According to Harrison Chase, providing agents with file system access is critical for long-horizon tasks. It serves as a powerful context management tool, allowing the agent to save large tool outputs or conversation histories to files, then retrieve them as needed, effectively bypassing context window limitations.

To prevent an AI agent from repeating mistakes across coding sessions, create 'agents.md' files in your codebase. These act as a persistent memory, providing context and instructions specific to a folder or the entire repo. The agent reads these files before working, allowing it to learn from past iterations and improve over time.

When an AI agent like Claude Code nears its context limit where automatic compaction might fail, a useful hack is instructing it to "write a markdown file of your process and your progress and what you have left to do." This creates a manual state transfer mechanism for starting a new session.

To maximize an AI assistant's effectiveness, pair it with a persistent knowledge store like Obsidian. By feeding past research outputs back into Claude as markdown files, the user creates a virtuous cycle of compounding knowledge, allowing the AI to reference and build upon previous conclusions for new tasks.

Instead of a complex database, store content for personal AI tools as simple Markdown files within the code repository. This makes information, like research notes, easily renderable in a web UI and directly accessible by AI agents for queries, simplifying development and data management for N-of-1 applications.

Before ending a complex session or hitting a context window limit, instruct your AI to summarize key themes, decisions, and open questions into a "handoff document." This tactic treats each session like a work shift, ensuring you can seamlessly resume progress later without losing valuable accumulated context.

Long-running AI agent conversations degrade in quality as the context window fills. The best engineers combat this with "intentional compaction": they direct the agent to summarize its progress into a clean markdown file, then start a fresh session using that summary as the new, clean input. This is like rebooting the agent's short-term memory.

The `cloud.md` file acts as a project-specific memory and personality for an AI agent like Claude Code. By instructing the agent to save learnings, preferences, and session summaries to this file, you create a self-improving system that gets more effective with each interaction on that project.

Building a comprehensive context library can be daunting. A simple and effective hack is to end each work session by asking the AI, "What did you learn today that we should document?" The AI can then self-generate the necessary context files, iteratively building its own knowledge base.