borgmemory: Instructions file for Codex

AGENTS.md — Project Borg

What is Borg?

Borg is a memory system connected via MCP. It maintains a knowledge graph of entities, facts, and procedures extracted from past conversations across all your AI tools. Use it to avoid re-explaining context and to make decisions informed by prior work.

When to use Borg

borg_think — Call BEFORE starting complex tasks

Call borg_think before any task that would benefit from knowing what was done previously. This compiles relevant context from the knowledge graph and returns it as structured output.

Always call borg_think when:

• Starting work on any file or module you haven't seen in this session
• Debugging an issue (retrieves past bugs, patterns, and related decisions)
• Making an architecture or design decision (retrieves prior decisions and rationale)
• Writing documentation, proposals, or RFPs (retrieves relevant facts and terminology)
• Asked about project history, prior decisions, or "what did we decide about X"
• Working in a namespace/project area you haven't touched recently

Example calls:

borg_think(query="APIM authentication issues", namespace="azure-msp", task_hint="debug")
borg_think(query="AMA compliance tracking architecture", namespace="azure-msp", task_hint="architecture")
borg_think(query="Project Sentinel customer targeting", namespace="azure-msp", task_hint="writing")

Task hints (use the most specific one):

• debug — retrieves episodic memory + procedures + graph traversal
• architecture — retrieves semantic facts + graph neighborhood
• compliance — retrieves episode evidence + facts, excludes procedures
• writing — retrieves semantic facts for accurate terminology
• chat — lightweight fact lookup (default)

borg_learn — Call AFTER significant events

Call borg_learn to record decisions, discoveries, and important context that should persist across sessions. The background worker extracts entities, facts, and procedures automatically.

Always call borg_learn when:

• A significant decision is made (technology choice, architecture change, policy)
• A non-obvious bug is diagnosed and fixed (root cause + solution)
• A new pattern or convention is established
• Important context is shared that would be lost when this session ends
• A meeting outcome, customer conversation, or requirement is discussed