Skip to main content

Timeliner 🌟 - AI's diary. Track AI agent work with markdown log

Project description

Timeliner

Auto-documenting memory layer for AI coding agents. Timeliner logs development sessions as timestamped markdown files, giving perfect recall of past decisions, implementations, and context.

Feature Highlights

  • Zero-friction logging - easy-save work via /save command
  • Markdown storage - Human-readable logs, Obsidian-friendly
  • Integration - Works with Claude Code, RooCode, and other MCP-enabled tools
  • Rich context - Capture outcomes, tags, metadata (PRs, commits, issues)
  • Obsidian vault - Auto-creates .obsidian/ with Minimal theme on install

Use Cases

Software Development:

  • Document decisions and rationale during coding sessions
  • Track refactoring steps
  • Log implementation progress

Research & Learning:

  • Maintain experiment logs with results and insights
  • Learning journal
  • Track hypothesis

Installation

Automatic Setup for Claude Code

Run the installer in your project root:

uvx --from tliner@latest tliner-install

Documents stored in docs/timeline/ by default. Customize via Environment Variables

See details below.

Manual Setup for other MCP Tools

See Manual Installation below.

Quick Start

Using the /save Command

  1. Run /save in your Agent Tool, when you feel you have made significant progress or decisions.
  2. File will be created/updated in your configured TIMELINER_WORK_FOLDER (docs/timeline/ by default).

Using the /report Command

Generate work reports analyzing your Timeline: /report [topic] [time_period]

Examples:

  • /report authentication bug last 48 hours - Find work on authentication in recent files
  • /report yesterday - Generate summary of all work yesterday

The report groups work into distinct approaches, showing implementation attempts, outcomes, and current status.

Using the /load Command

Restore previous work into context. Universal retrieval: /load [topic | task_id ] [time_period]

Examples:

  • /load 20251204T182649.123456Z - Load exact task or step by ID
  • /load last week - Load all work from last week
  • /load auth bug since Monday - Topic + time filter
  • /load - Continues from last saved task (remembers context)

Configuration

Environment Variables

  • TIMELINER_WORK_FOLDER: Storage directory (default: work/docs)
  • add envvar to .claude/settings.json or .claude/settings.local.json :
{ 
  "env": { "TIMELINER_WORK_FOLDER": "info/mydocs"  } 
}

Advanced Usage

CLI Commands

For manual inspection and debugging:

# List all tasks
TIMELINER_WORK_FOLDER="${PWD}/docs/timeline" uvx tliner@latest task-list

# Show all steps for a task
TIMELINER_WORK_FOLDER="${PWD}/docs/timeline" uvx tliner@latest task-show <task_id>

# Run MCP server manually
TIMELINER_WORK_FOLDER="${PWD}/docs/timeline" uvx tliner@latest serve

Archiving Tasks

Got too many tasks cluttering your timeline? Just toss old ones into year-month folders like 2025_09, 2025_10, etc.

Everything still works—searches, retrieval, CLI commands—but now your root stays clean. It's like filing papers in dated folders, except the computer remembers where everything is.

Obsidian Integration

Open your docs/timeline/ folder in Obsidian and browse your AI work sessions like a wiki.

What you get out of the box:

  • .obsidian/ vault auto-created on install
  • Minimal theme pre-configured
  • Style Settings plugin for theme customization

Claude Code Modes

  • Two modes available: plugin and standalone
  • Install script detects Claude CLI:
    • If Claude CLI available → installs as plugin (recommended)
    • If not → falls back to standalone mode

1. Plugin mode (default when Claude detected):

  • Adds sinai-io/ai-plugins marketplace
  • Installs tliner plugin with /tliner:save, /tliner:load, /tliner:report commands

2. Standalone mode (deprecated, force with --standalone or -w):

uvx --from tliner@latest tliner-install --standalone
uvx --from tliner@latest tliner-install -w custom/path
  • Configures .mcp.json directly
  • Creates /save, /load, /report in .claude/commands/
  • Use when you want full control or custom work folder

Manual Installation

Add/create to .mcp.json in the root folder of your project:

{
  "mcpServers": {
    "timeliner": {
      "type": "stdio",
      "command": "uvx",
      "args": ["tliner@latest", "serve"],
      "env": {"TIMELINER_WORK_FOLDER": "${PWD}/docs/timeline"}
    }
  }
}

Copy commands from our repo to .claude/commands/:

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

tliner-0.4.2-py3-none-any.whl (134.7 kB view details)

Uploaded Python 3

File details

Details for the file tliner-0.4.2-py3-none-any.whl.

File metadata

  • Download URL: tliner-0.4.2-py3-none-any.whl
  • Upload date:
  • Size: 134.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.22

File hashes

Hashes for tliner-0.4.2-py3-none-any.whl
Algorithm Hash digest
SHA256 5665cb8521d60ea28538d9112c6c54fba88d6ffab41d3337f195c1e0f533c4e3
MD5 8b611ab8b8b213972eb04b7519637d5b
BLAKE2b-256 df6d8e80864182d1b90c78b800c98ad2a3df013f8f2a5b22c1e367bc672a1616

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page