. Here is an honest map of what it leaves unfinished — and how a solo technical operator closes those
- AI Agent ToolsPydantic AI Agent Framework: Typed Control Surface, Not MagicPydantic AI is useful because it makes typed agent contracts visible. The current evidence supports a control-surface map, not runtime, safety, benchmark, or adoption claims.
- AI Agent ToolsMastra Agent Framework: What Its TypeScript Control Surface ShowsMastra is useful Starkslab evidence because its public repo and docs expose a TypeScript agent framework with clear control surfaces. That supports inspection, not adoption guidance.
- AI Agent ToolsOpen Computer Use MCP: The Computer Runtime BoundaryOpen Computer Use MCP is useful Starkslab evidence because it makes the computer-use runtime boundary visible. That supports inspection, not adoption guidance.
- AI Agent ToolsHerdr Agent Multiplexer: Terminal Control Surface for AgentsHerdr is useful Starkslab evidence because its repo and docs expose an agent-aware terminal multiplexer: real panes, persistent sessions, state rollups, and CLI/socket controls.
- AI Agent ToolsEntire CLI AI Agent Sessions: Git-Native Provenance for Agent WorkEntire CLI is useful Starkslab source stock because it treats AI agent sessions as Git-indexed provenance. The source read supports workflow-inspection lessons, not adoption, runtime, security, or compliance claims.
- AI Agent ToolsQwen Code Agent CLI: What the Source Shows About Its Control SurfaceQwen Code is useful Starkslab evidence because its official source and docs expose a modern agent CLI control surface. That supports inspection, not adoption guidance.
- AI Agent ToolsAntigravity CLI: What Changed After Gemini CLI Became A Transition StoryAntigravity CLI changes how operators should read Gemini CLI guidance: currentness and control-surface evidence, not runtime, migration, security, or adoption proof.
- AI Agent ToolsOpenCode Shows the Real Boundary of Terminal Coding AgentsSource-read note on what OpenCode reveals about terminal coding-agent workflows, and why source evidence is enough to map the boundary but not enough to recommend adoption.
- AI Agent ToolsBrowser Harness Is an Editable CDP Sidecar, Not a Magic Browser AgentBrowser Harness is useful because it makes the browser-agent control boundary visible. The source read supports a small CDP/helper/domain-skill harness, not claims about safe accounts, runtime reliability, pricing, adoption, or production readiness.
- AI Agent ToolsUI-TARS Desktop: The Four Operator Surfaces Behind Computer-Use AgentsUI-TARS Desktop is useful Starkslab source stock because it exposes the topology behind computer-use agents. The source read supports an operator-surface map, not a benchmark, safety claim, or adoption recommendation.
- AI Agent ToolsAI Agent Sandbox Substrates: What CubeSandbox Makes VisibleAn AI agent sandbox is a substrate contract, not a checkbox on an SDK. CubeSandbox is useful because its source makes the substrate layers visible, but the current evidence does not prove runtime safety, production use, E2B parity, benchmark performance, or Starkslab adoption.
- AI Agent ToolsOpenAI Agents SDK Is a Workflow-Control Stack, Not Just an Agent LoopOpenAI Agents SDK is useful because its source-visible surfaces expose workflow-control boundaries without proving runtime quality, production readiness, sandbox safety, benchmarks, or adoption value.
- AI Agent ToolsAgent CLI Control Surfaces: What To Compare Before You Trust a Coding AgentThe useful agent CLI comparison is not a winner ranking. It is a control-surface audit: what the tool can see, edit, execute, delegate, extend, report, and recover from before an operator trusts it.
- AI Agent ToolsSuperpowers Skills Framework: Source Read, Control-Plane Lessons, and Adoption BoundariesSuperpowers is useful proof stock for agent skills as behavior-changing source artifacts, but the source read does not prove install safety, runtime enforcement, or adoption readiness.
- AI Agent ToolsHow Agent Tool Radar Scores Open-Source AI Agent ToolsA methodology note for Agent Tool Radar: public GitHub signals, deterministic scoring, evidence boundaries, and why scores are research leads, not recommendations.
- AI Agent ToolsComputer Use Agents Are Website QA Sensors, Not Site FixersA proof-safe operator note for computer use agents website QA: visible-state sensors, route parity checks, and browser evidence without source-truth overreach.
- AI Agent ToolsWhat Is a Coding-Agent Control Plane? Skills, MCP, Config, and Safety GatesA coding-agent control plane is the operator-owned layer around skills, MCP servers, config, memory, sessions, and safety gates.
