OpenClaw! What is your opinion on this and others like it?

You can actually do things also with the other AIs, but what if they hallucinate or decide to disobey?
tomshardware.com/tech-industry/artificial-in…e-goes-rogue

Privacy : Venice ai doing good work Venice End-to-End Encrypted AI, don't give or share any sensitive information of any kind.

Memory : GitHub is full of academic and tech essays to fix it.
OpenViking: The Context Database for AI Agents
by Volcengine (ByteDance's cloud platform)
GitHub repo. GitHub - volcengine/OpenViking: OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

Security : Sandboxing actually helps but there is no fully protected system at all.

Budget : like kimi 2.6 is showing good results. Or OpenRouter. Etc..

I have to mention one tweet : I tracked 430 hours of Claude Code usage. 73% was wasted on these 9 patterns.

View on X

Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

Link one. Hermes Agent | OpenRouter

Link two. Hermes Agent — The Agent That Grows With You

By NOUS RESEARCH

Introducing Response Caching: save tons of money and time on tests and agent retries.

openrouter.ai/announcements/response-caching

I prefer Hermes Agent over OpenClaw.

Rather not cheap out and just run GPT 5.5 Medium/High. If you want to save, run OpenClaw with OAuth into the $200 Codex sub.

jafo said:

See.... this is what I was afraid of without actually knowing about this specific danger. I'm afraid that f*cker will call the feds or turn me into the tax authorities. Tomorrow, it can, based on any of my citizenship, report my income to the respective mafia of the parasitic country issuing a slab of paper they label as "passport", or just send my clients all my price list and vendor contacts.

As you know, they are regularly subpoenaing all LLMs, so the next logical step is “preventive” sharing of personal information with LE.

jafo said:

This worries me, so is there a way to contain this f*cker?

Run it locally?

Just running a model locally does not necessarily mean it cannot reach out to third parties or delete things en masse. Best thing imo is to keep it set so that when it wants to run a command it asks for it to be accepted, and that file writes in the working directory can be edited as it pleases (this way it is less likely to go rogue and outside of the folder, as the only way I can imagine it could break out is by writing a script in the folder and then running it, which then needs your permission).

jafo said:

Thank you! This is really helpful!

Update.

nym.com/blog/nym-private-agent-access

jafo said:

Yes, this is what I am trying to do here now. I'm +50% into it already. Here, I can, because I can train/metro around with a few computers, laptops, and smartphones and nobody bats an eye, but what will I do when I travel overseas? 🙄

If I arrive in the EU with +2 laptops and 8 phones, I think I'm f*cked! 🤦:banghead::banghead::banghead:

Two of these sharks is good to start playing locally with ai but with the Max spec (crazy RAMs and GPUs) :

store.minisforum.com/products/minisforum-ms-…5031345397#1

jafo said:

Thank you! I can have that made here at The World's BIGGEST Electronics Market | Huaqiangbei Shenzhen, China for a fraction of the price. Thank you very much for that link.

PS. At Uni, the students are young (I'm NOT) so they don't know much and the computers we use at Uni are powerful, but the AI & Robotics we do there is for school work. I can't start doing my "COSA NOSTRA" there 🤣 🤣 - That's akin to being invited to someone's house and go take a nap in their master bedroom 🤣:ROFLMAO::ROFLMAO: - I'm NOT Chinese, so I try to behave BETTER than the Chinese, so I don't have to find myself deported. 😭

First of all I have to say LOL 🤣
There is no OUR THING Work in public computers and are not secure at all. 😂
The problem here isn't the price, the quality of Rams and GPUs the rest can be rebuilt in Shenzhen as you said of course.

I keep sharing a new out of the box ideas.
Cheers.

jafo said:

Yes, thank you! And also "yes"...there is an abundant supply of "treasonous" Americans (and other Westerners) who will sell anything for an extra buck to the Chinese...with sanctions and without sanctions. NVIDIA chips? No problem....they are all over Shenzhen. Now, the Chinese are warming up to me because I was on the news of how the Empire tried to bury me because I refused to make up stories about Lei Jin or testify against him. Lei Jin - Genescience 🤣 🤣 🤣

So I think I have to build a mini data center in China for research and development 😅

God bless you man.

View on X

Always prepare and scan :

GitHub - PrismorSec/immunity-agent: Security for AI agents : Block dangerous commands, prevent secret leaks, and enforce runtime policies across Claude, OpenClaw, Hermes, Antigravity, Codex, Cursor and Windsurf - - by Prismor - Security and Compliance Autopilot for your code

GitHub - protectai/modelscan: Protection against Model Serialization Attacks - - by Protect AI | The Platform for AI Security

Update :

Memory layer by Plastic Labs, amazing work

MEMORY That REASONS Honcho

MEMORY BENCHMARKS Honcho Memory Benchmarks

Website. Plastic Labs
GitHub. Plastic Labs

Hermes. Autonomous agent with built-in Honcho memory. Honcho Memory | Hermes Agent

They also have:

NEUROMANCER is the first collection of models dedicated to AI-native memory and social cognition. They're trained specifically to do formal logical reasoning over user and agent data to form representations of any entity's personal identity.

Project. Neuromancer - Plastic Labs