shakshukan

Simple markdown files definitely work, but the downside is that they only hold what you actually remember to write down / tell your agents to write down. The useful learnings are usually in the session itself i.e. the 3 approaches the agent tried before one of them worked.

Beacon keeps the full execution trace (prompts, reasoning, tool calls, commands) outside the agent's context and distills lessons from it. Ultimately the agent still only has access to snippets of information (via skill progressive disclousure) but it's drawn from much richer session data rather than what you remembered to note down. Also you don't have to maintain it yourself!

Beacon packages memory into skills, which you can scope to specific repos or projects instead of having it apply generally across any task.

This directionally makes a ton of sense! Most EDR solutions like Crowdstrike are still playing catch up when it comes to AI agent observability. This is only going to become more important as these tools continue to proliferate in the enterprise.