- AI Agent ToolsThe AI Developer Tools I Built and Open Sourced
- How to Build an AI Agent Beyond the Demo: The Production StackA practical map of the production stack behind AI agents: runtime, tools, memory, workflows, observability, evals, guardrails, deployment gates, and control-plane boundaries.
- AI Agent ToolsMCP Gateway for AI Agents: Why Tool Access Needs a Sandbox ContractAgent tool access is getting more serious than "give the model another integration." Once an agent can touch repositories, analytics, Search Console, deployment, public publishing, or account state, the real question becomes: what is it allowed to read, whe...
- AI Agent Toolsdmux Shows the Useful Coding-Agent UI Is a Worktree CockpitA proof-support note for AI Agent Tools: dmux is useful as a worktree cockpit pattern, not a validated runtime recommendation.
- AI Agent ToolsLangSmith Observability: The Trace Layer AI Agents Need Before ProductionLangSmith observability gives AI agents traces, runs, threads, dashboards, evals, and OpenTelemetry support. Here is what matters, what to steal, and where local traces still win.
- AI Agent ToolsThe Coding Agent Harness Layer: How to Orchestrate Claude Code, Codex, Gemini CLI, and More Without Workflow RotA practical field guide to the coding agent harness layer: when to stay native, when wrappers help, and when a harness earns its complexity.
- AI Agent ToolsCoding Agent Wrappers: Convenience, Durability, and Policy Risk Without the HypeA practical guide to coding agent wrappers: where they help, where they degrade workflow quality, and how to judge native CLI vs wrapper vs harness without policy melodrama.
- AI Agent ToolsCross-Agent Handoff: How to Move Work Between Coding Agents Without Losing ContinuityA practical field guide to cross-agent handoff: what belongs in the packet, when to resume instead of switch, and how to move work between coding agents without turning the workflow into mush.
- Build AI AgentAI Agent Architecture: Build Factories, Not Fake TeamsUse this AI agent architecture page to choose factory-model queues, worker contracts, QA gates, and rework lanes before building an AI agent framework.
- AI Agent ToolsClawSweeper Review: What It Actually DoesClawSweeper is an AI repo-maintenance worker with typed decisions, durable artifacts, and a proposal/apply split. Here’s what it actually does and why the design matters.
- AI Agent ToolsOpenAI Symphony Review: What It Actually DoesOpenAI Symphony is an issue-driven coding-agent orchestrator with repo-owned workflow contracts, reconciliation loops, and per-issue workspaces. Here’s what it actually does and what builders should steal.
- OpenClawOpenClaw Architecture Explained: Gateway, Sessions, Memory, and ToolsSkimmable OpenClaw system map covering the gateway, sessions, memory files, heartbeat and cron, and the execution layer from inbound message to action.
- OpenClawOpenClaw Cron vs Heartbeat: When to Use Each Without Creating NoisePractical OpenClaw scheduling guide: when heartbeat should batch recurring checks, when cron should own exact reminders, and how to avoid notification noise.
- OpenClawOpenClaw `HEARTBEAT.md` Example: Safe Defaults, Quiet Hours, and Real TemplatesCopyable OpenClaw `HEARTBEAT.md` templates and the rules for quiet hours, `HEARTBEAT_OK`, and keeping heartbeat silent by default.
- Claude Managed Agents Review: What Anthropic Actually ShipsClaude Managed Agents gives Anthropic a hosted agent runtime with sessions, environments, and tools. Here’s what it actually ships, what it gets right, and what control you give up.
- OpenClawOpenClaw Pro Setup: The Sync-to-Async Founder Operator StackAn advanced OpenClaw pro setup for founders and technical operators: Meta Glasses or voice-first capture, WhatsApp dispatch, Symphony as the async engine, and the doctrine that turns rough input into serious deliverables.
- How to Run Codex and Claude Code Through OpenClaw with ACPA practical OpenClaw Codex guide for running Codex and Claude Code through ACP, with the real runtime boundary, thread workflow, permission caveats, and decision rule.
- Compound Engineering Plugin Review: What It Actually DoesCompound Engineering Plugin review for builders: what the repo actually does, what is hype, what we validated, and which adapter pattern is worth stealing.
- AI Agent ToolsHermes Agent Review: What It Actually Does, What Works, and What Is HypeCode-first Hermes Agent review for builders: runtime architecture, memory, skills, messaging, scheduler, validation boundary, and what to trust versus ignore.
- What Karpathy’s autoresearch Actually DoesKarpathy’s autoresearch is a real autonomous experiment loop, but it is much narrower than the hype suggests. Here is what the repo actually does, what breaks when you generalize it, and the one pattern worth stealing.
