agentlog 0.1.2

CLI flight recorder for AI coding agents - capture, store, and replay AI sessions
Documentation

AgentLog

CLI flight recorder for AI coding agents. Capture every file change, command, and diff as a replayable timeline.

Installation

cargo install agentlog

Or download pre-built binaries from GitHub Releases.

Quick Start

# Initialize in your project
cd your-project
agentlog init

# Run an AI agent with capture
agentlog run claude

# Review what changed
agentlog timeline
agentlog replay <session-id>

Commands

agentlog init

Initialize AgentLog in the current directory. Creates .agentlog/ directory with SQLite database and config.

agentlog run <agent>

Run an AI agent with full session capture. File changes are monitored in real-time.

agentlog run claude
agentlog run cursor
agentlog run ./my-script.sh

agentlog search

Search and filter sessions by date, agent, or files touched. Perfect for finding context when debugging issues.

# Find sessions from last 2 weeks
agentlog search --since "2 weeks ago"

# Find Claude sessions that touched auth files
agentlog search --agent claude --file "auth/"

# Find sessions from specific date range
agentlog search --since "2024-03-01" --until "2024-03-15"

# Find sessions affecting specific file
agentlog search --file "src/components/Login.tsx"

agentlog timeline

Display all captured sessions with duration, files changed, and line statistics.

agentlog replay <session-id>

Replay a specific session step-by-step. Shows each file change with timestamps and diffs.

agentlog replay abc123de

agentlog blame <path>

Show which AI session last modified each line of a file.

agentlog blame src/main.rs

agentlog status

Check AgentLog status and health for the current project.

agentlog export

Export events to JSONL format for sharing or backup.

agentlog export --format jsonl --output events.jsonl

agentlog watch

Start background file watcher without wrapping an agent. Useful for monitoring manual edits.

agentlog policy

Manage security policies to block or warn on sensitive file modifications.

agentlog policy list                    # Show all rules
agentlog policy check .env              # Test if file violates policy
agentlog policy add --name "api-keys" --pattern "**/api-keys.*" --action block
agentlog policy remove api-keys
agentlog policy toggle false            # Disable enforcement

Workflow Example

Scenario: QA reports a bug in the auth feature from 2 weeks ago.

# 1. Find sessions from last 2 weeks that touched auth files
agentlog search --since "2 weeks ago" --file "auth/"

# 2. Found session abc123de - view full details
agentlog replay abc123de

# 3. Export context for sharing with team
agentlog export --output auth_bug_context.jsonl

Policy Enforcement

AgentLog includes built-in policies to protect sensitive files:

Pattern Action
.env* Block
auth/**/* Block
*.key, *.pem Block
*.tfstate* Block
migrations/**/* Require confirmation

Storage

Events are stored locally in .agentlog/events.db as a SQLite database:

  • Fast queries: Indexed for O(log n) lookups
  • Scalable: Handles millions of events efficiently
  • Local only: No cloud, no external dependencies
  • Exportable: Export to JSONL anytime with agentlog export
  • Git-friendly: Add .agentlog/ to .gitignore

Direct SQL Access

Advanced users can query the database directly:

sqlite3 .agentlog/events.db "SELECT * FROM events WHERE event_type = 'file_change' LIMIT 10"

Requirements

  • Rust 1.93+
  • Linux, macOS, or Windows

License

MIT