# oh-my-pi Hacker Approved page: https://hackerapproved.com/p/oh-my-pi/ 137 people recommended oh-my-pi in Hacker News comments, 23 had mixed feelings and 46 criticized it, November 2025 to October 2026. It was recommended in 9 of 12 months, in 142 threads. It meets the Hacker Approved badge rule. **Verdict:** A batteries-included fork of the Pi coding harness with sensible defaults, easy provider switching and built-in search and context tools, though critics find it bloated and token-hungry. Summary written by Claude from 57 comments. Claude agents reviewed it against the quotes on 2 Nov 2026. ## Why people recommend it - Batteries included, sensible defaults (7 comments in the sample): "it has the stability of Pi with the features Opencode (and more I think; OMP has web browsing and a more advanced edit system too" ([source](https://news.ycombinator.com/item?id=48978846)) "I think omp.sh (oh-my-pi) is the best by a comfortable margin and its completely batteries included." ([source](https://news.ycombinator.com/item?id=50287459)) "Checks all of the boxes I want and is the most consistent set of AI tools I've used thus far." ([source](https://news.ycombinator.com/item?id=49926400)) - Easy switching between models, providers (4 comments in the sample): "Oh-my-py unlocks max capabilities at the smartest token usage, and you can change AI company and providers while still getting things done." ([source](https://news.ycombinator.com/item?id=49766401)) "really glad to see that in omp (oh-my-pi) Zai is a 1st class provider, can be selected on it's own no configs shananigans needed" ([source](https://news.ycombinator.com/item?id=49296466)) "Lately I use Zai in omp (oh-my-pi). It's listed built-in provider can be selected without configs shenanigans." ([source](https://news.ycombinator.com/item?id=49296666)) - Strong context and memory management (4 comments in the sample): "You can also use "/btw" to have side tangent conversations with the current context but with the benefit that it will not bloat your current…" ([source](https://news.ycombinator.com/item?id=49294360)) "I realized oh-my-pi was doing the same things I've been doing, including advisor, native server-side compaction, etc. It's a really good harness." ([source](https://news.ycombinator.com/item?id=49680440)) "it automated out-of-the-box a pattern I naturally would do of writing a spec just before the context window would fill" ([source](https://news.ycombinator.com/item?id=49926847)) - Built-in web search (2 comments in the sample): "will scrape search results for you out of the box, no api key or search provider needed" ([source](https://news.ycombinator.com/item?id=50139399)) "I really like it, especially how it can easily get search from Codex/Gemini/etc." ([source](https://news.ycombinator.com/item?id=49000430)) ## What people warn about - Bloated, huge codebase (5 comments in the sample): "Downloading 200k+ lines of additional code seems completely against the philosophy of building up your harness" ([source](https://news.ycombinator.com/item?id=47150082)) "Checked out Pi and Oh-My-Pi. 250k LoC and 1.5M LoC respectively. Sheesh. How's that for minimalism..." ([source](https://news.ycombinator.com/item?id=49368928)) "Too heavy handed and opinionated, not interested in the "agent team" setup" ([source](https://news.ycombinator.com/item?id=50142967)) - Uses more tokens than Pi (2 comments in the sample): "This harness also burns a lot more tokens than Pi, which sort of kills the minimal philosophy/system prompt that Pi came from." ([source](https://news.ycombinator.com/item?id=49926482)) "not the opinionated omp setup I have that probably makes the initial context larger than it should be" ([source](https://news.ycombinator.com/item?id=49763228)) - Crashes with some models (2 comments in the sample): "For some reason the 35B A3B model had issues with Oh My Pi's ability to pass a thinking parameter which caused it to crash" ([source](https://news.ycombinator.com/item?id=47295445)) "it wont event execute because omp sends multiple system prompts" ([source](https://news.ycombinator.com/item?id=48049454)) - Frequent updates can break things (2 comments in the sample): "The last couple of days whatever changes I pulled from upstream is causing the models to get confused" ([source](https://news.ycombinator.com/item?id=47150393)) "It updates very frequently so as a safe guard I run it sandboxed with" ([source](https://news.ycombinator.com/item?id=48666780)) ## Other coding agents people recommend - [Claude Code](https://hackerapproved.com/p/claude-code/): 2558 recommend, 960 mixed, 3101 criticize - [OpenAI Codex](https://hackerapproved.com/p/codex/): 1670 recommend, 449 mixed, 995 criticize - [OpenCode](https://hackerapproved.com/p/opencode/): 760 recommend, 177 mixed, 484 criticize - [Pi coding agent](https://hackerapproved.com/p/pi/): 707 recommend, 124 mixed, 159 criticize ## The badge A product earns the Hacker Approved badge when at least 10 people recommend it, recommenders outnumber critics at least 2 to 1 (mixed feelings count toward neither side), it was recommended in at least 4 of the 12 months and in at least 5 different threads, and no single thread supplies more than half of the people who recommend it. Health and money products are never badged. ## Cite as Hacker Approved, "oh-my-pi", https://hackerapproved.com/p/oh-my-pi/ (137 recommend, 23 mixed, 46 criticize; Hacker News comments, November 2025 to October 2026). Counts updated 2 Nov 2026, with data through October 31, 2026.