can1357/oh-my-pi

⌥ Coding agent with the IDE wired in

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 39 minutes ago
Added to GitGenius on June 5th, 2026
Created on December 31st, 2025
Open Issues & Pull Requests: 2,419 (+2)
GitHub issues: Enabled
Number of forks: 3,040
Total Stargazers: 29,837 (+1)
Total Subscribers: 90 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 0.1 hours
Mean response time: 30.4 hours
90th percentile: 31.4 hours
Tracked items: 4,831

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Almost all tracked open issues have seen activity in the last three months. Only 7% of issues opened in the past year have been closed. Three people close 86% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 1,412
New in 7 days: 322
Closed in 7 days: 117
Avg open age: 6 days
Stale 30+ days: 587
Stale 90+ days: 12

Recent activity

Opened in 7 days: 283
Closed in 7 days: 112
Comments in 7 days: 694
Events in 7 days: 2,105

Top labels

  • triaged (4,100)
  • bug (2,708)
  • prio:p2 (1,691)
  • agent (1,535)
  • tool (1,377)
  • enhancement (1,243)
  • providers (1,187)
  • tui (1,046)

Detailed Description

Oh-my-pi is an AI coding agent for the terminal that integrates language model capabilities with IDE-like functionality through hash-anchored edits, optimized tool execution, and language server protocol support.

The tool addresses the challenge of using AI models effectively for code generation and modification by embedding the IDE directly into the agent's workflow. Rather than treating the model as a black box, it optimizes how tools are invoked and how results are presented back to the model. The agent supports over 60 providers and includes 31 built-in tools alongside 14 language server operations and 28 debug adapter operations. It emphasizes making edits land correctly on the first attempt through benchmarked tool implementations and reads that summarize files rather than dumping full content.

The tool suits developers who want AI-assisted coding in their terminal without leaving the command line, particularly those working with multiple language model providers. It ships complete out of the box with support for macOS, Linux, and Windows, including shell completions that dynamically resolve against the bundled model catalog. The project is built on a substantial Rust core and runs on the Bun runtime.

The project maintains a substantial base of real-world adopters, with almost all open issues raised by outside users rather than the core team. Maintainers typically respond to new issues and pull requests within hours.