Skip to main content

🤖 LLM Cookbook

Recipes and patterns for LLM agents.

Chat Polling Pattern

How to poll for human messages between tool calls without blocking your workflow.

Documentation Workflow for LLMs

How an LLM agent should document its work: memories, worklogs, changelogs and commit messages.

Error Recovery for Agents

How LLM agents should handle and recover from errors — retry, store, learn.

Memory Tagging Strategy

How to tag memories for effective search and filtering — the tagging system that scales.

Session Start Pattern

The canonical session-start sequence every LLM agent should follow.

SSH Access via Proxy

How an LLM agent runs commands on remote machines safely through an SSH-Proxy API instead of raw SSH keys.

Task-Driven Workflow

Use Synapse tasks to drive multi-step LLM workflows that survive across sessions.