Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Moltis – AI assistant with memory, tools, and self-extending skills

moltis.org

Post reply on HN
Print view View original

51–60 of 60 posts

Re: Show HN: Moltis – AI assistant with memory, tools, and self-extending skills

#51

Post by fabienpenso »

afro88 wrote: post #29
zimbatm wrote: post #20

Isn't the point of OpenClaw that the agent can modify itself?

This is what I'm interested in knowing. Just how much can it modify if it's a static binary? Can it modify it's own agents.md etc?

It can modify everything, because while it's a single binary and that makes it easy for installation, there are things stored outside that binary. The memories, the skills, the config etc. But you can do everything from the UI and you don't need to bother, it will be all automatic.

Re: Show HN: Moltis – AI assistant with memory, tools, and self-extending skills

#53

Post by eibrahim »

the self-extending skills part is really interesting. ive been building AI agents with persistent memory for a while now and the skill/tool extensibility piece is where most frameworks fall short. they either give you a rigid plugin system or completley open-ended function calling with no guardrails.

how are you handling the trust boundary for self-created skills? thats usually where things get tricky.

also curious about the memory architecture. file-based memory (like markdown files the agent reads/writes) has been surprisingly effective in my experience compared to fancy vector DB approaches. simpler to debug, easier for the agent to reason about, and way less infrastructure overhead. whats your approach?

Re: Show HN: Moltis – AI assistant with memory, tools, and self-extending skills

#54

Post by atmosx »

LaurensBER wrote: post #8

Very cool! I love the approach, OpenClaw is really cool but there's two major things holding me back for deploying it from friends a family; - Cybersecurity (you can't expect a non-technical person to read a skill) - Token usage (without a flat fee subscription it'll become expensive very fast) I understand that security is a hard problem to solve but having a single binary + containers should definitely help! I'll d…

Yeap. Cost is a major problem with these agents. I wonder why MistralAI is never natively supported. It’s the cheapest paid option out there.

ps. One can use mistral’s API through liteLLM.

Re: Show HN: Moltis – AI assistant with memory, tools, and self-extending skills

#56

Post by yencabulator »

eibrahim wrote: post #53

the self-extending skills part is really interesting. ive been building AI agents with persistent memory for a while now and the skill/tool extensibility piece is where most frameworks fall short. they either give you a rigid plugin system or completley open-ended function calling with no guardrails. how are you handling the trust boundary for self-created skills? thats usually where things get tricky. also curious a…

> how are you handling the trust boundary for self-created skills?

At least in the Claude model, there's nothing a skill can do that the model couldn't already do? Isn't it still the same tool calls underneath, with the same permissions?

Think of skills as plugins providing AGENTS.md snippets and a subdirectory of executables, as if those were part of the workspace to begin with.

Re: Show HN: Moltis – AI assistant with memory, tools, and self-extending skills

#57

Post by yencabulator »

sathish316 wrote: post #33
LaurensBER wrote: post #8

Very cool! I love the approach, OpenClaw is really cool but there's two major things holding me back for deploying it from friends a family; - Cybersecurity (you can't expect a non-technical person to read a skill) - Token usage (without a flat fee subscription it'll become expensive very fast) I understand that security is a hard problem to solve but having a single binary + containers should definitely help! I'll d…

Don’t install skills in OpenClaw or Moltis for security reasons. Self-extension or self-evolving nature means that you can customise it to create your own skills

Sure but also don't let it consume any content you didn't write or don't give it write access to anything outside its sandbox[1]. Prompt injection is a thing, and all this molt stuff is yolo for life on all things you give it access to.

https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

[1]: And even then, if you allow it to make web fetches, it can smuggle your private data out.

Re: Show HN: Moltis – AI assistant with memory, tools, and self-extending skills

#60

Post by P2Chill »

fabienpenso wrote: post #52
twostorytower wrote: post #31

Is it compatible with OpenClaw Plugins?

Yes. The UI allows you to add repositories (OpenClaw is one listed), and you can enable/disable any of them.

Thanks for making this! It's a great application, and in stark contrast with the 'competitors', everything is so polished and it's not full of half baked features. That's a huge plus in my book. More features =/= better if the core isn't solid. I love how right moltis gets this.

I've really been enjoying it. Heavily added onto my fork already. Not at all because it wasn't good already, exactly because it is so it's worth building on top of!

I tried fixing bugs in some alternatives but there were just so many and it felt like a losing battle.

I'll definitely be submitting some (more) PRs in the future. I've pushed one upstream so far for review, but I have a lot more ready to submit later on.

Again, thank you so much for making this! Stellar work!

Post reply on HN