I think the benefits of this one vastly outweigh the risks since it enables the self-modification Pi (!) became famous for.
you cannot have both and be serious about security
to be clear, I'm talking about hot reload, agent can manipulate its own environment in real time, that's asking for trouble, put some controls on that or reap the consequences from loss of control
It was the big selling point of the harness a couple months ago.
1. agent != harness, Pi is a harness, agents running under Pi can do things, Pi is not the actor or agent
2. self modification vs Pi supports customization / extension / plugin
3. hot-reload (real time modification) vs restart/reload (agent can be blocked)
but "self modification" sounds cooler, I guess
Pi’s whole UI is customizable, so a lot of people were having their agents build their own interfaces.
The distinction is probably irrelevant for most people. I secure the whole thing in a container, because I lack the willpower to audit a bajillion lines of LLM code just inside the harness.
What stops your agent from adding a new MCP server on its own? Would you consider that a gap in security posturing?
It does have native tools, but they're also in plugins that aren't hot-reloaded. The LLM would have to write the tool, you close Pi and re-open it before it was available.
> Would you consider that a gap in security posturing?
Honestly, I think trying to secure the harness is a lost cause for the same reasons SELinux never really took off. They solve a real problem in a way so painful people would rather just live dangerously.
I actually wrote a thing to implement my security posture https://github.com/SethCurry/abyss TLDR it pretends to be an ACP agent, but runs the agent inside Docker (with optional bind mounts) and proxies the ACP connection into the container.
I'm also tinkering with WASM-based plugins in the ACP proxy to add some additional security and compliance posturing at the protocol layer (ie agnostic to what the underlying agent is). E.g. I slapped together a plugin that will automatically cancel a prompt mid-turn if an OpenRouter API token shows up in a) the prompt, b) agent output/thinking, c) agent tool calls. ([1], [2], [3]). The grand vision is slapping centralized management on that so security and compliance teams get a "firewall" of sorts to prevent leaking secrets, filter bash commands, censor PII, yada, yada.
1. Screenshot of it blocking something in Zed https://abyss.scurry.io/docs/guides/what-is-abyss/#i-am-not-... (I need to add buffering so it doesn't output any of the key)
2. Implementation of ^ https://github.com/SethCurry/abyss/blob/main/plugins/secrets...
3. Plugin architecture docs https://abyss.scurry.io/docs/guides/04-plugins/02-developing...
1. I can feel the claudisms coming through, a turnoff for me personally
2. You're shaving yourself short on a good pun
I'll still give it a look since I am in the market for a kubernetes based platform for dealing with lots of agents across harnesses. Scion was my goto, but I'm not so keen on that project anymore.
My ideal solution does not require a running server (CRDs should be sufficient) nor a UI, I want to start new agents in my existing automations.
Also, which lines on the website are the claudiest? I tried to edit out the tone, especially too many one-two punches, but to be honest couldn’t be bothered to write every word myself still
If you want humans to spend time reading and evaluating, put the human time into writing and editing.
I had debated building something like this, and I really want to see what the other fork in the path looks like.
One of the core tenants of mine is to not impose a workflow or set of tooling on the user. I specifically opted not to go with k8s because access to local files is going to be a pain, and I think people will still expect that. There’s all sorts of “I need this binary that’s not in APT”, or “you need this cert to test, and we can’t commit it” stumbling blocks.
Yours feels like it’s pushing me into an unfamiliar workflow, but opinionated tools are often better so it’s worth a try.
My only direct criticism is that I think k8s is a bad way to go for this (but is probably what people expect). For personal use, k8s is more than I want to deal with. For work use, I suspect lambdas would be cheaper and avoid a ton of maintenance junk. We tend to think of agents as a persistent process, but they’re sort of not. They’re a stateless process that is effectively dead until a new message comes in, let it be dead until something else comes down the pipe.
https://pi.dev/docs/latest/mcp
I'm using a number of @gotgene's plugins, they are really nice
I'm looking at porting my Dagger based env to Pi, mainly because it allows me to fork / time-travel the complete environment. One thing I really like about Pi is that /tree command and friends. It aligns really well with how container layer based env can be realized with the Dagger SDK.
Why not? I think DSH does this pretty well with an agent preset that exposes the tools required for the agent to modify the harness.
It's kind of like how the kernel can expose interfaces to allow userspace to load kernel modules at runtime: you "just" have to control which processes can use them.
Between that, and a couple of extra injected bwrap args to make my SSH keys and LLM API credentials unreadable from the agent's shell by default, I'm pretty comfortable using the harness outside of a VM for most things.
If an agent can change the harness it is running in, in real-time, all bets are off
There is semantic ambiguity here. An agent being able to write plugin code for the harness it runs in is related, but orthogonal, to the real-time or not availability of that plugin to the current session.
When I have my agents assist with plugins, I pay closer attention and either do the testing myself or have them run the altered harness in another instance.
Part of this is because they have borked themselves and it can be super annoying to undo their f-ups. Little qwen did this once, breaking its own connection to vllm.
I'm going to distill that from you :]
It was more I let the agent work on my homelab setup and it wrote a bad config value, but I had to actually look at what it had done to figure it out...
There does not seem to be a flag for this, not finding any configuration options yet either, and there is the shared server aspect now too.
Then I upgraded OpenCode to 2.0 and pretty much all the bugs vanished. I still wish there was a happy medium between "parse tool calls for perms" (which fails all the time if the tool call is long/complex enough) and a full-on sandbox, but otherwise 2.0 is really solid.
This is all a stopgap until I have some time to go back to my personal/custom harness.
Cordis also looks interesting as an alternative, but appears more bound to DSH rather than a more general thing (which I prefer).
2. opencode 2.0 does not exists. I mean it: there is no release[1] and per their own instructions, `npm i -g @opencode/cli@latest` does not install opencode 2.0.
3. `Error: @opencode/cli's postinstall script was not run.` Not even running postinstall.js can fix that, neither on linux nor macos. And even if it works, in a couple of days or on the next upgrade it will fail again.
Fun fact: The npm release does not contain the code, it is downloaded by the postinsta script. Galaxy brain.
npm install -g --allow-scripts=@opencode/cli @opencode/cli- several poor security mistakes or choices that broke my trust
- trying to be closer to an IDE, all these harnesses want to be the interface to rule them all, that's not what I want in my harness
- doing things that another tool, which is harness independent, should own (multiple async/parallel agents)
- too much change dropped at once, so many breaking changes, several I cannot migrate at work without impacting the devs I support
I heard it from someone as well, but I cannot find the link or specific details.
Can someone summarise what are the security issues related to using opencode?
Do these issues still exist, especially in V2 ?