oh-my-pi
Hacker ApprovedRanked 2 of 41 coding agents by recommenders
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.
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.
132 people gave an opinion
- recommend it
- 104
- criticize it
- 28
- approval share
- 79%
Recommended in 9 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Owned for 2 months
Median of the 5 owners who said how long they have had it.
Each square is one year.
Why it carries the badge
- 104 people recommend itNeeds 10 or more, met.
- 3.7 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 9 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Batteries included, sensible defaults
“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)”
Comment from 20 Jul 2026 in “Stop Using OpenCode” “I think omp.sh (oh-my-pi) is the best by a comfortable margin and its completely batteries included.”
Comment from 29 Oct 2026 in “Claude Code regularly sends each background agent’s transcript to its model” “Checks all of the boxes I want and is the most consistent set of AI tools I've used thus far.”
Comment from 1 Oct 2026 in “Pi 1.0” - Comment from 13 Jun 2026 in “Kimi K2.7-Code: open-source coding model with better token efficiency”
- Comment from 6 Aug 2026 in “Qwen3.8 Max now ranked as the best overall model by agentic index”
- Comment from 2 Oct 2026 in “Pi 1.0”
- Comment from 31 Jul 2026 in “DeepSeek-V4-Flash Update”
- Comment from 29 Jun 2026 in “Semgrep: GLM 5.2 beats Claude in our Cyber Benchmarks”
Easy switching between models, providers
“Oh-my-py unlocks max capabilities at the smartest token usage, and you can change AI company and providers while still getting things done.”
Comment from 19 Sep 2026 in “Claude Code now reads AGENTS.md if there is no Claude.md” “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”
Comment from 14 Aug 2026 in “GLM-5.3: Frontier Coding with Emergent Cyber Capabilities” “Lately I use Zai in omp (oh-my-pi). It's listed built-in provider can be selected without configs shenanigans.”
Comment from 14 Aug 2026 in “GLM-5.3: Frontier Coding with Emergent Cyber Capabilities” - Comment from 28 Oct 2026 in “The Agent SDK”
Strong context and memory management
“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 context after the tangent is done.”
Comment from 14 Aug 2026 in “How Compaction Works in Pi” “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.”
Comment from 13 Sep 2026 in “Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases” “it automated out-of-the-box a pattern I naturally would do of writing a spec just before the context window would fill”
Comment from 1 Oct 2026 in “Pi 1.0” - Comment from 28 Oct 2026 in “The Agent SDK”
Built-in web search
“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)”
Comment from 20 Jul 2026 in “Stop Using OpenCode” “will scrape search results for you out of the box, no api key or search provider needed”
Comment from 18 Oct 2026 in “DeepSeek search and fetch – $0.75 per 1000 successful requests” “I really like it, especially how it can easily get search from Codex/Gemini/etc.”
Comment from 22 Jul 2026 in “Oh-my-pi: A coding agent with the IDE wired in”
What people warn about
Each mark is one comment
Bloated, huge codebase
“Downloading 200k+ lines of additional code seems completely against the philosophy of building up your harness”
Comment from 25 Feb 2026 in “Pi – a minimal terminal coding harness” “Checked out Pi and Oh-My-Pi. 250k LoC and 1.5M LoC respectively. Sheesh. How's that for minimalism...”
Comment from 20 Aug 2026 in “Anthropic Refuses to Support Agents.md” “Too heavy handed and opinionated, not interested in the "agent team" setup”
Comment from 18 Oct 2026 in “OpenCode has a security breach last that impacted 1.4% of console users” - Comment from 29 Apr 2026 in “Claude.ai Is Unavailable”
- Comment from 6 Aug 2026 in “DeepSeek planning to significantly raise prices”
Uses more tokens than Pi
“This harness also burns a lot more tokens than Pi, which sort of kills the minimal philosophy/system prompt that Pi came from.”
