omp (oh-my-pi)

“For them/me, omp ( https://omp.sh/ ) is excellent and batteries-included.”

“OMP is too convoluted with features that also resemble an old linux distro”

“I just loved embracing the terminal and being able to switch between providers freely.”

“with omp you can plan with a smart model and then implement with a dumber one”

“significantly reduce the time it takes to prepare internal and public reporting documents”

“The latter landing page has a single sentence that’s generic and vague.”

“GLM5.3 Flash + OMP and DeepSeek Flash as advisor to be able to get jobs done just fine”

“I was mesmerized by the animation in https://omp.sh/ yesterday but this takes it to the next level.”

“omp.sh mimics the Claude Code useragent + payload, so the risks are a lot lower”

“omp offers some nice tools, like /shake, to manage context efficiently and offset some of that consumption.”

“I tried using orchestrate and it drained my wallet… I didn't know about /tan though, that is sick”

“I ended up choosing omp as my daily driver, mostly because I see the velocity of change in AI development being far too fast”

“Aspects of all harnesses are great, but there is always something that bugs me.”

“I personally found the output to be much better without all that”

“if you want strong defaults and batteries included (like omp promises) then that's just annoying”

“I set it up so it never works in the main branch so subagents etc don't step on each others toes”

“its close to the right balance but not quite enough of the brainstorming and spec maintenance built in”

“Using omp helps a lot too, the fact that it uses an LSP under the covers is a game changer.”

“Both of these seem to do a pretty good job of choosing an appropriate model for subagent tasks”

“I am omp pilled, but as the other comments say, any good harness lets you do this”

“Use omp.sh with Task Delegation -> Always to strongly encourage Sol to drive Lunas.”

“With local llms they seem to work well with maximalist harnesses like omp, Hermes etc.”

“I have a web user interface connected to a coding agent (OMP) running inside a container”

“OMP is okay but you really don't need much for a great harness”

“Standard flow with a vision model in OMP is to write the front end code... Works great.”

“The out of box experience of omp.sh is wow imo so much nicer than Claude”

“Does it's own vendoring of tools, so I assume it'd be a pain in the ass to audit”

“I can get way better outcomes, and an order of magnitude less cost with my slapped together sandboxed omp setup”

“Pi and Omp are optimized for a wide variety of models, including open weights”

“Spawning subagents via orchestrate and using /advisor are both super valuable.”

“Using OMP through ACP inside Zed is drastically worse experience than just running OMP inside Zed terminal”

“it gave me many issues that it was easier just to use the terminal directly”

“I like OMP because I don't have to spend time figuring out the next best thing”

“OMP is great to get started with, there's a whole bunch of stuff in there but it's mostly optional”

“The good thing is the main model is confident - checks and then it stands its ground.”

“if the website is any indication, omp is just vibe coded AI slop as well”

“it loves to use subagents, and it's basically unusable subagents with GPT 5.6 Sol there with Plus limits”

“omp.sh is unreadable. I've tried understanding what exactly this is and it's just a wall of edgy sounding slop.”

“Then I figured out I should try OMP (Pi), and the experience was much better.”

“I've been using omp with deepseek as my task and quicktask agents”