AXME
Everything to help you build, deploy, and govern AI agents
Guides, migration paths, blog posts, code examples, integration docs, and compliance references — organized by topic so you can find what you need without digging.
RESOURCES
Featured guides
Long-form references for production agent teams.
Agentic orchestration
Category-defining overview.
Durable execution
The pattern for reliable async.
Human-in-the-loop
HITL patterns for production.
Multi-agent orchestration
Coordinate without losing state.
AI agent governance
Enterprise visibility and control.
AI agent cost management
Caps, attribution, optimization.
BLOG
Recent posts
Production notes from the AXME team.
Your AI Agent Spent $500 Overnight and Nobody Noticed
How runaway loops burn token budgets.
What Temporal Can't Do
Determinism vs agents.
I Stopped Building Webhook Retry Logic
From webhooks to intent lifecycle.
Temporal Alternative Without Running a Cluster
Moving toward intent-based execution.
AI Agent Kill Switch
Stop rogue agents in production.
Human Approval for AI Agent Workflows
HITL without 200 lines of glue.
Related reading
Deeper dives from the AXME blog.
Your AI Agent Spent $500 Overnight and Nobody Noticed
AI agents call LLMs. LLMs cost money per token. Nobody tracks it per agent. One runaway loop and your OpenAI bill is a disaster.
Read post →What Temporal Can't Do: Human Approval Mid-Workflow
Temporal gives you durable execution. But adding a human approval step mid-workflow requires building a signal handler, notification service, and UI. There's a simpler way.
Read post →I Stopped Building Webhook Retry Logic. Here's What I Use Instead.
Exponential backoff, jitter, dead letter queues, idempotency keys, HMAC verification - all to deliver one message reliably. There are better options now.
Read post →Your AI Agent Is Running Wild and You Can't Stop It
AI agents go rogue. They send thousands of emails, make unauthorized API calls, burn through budgets. You need a kill switch that works in under 1 second.
Read post →How to Add Human Approval to AI Agent Workflows Without Building It Yourself
Adding a human approval step to an AI agent workflow means building a notification service, reminder scheduler, escalation chain, and webhook handler. Or you can use 4 lines of code.
Read post →How I Fixed Claude Code's Amnesia (Actually)
Claude Code forgets your project every session. CLAUDE.md helps, but it doesn't scale. I built an MCP server plugin that gives Claude Code persistent memory, decisions, and safety guardrails.
Read post →
Build and learn
Ship your first durable agent — in under 10 minutes.
Free tier. No credit card. Self-host or hosted — your choice.