can1357/oh-my-pi
⌥ Coding agent with the IDE wired in
About the project
Terminal coding agent with LSP and debugger wired in: 60+ model providers, 31 built-in tools, subagents and collaborative sessions. A fork of Mario Zechner's Pi.
Useful for
- Run the agent to refactor code with LSP-backed renames
- Attach lldb or dlv so the agent diagnoses a segfault or hang
- Fan out a task across subagents in isolated worktrees and get typed results
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 80 stars so far today, about 213 expected by the end of the day.
- Over the last two days the pace is 2× that of the previous week and a half.
- GitHub Trending TypeScript today: #6, +405 stars.
- About 67 forks a day — people are taking the code.
- Recent forks include notable developers: @HACKE-RC (713 followers), @DrB0rk (220 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 32,929
- Today
- 80 · ≈ 213 by evening
- Forks
- 3,484
- Issues and pull requests
- 12,687
- Watchers
- 94
- Language
- TypeScript
- License
- MIT
- Latest release
- v18.2.11 · September 23, 2026
- Created
- December 31, 2025
- Last push
- September 23, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 23, 2026GitHub Trending TypeScript today: #6, +405 stars
Similar by description
-
2.0
charmbracelet/crush
Terminal-based agentic coding tool that wires your tools, code, and workflows into the LLM of your choice. Supports multiple models, sessions, LSP context, and MCP extensions.
-
4.1
earendil-works/pi
A TypeScript AI agent toolkit: a unified API across LLM providers, an agent runtime with tool calling, a TUI library, and an interactive coding agent CLI.
-
0.7
microsoft/intelligent-terminal
An experimental fork of Windows Terminal with native AI agent integration via the Agent Client Protocol (ACP). Lets you chat with an agent right in the terminal, using your shell output as context.