Tracking Claude Code & Codex Sessions: How 인공지능(AI) Agent History & Token Analytics Supercharge macOS Development

Software engineering workflows have undergone a massive shift. Developers no longer rely solely on basic autocomplete; today, we pair with autonomous CLI coding agents like Claude Code and Codex to execute multi-turn refactors, write unit tests, and resolve complex edge-case bugs across full repositories.

However, as engineers run dozens of agent tasks daily across different terminals and projects, managing 인공지능(AI) agent context has become a major productivity bottleneck.

Figure 1: L2Cache floating panel surfacing Claude Code & Codex session summaries, token consumption, prompt cache hit ratios, and 1-click terminal resumption.

1. Unified Session Capture & Token Analytics

In L2Cache 1.4, we introduced native 인공지능(AI) Agent History & Analytics—bringing full visibility to your CLI agent sessions directly from your Mac's menu bar or global hotkey (⌥Space).

L2Cache automatically parses and indexes local agent logs in real time, giving developers zero-cloud access to critical session metrics:

2. 1-Click Terminal Session Replay & Resume

One of the most frustrating parts of using CLI agents is resuming a session after switching terminals or closing a window. Previously, developers had to manually locate session UUIDs or inspect raw logs to run CLI commands:

# Manual session resumption in CLI
claude --resume a85fd1e8-3b4a-4f12-89cd-7e62a104f982
codex resume session_2026_09_08_build

With L2Cache, session resumption is seamless:

• Inspect any past session in the L2Cache floating panel to see full turn-by-turn prompts, tool executions, and file edits.
• Click "Resume in Terminal" to launch a fresh terminal window automatically attached to the selected agent session.
• Never lose your place or re-explain context when returning to a complex multi-hour debugging session.

3. Repository Knowledge Graph: Preventing Agent Memory Rot

When an agent spends 20 turns debugging a subtle AppKit threading bug, a SQLite concurrency issue, or a custom build flag constraint, it learns vital facts about your codebase. But when that session finishes, those insights often stay buried in local log archives.

L2Cache's Repository Knowledge Graph bridge converts transient agent discoveries into permanent repository documentation:

Figure 2: L2Cache Repository Knowledge Graph surfacing discovered gotchas, fragile components, and 1-click promotion to AGENTS.md.

# Example AGENTS.md rule promoted from agent session #a85fd1e8
## AppKit & SwiftUI Concurrency Rules
- guard `view.window != nil` before displaying popovers in async tasks to prevent EXC_BAD_ACCESS.
- Never perform DB reads/writes on the main thread; use `Task` with `await`.

1. Extract Discovered Gotchas: L2Cache parses agent execution logs to surface fragile components, recurring error tracebacks, and technical debt notes.
2. 1-Click Promotion to AGENTS.md: Review extracted constraints and click "Promote to AGENTS.md" to write the rule directly into your project's root AGENTS.md or CLAUDE.md file.
3. Cross-Agent Alignment: Ensure all coding agents (Claude, Codex, Antigravity, or Cursor) share the exact same rules, preventing agents from repeating known bugs in future sessions.

4. 100% Local, Zero-Cloud Privacy

Just like L2Cache's core clipboard management, all Agent History & Analytics parsing occurs strictly on-device on your Mac. L2Cache reads local session logs directly from your home directory, stores analytics in local SQLite databases using GRDB, and never sends your prompts, code snippets, or token statistics to external servers.