I dont. I use this as my coding harness (replacement of gemini-cli/claudecode etc). I dont want to sandbox it because I expect it to be used only for coding on projects. I dont want to over complicate it.
I am building my own assistant as an AI harness - that is definitely getting sandboxed to run only as a VM on my Mac.
I use a sandbox example extension with comes with Pi, it uses the anthropic sandbox runtime (bubblewrap on linux). The runtime has one bug and needs one improvement (I've made PRs, no response yet). Pi's sandbox example extension does not block internal tools (read/write) according to rules, I've created a PR but can't submit because of Pi's OSS vacation BS... https://github.com/badlogic/pi-mono/compare/main...k3a:pi-mo... I am quite happy with my patched forks for now
A few things. I intentionally clone the repo and build it locally for my use and use it as my-omp.. this way, I can make oh-my-pi make customisations like skills, tools, anything and yet retain the ability to do a git pull from upstream with cherry picking if necessary.
I have this in my shell rc.
# bun
export BUN_INSTALL="$HOME/.bun"
export PATH="$BUN_INSTALL/bin:$PATH"
alias my-omp= "bun/Users/aravindhsampathkumar/ai_playground/oh-my-pi/packages/coding-agent/src/cli.ts"
and do
1. git pull origin main
2. bun install
3. bun run build:native
every time I pull changes from upstream.
Until yesterday, this process was purely bliss - my own minimal custom system prompt, minimal AGENTS.md, and self curated skills.md. One thing I was wary of switching from pi to oh-my-pi was the use of Rust tools pi-native using NAPI. The last couple of days whatever changes I pulled from upstream is causing the models to get confused about which tool to use and how while editing/patching files. They are getting extremely annoyed - I see 11 iterations of a tool call to edit a damn file and the model then resorted to rewriting the whole file from memory, and we al know how that goes. This may not be a bug in oh-my-pi per se. My guess is that the agent developed its memory based on prior usage of the tools and my updating oh-my-pi brought changes in their usage. It might be okay if I could lose all agent memory and begin again, but I dont want to.
I'm going to be more diligent about pulling upstream changes from now on, and only do when I can afford a full session memory wipe.
Otherwise, the integrations with exa for search, LSP servers on local machine, syntax highlighting, steering prompts, custom tools (using trafilatura to fetch contents of any url as markdown, use calculator instead of making LLM do arithmetic) etc work like a charm. I haven't used the IPython integration nor do I plan to.
self_awareness|5 days ago
reacharavindh|5 days ago
I am building my own assistant as an AI harness - that is definitely getting sandboxed to run only as a VM on my Mac.
neop1x|4 days ago
mr_o47|5 days ago
reacharavindh|5 days ago
I have this in my shell rc.
and do1. git pull origin main
2. bun install
3. bun run build:native
every time I pull changes from upstream.
Until yesterday, this process was purely bliss - my own minimal custom system prompt, minimal AGENTS.md, and self curated skills.md. One thing I was wary of switching from pi to oh-my-pi was the use of Rust tools pi-native using NAPI. The last couple of days whatever changes I pulled from upstream is causing the models to get confused about which tool to use and how while editing/patching files. They are getting extremely annoyed - I see 11 iterations of a tool call to edit a damn file and the model then resorted to rewriting the whole file from memory, and we al know how that goes. This may not be a bug in oh-my-pi per se. My guess is that the agent developed its memory based on prior usage of the tools and my updating oh-my-pi brought changes in their usage. It might be okay if I could lose all agent memory and begin again, but I dont want to.
I'm going to be more diligent about pulling upstream changes from now on, and only do when I can afford a full session memory wipe.
Otherwise, the integrations with exa for search, LSP servers on local machine, syntax highlighting, steering prompts, custom tools (using trafilatura to fetch contents of any url as markdown, use calculator instead of making LLM do arithmetic) etc work like a charm. I haven't used the IPython integration nor do I plan to.