- Build AI AgentAI Coding Agent Workflow: Guardrails, Delegation, ReviewA practical field guide to running coding agents safely: scope, isolation, verification, and review.
- AI Agent ToolsDatafast CLI for AI Agent Tools: Workflow, Artifacts, HandoffsA support page for the AI Agent Tools cluster: why Datafast CLI works as a JSON-first analytics workflow after the tool already exists.
- AI Agent ToolsSEO CLI for AI Developer Tools: SERPs, Audits, HandoffsA CLI-first SEO workflow for Starkslab: keywords, SERPs, audits, rank checks, and failure logs turned into reusable artifacts for AI agent tools.
- OpenClawOpenClaw Mac mini Setup Tutorial: WhatsApp, Tailscale, Termius, and tmux RecoveryOpenClaw Mac mini setup tutorial for WhatsApp control, Tailscale reachability, Termius recovery, tmux sessions, and a boring recovery rail.
- Claude Agent SDK Workspace: An Open-Source Multi-Workspace Agent Dev Environment (FastAPI + Vite)A deep, command-level teardown of claudeagentsdk (#005): an open-source agent workspace built around the Anthropic Agent SDK, with a FastAPI backend, a Vite/React frontend, and an optional Vercel Sandbox runner for async, reproducible runs.
- Inbox to Execution: The Human + Agent Loop We Use to Ship Without DriftA command-level teardown of the Starkslab inbox-to-execution loop: intake, triage, routing, artifact discipline, incidents, handoffs, metrics, and checklist controls.
- OpenClaw in the AI Developer Tools Stack: When to Use It and WhyA command-level, evidence-first teardown of where OpenClaw fits in an ai developer tools stack: architecture, workflows, incidents, throughput, and adoption boundaries.
- AI Agent ToolsAI Developer Tools: The Starkslab Operating System We Run in ProductionAI developer tools mapped as a production operating system: orchestration, coding delegation, SEO, analytics, intake, artifact gates, and support routes.
- Build AI AgentHow to Build Your First AI Agent: A Beginner Tutorial That Actually ShipsBuild your first AI agent with a local runtime, one constrained tool, visible traces, stop conditions, and a practical production checklist.
- How to Build AI Agent Tools: A Revenue Data CLI from ScratchI built trustmrr-cli — a TypeScript CLI giving AI agents access to verified revenue data for 4,900+ startups. Here's the architecture, the API workarounds, and why agent-native CLI tools are the missing layer.
- Build AI AgentBuild an AI Agent Framework in Python: MAF Loop, Tools, TracesBuild an AI agent framework in Python with MAF's one-loop runtime, typed tool schemas, JSONL traces, real API battle tests, and honest failure modes.
- Build AI AgentAI Agent Automation: How to Build an X SchedulerAI agent automation needs boring scheduling infrastructure. This X Scheduler proof note shows the Express API, Postgres state, cron worker, and failure modes.
- AI Agent ToolsHow to Build CLI Tools That AI Agents Can Actually UseI built datafast-cli and pointed an autonomous AI agent at it. 13 commands, 2 bugs found, and the 5 principles that make CLI tools genuinely useful as AI agent tools.
- OpenClawOpenClaw Heartbeat Guide: HEARTBEAT.md, HEARTBEAT_OK, Cron, and WakeupsSource-backed OpenClaw heartbeat guide: HEARTBEAT.md, HEARTBEAT_OK, cron wakes, service health checks, wake reasons, and what operators should configure.
- OpenClawOpenClaw Gateway Architecture: WebSocket Routing, Presence, PluginsOpenClaw gateway architecture explained: WebSocket presence, session routing, channel plugins, block streaming, and why the local gateway layer matters.
- OpenClawOpenClaw Self-Modification: Files, Memory, and GuardrailsOpenClaw self-modification is the writable-file layer behind SOUL.md, AGENTS.md, MEMORY.md, BOOTSTRAP.md, skills, and guardrails.
- OpenClawOpenClaw Source Code Structure: Gateway, Heartbeat, Skills, and Runtime ArchitectureOpenClaw source code structure teardown: gateway architecture, heartbeat wakes, skills, writable memory, session routing, channel plugins, and runtime boundaries.
- Build AI AgentEscape Velocity: Ship the Smallest Working SystemAcceleration comes from shipping the smallest working system, then compounding it with tight feedback loops.
- AI Agent ToolsWhat Is a Coding-Agent Control Plane? Skills, MCP, Config, and Safety GatesA source-observed field guide to the operator layer around coding agents: runtime routing, skills, MCP tools, project memory, sessions, and safety gates.