Most personal knowledge systems fail not because capture is difficult, but because notes rarely make it back into decisions and useful work. COG tackles that gap by treating the vault as both memory and an operating surface: agents can organize material, connect it to ongoing work, and check whether their outputs meet explicit criteria.
What Sets It Apart
- Plain files are the source of truth. Markdown, Git, and optional iCloud keep knowledge inspectable and portable rather than locked in a proprietary database.
- Work is divided among specialists. Workers handle extraction and updates, while read-only verifiers inspect artifacts independently; a worker does not certify its own result.
- It connects personal knowledge to team and product work. Skills span capture, synthesis, research, meeting processing, and workflows involving tools such as GitHub, Linear, Slack, and PostHog. This makes the system more than a note organizer, but those integrations require setup.
Who It’s For—and the Trade-Off
Great fit for people who already use Markdown or Obsidian and want an AI agent to maintain and synthesize a working knowledge base across multiple agent platforms. Look elsewhere if you want a polished hosted knowledge app, built-in collaboration, or a system that works without configuring an AI agent and its integrations. Local files improve portability, but the workflow still depends on the capabilities and API costs of the chosen agent.