How to View & Search OpenAI Codex CLI Sessions

When using OpenAI Codex in your terminal, the agent executes complex shell scripts, builds test fixtures, and writes code across multiple directories. Finding past prompt reasoning and tool commands shouldn't require manual file hunting. Here is how to access and search Codex session rollouts across macOS, Linux, and Windows.

Updated September 2026 · By the team behind L2Cache

Where Are Codex Sessions Stored?

OpenAI Codex organizes transcripts in date-based directories under your user home directory:

macOS & Linux:

~/.codex/sessions/YYYY/MM/DD/rollout-*.jsonl

Windows:

%USERPROFILE%\.codex\sessions\YYYY\MM\DD\rollout-*.jsonl

Each session is assigned a unique rollout ID containing the full conversation history, agent actions, tool inputs, and return results formatted in JSON Lines.

Built-in Command: Resuming Codex Sessions

To pick up where you left off in your current or recent coding session:

# Resume recent Codex sessions interactively
codex resume

Limitations of Directory-Based Rollout Files:

• Date Fragmented: Because sessions are partitioned by YYYY/MM/DD, finding a prompt from 3 weeks ago requires recursively searching across multiple nested folders.
• Nested Tool Payloads: Tool executions are stored as JSON strings inside JSON objects, making quick visual scanning difficult in standard text editors.

Parsing Codex Sessions via CLI

You can search across all Codex session files recursively using ripgrep and jq:

# Search all past Codex prompts for a keyword
find ~/.codex/sessions -name "rollout-*.jsonl" -exec jq -r 'select(.type=="USER_INPUT") | .content' {} + | grep -i "docker"

# Find recently executed shell commands
find ~/.codex/sessions -name "rollout-*.jsonl" -exec jq -r 'select(.tool_calls? != null) | .tool_calls[] | .args' {} +

Automated Capture with L2Cache for Mac

Rather than running multi-line shell pipelines to find old prompts, L2Cache for Mac runs natively in your menu bar:

• Automatic Developer Albums: Categorizes AI prompts, Git commands, SQL queries, and code blocks automatically.
• Sub-Millisecond Offline Search: Uses native SQLite FTS5 for lightning-fast retrieval across thousands of entries.
• Private & Encrypted: Keeps all history locally on your Mac with biometric Touch ID lock for sensitive API keys and tokens.