loweryaustin/YAITracker
AI-native issue tracker with MCP integration, human/agent time tracking, and velocity analytics. A self-hosted alternative to Jira and Linear for developers who work alongside AI agents.
Platform-specific configuration:
{
"mcpServers": {
"YAITracker": {
"command": "npx",
"args": [
"-y",
"YAITracker"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Your Automated Intelligence Tracker (or *Yet Another Issue Tracker*, depending on how many grey hairs you have).
A self-hosted, AI-native issue tracker with built-in MCP integration, human/agent time tracking, and velocity analytics. An alternative to Jira and Linear for developers who work alongside AI agents.
> Alpha Software -- YAITracker is under active development. Features are missing, some things are broken, and the API will change. I'm dogfooding this project as I build it -- logging issues and tracking time from day one, then using what I find to improve it as I go. Send me your feedback about what you want to see in this project, your own AI workflows, or anything else that you think would be useful.
Traditional issue trackers were built for a world where humans write all the code. AI coding tools like Cursor, Copilot, and Claude have fundamentally changed development velocity, but project management hasn't caught up. When AI agents can produce code in minutes, the old assumptions about estimation, sprint planning, and time tracking fall apart.
The most effective developers in the AI age aren't just using one agent -- they're orchestrating multiple agents in parallel, sometimes across multiple projects at once. One person's hour of productivity can look radically different from another's depending on how well they manage that orchestration. The right tooling makes that difference easier to see, measure, and act on.
YAITracker is built around these ideas:
Loading reviews...