Openclaw - your free open-source AI personal assistant (formerly Clawdbot & Moltbot)
-
@marcusquinn said in Openclawd - your free open-source AI personal assistant (formerly Clawdbot & Moltbot):
Another day, another rename
The title of this thread has openclawd instead of openclaw
@jdaviescoates sorted
-
This thread is inspirational for how to tier your model usage, especially if you're hitting token limits.
https://x.com/code_rams/status/2017684921091772591
-
This thread is inspirational for how to tier your model usage, especially if you're hitting token limits.
https://x.com/code_rams/status/2017684921091772591 -
@robi Sonnet 5 is due out this week, don't think we'll need anything else once that is
@marcusquinn token burn is real, and default config doesn't care.
Hence openrouter's auto route helps
As does this config optimization
OC efficient config - https://x.com/alexxzay/status/2017824548276600914 -
@marcusquinn token burn is real, and default config doesn't care.
Hence openrouter's auto route helps
As does this config optimization
OC efficient config - https://x.com/alexxzay/status/2017824548276600914 -
As an AI practitioner with our own AI server and projects, I was excited about testing this agent as well - until I read this article about ClawDBot Vulnerabilities.
Now I'm thinking about whether I want to explore this, but at least, perhaps I will try it using a machine and digital presence that is separate, apart and isolated from everything that matters! -
As an AI practitioner with our own AI server and projects, I was excited about testing this agent as well - until I read this article about ClawDBot Vulnerabilities.
Now I'm thinking about whether I want to explore this, but at least, perhaps I will try it using a machine and digital presence that is separate, apart and isolated from everything that matters!@crazybrad I have very similar thoughts & cautions.
- packaging it because it looks cool and fun to learn what the fuss is about
- I would NEVER deploy this on a primary working computer like desktop/laptop
- deploying it in a container seems like it could be viable
I have a feeling that Agent Zero is much better than Openclaw, but I can't really say that until I have test Openclaw fairly. So continuing on the package "just in case" it can help me or others.
-
As an AI practitioner with our own AI server and projects, I was excited about testing this agent as well - until I read this article about ClawDBot Vulnerabilities.
Now I'm thinking about whether I want to explore this, but at least, perhaps I will try it using a machine and digital presence that is separate, apart and isolated from everything that matters!@crazybrad no fear, the enchanting experience is key.
-
@timconsidine I think "containerizing" is a great and much safer approach. I would just not use real accounts: email, social, etc. The fact that you are doing this might encourage me to create some test accounts and try it:) @robi Excellent point! "Mirror, mirror on the wall... whose the smartest one of all:)"
-
I was thinking few roles for clawdbot / openclaw / agentzero as a bookeeper who with giving access to irs taxcode and postgress database ask him to be my accountant. Still thinking about it but i have to free few weekends for this. Any thoughts / suggestions?
-
I was thinking few roles for clawdbot / openclaw / agentzero as a bookeeper who with giving access to irs taxcode and postgress database ask him to be my accountant. Still thinking about it but i have to free few weekends for this. Any thoughts / suggestions?
@DualOSWinWiz exactly the kind of thing this is for — go for it!
-
@DualOSWinWiz exactly the kind of thing this is for — go for it!
@marcusquinn but the necessary requirement is to need 2 more bots one bot to audit bookeeper so its kind of more complex and then the 3rd bot as the decision maker so decision should always be 2 to 1. Otherwise it could be a mess. Still thinking
-
@marcusquinn but the necessary requirement is to need 2 more bots one bot to audit bookeeper so its kind of more complex and then the 3rd bot as the decision maker so decision should always be 2 to 1. Otherwise it could be a mess. Still thinking
@DualOSWinWiz sure, you could still do all that on one device.
Might be a useful skill to add into your mix:
-
@DualOSWinWiz sure, you could still do all that on one device.
Might be a useful skill to add into your mix:
@marcusquinn thank you i will