Comment from 1 Oct 2026 in “Pi 1.0” “not the opinionated omp setup I have that probably makes the initial context larger than it should be”
Comment from 19 Sep 2026 in “Claude Code now reads AGENTS.md if there is no Claude.md” “omp used quite a bit more tokens than my fairly basic pi setup”
Comment from 29 Sep 2026 in “GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price” Crashes with some models
“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”
Comment from 8 Mar 2026 in “How to run Qwen 3.5 locally” “it wont event execute because omp sends multiple system prompts”
Comment from 7 May 2026 in “ZAYA1-8B: An 8B Moe Model with 760M Active Params Matching DeepSeek-R1 on Math” Frequent updates can break things
“The last couple of days whatever changes I pulled from upstream is causing the models to get confused”
Comment from 25 Feb 2026 in “Pi – a minimal terminal coding harness” “It updates very frequently so as a safe guard I run it sandboxed with”
Comment from 24 Jun 2026 in “GLM-5.2 is the step change for open agents”
Other coding agents people recommend
The four most recommended other coding agents, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| GitHub Copilot | 571 | 993 | 37% | 12 | 1 yr46 owners | — |
| oh-my-piThis page | 104 | 28 | 79% | 9 | 2 mo5 owners | Approved |
| Grok Build CLI | 66 | 114 | 37% | 6 | — | — |
| DeepSeek Harness | 63 | 28 | 69% | 4 | 1 mo5 owners | Approved |
| Claude Code VS Code extension | 31 | 43 | 42% | 11 | — | — |
What people said
40 of the 175 comments that mention it, newest first. Each links to the original comment.
“I think omp.sh (oh-my-pi) is the best by a comfortable margin and its completely batteries included.”
“Being able to quickly to switch between models without changing your workflow is such a joy”
“it has very good memory and context management tools that ship with it and are extremely easy to set up.”
“I believe oh-my-pi will be able to ingest your Claude and codex conversations, count tokens, and then assign API-equivalent rates to them.”
“I've been using it without thinking much about it for 3 months now. Have yet to run into any bugs or strange behaviors.”
“Too heavy handed and opinionated, not interested in the "agent team" setup”
“will scrape search results for you out of the box, no api key or search provider needed”
“if you do software development with a harness such as oh-my-pi, your cache rates are probably somewhere above 98%”
“comes preloaded with most stuff you need, so there's not much need to add extensions”
“it automated out-of-the-box a pattern I naturally would do of writing a spec just before the context window would fill”
“This harness also burns a lot more tokens than Pi, which sort of kills the minimal philosophy/system prompt that Pi came from.”
“Checks all of the boxes I want and is the most consistent set of AI tools I've used thus far.”
“Oh-my-pi shows that these checks aren't really necessary for harness safety, it's best to invest in harness predictability.”
“omp used quite a bit more tokens than my fairly basic pi setup”
“I've never seen omp touch a file outside of the directory I start it up in, and the few times where I've been unhappy with a change git has been there to revert.”
“Oh-my-py unlocks max capabilities at the smartest token usage, and you can change AI company and providers while still getting things done.”
“not the opinionated omp setup I have that probably makes the initial context larger than it should be”
“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.”
“I like it a bit for the inspiration what could make sense, however, as there is little ablation studies”
“Checked out Pi and Oh-My-Pi. 250k LoC and 1.5M LoC respectively. Sheesh. How's that for minimalism...”
“Lately I use Zai in omp (oh-my-pi). It's listed built-in provider can be selected without configs shenanigans.”
“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”
“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 context after the tangent is done.”
“OpenCode or oh-my-pi might make more sense if you just want a batteries-included agent”
“advanced (but little bloated, yes) harnesses have good enough defaults”
“Lots of sensible defaults and good tweaks/settings you just don't worry about.”
“Oh-my-pi recommends installing via bun and I give it points there for not promoting this absolute rubbish.”
“I really like it, especially how it can easily get search from Codex/Gemini/etc.”
“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)”
“Without that enhancements it's almost useless, missing all the file edits, git amend or fixup strategies, or github api calls.”
“You can set up rules that watch output, and when the ai does something you don't want, they immediately fire and interrupt it”
“oh-my-pi has all the nice things included that I've built for pi previously”
“It updates very frequently so as a safe guard I run it sandboxed with”
“more feature packed, well put together, and gives me better results with some steering”
“it wont event execute because omp sends multiple system prompts”
“That (and oh-my-pi) seem like an excessive swing in the other direction.”
“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”
“The last couple of days whatever changes I pulled from upstream is causing the models to get confused”
“Downloading 200k+ lines of additional code seems completely against the philosophy of building up your harness”
“This looks great but It feels really risky to add more and more tools to the harness from random repos.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.