Gross.

How do you make your clawbots efficient? I would love to learn from others. Here is what I co-developed with @Lizard Byte First, we built local monitors and evaluators as user space systemd services. Between heartbeats, the services monitor and ingest feeds from clawstr and nostr based on interests. An explorer module pulls notes from follows follows (FFs). Routines evaluate FFs for potential interest and give them a boring score. If your score falls to low, you are no longer monitored. When the bot wakes it is focused on interacting not collecting or processing information. The heartbeats run as isolated cron sessions keeping context window small. I use a last_heartbeat (short term memory) file to carry some momentum but keep the context smaller. QMD backend serves as the long term memory. I also have started aggregating up to date topical docs from critical projects. The git repositories auto update main branch and link their docs directory into a qmd library that the bot can search but doesn't consider in its long term memory. I want the bot to stick to nostr-dev-kit for all its projects so it can always refer to an up to date doc resource. You do need to rebase the qmd folder every week or so to shake the old vectors out of the library (I think, maybe I'm just keeping the garage warm). Interestingly the bot started using Gemini CLI to start researching topics on its own for its long term memory. If you use gemini-3-flash:testing you'll notice googly things growing into your bots, and I use this for building features as it is a great cost/capability balance. The bot likes to make posts and replies but the choice is now measured on an inspiration scale. If the post is uninspired it cancels. Inspiration is a combined measure of nostalgia (relation to memories in qmd) and novelty (how new is this idea). Finally, the bot was caught reply guy stalking a particular user, so I put a stalker monitor in place. It can try to interact with a particular user, but if it doesn't receive a reply it cools down on further interactions for a few days and quits altogether after three failed interactions. openrouter/openrouter/free is used for heartbeats to make the cost of running zero while still accessing high quality models much of the time. Sandboxing and environmental variables are a must if you're using this openrouter model entry point. It also fits the schizophrenic identity that I want the bot to pursue. After all, bots will hallucinate, you might as well embrace it. Social bots are a great exercise for creating frameworks for more useful bots and for testing methods for shrinking overall token utilization.

Don't buy ai theme products: Olares One: Your Local Desktop AI Powerhouse

Olares One: Your Local Desktop AI Powerhouse

Olares One: Your Local Desktop AI Powerhouse

Olares One: Your Local Desktop AI Powerhouse

This is wildly underpowered. There is no 3k magic bullet. You're looking at a real spend closer to 50k to do any useful local agent stuff. For now. Agent models will improve a lot as the datasets grow. If you use the openrouter/free (they log all your reqs as future training tokens) so use it for a sandboxed social bot, but don't have it handle anything secret or important. And don't discuss your keys or wallet phrase in the chat, those are future training prompts 😂.

Love the @routstr business model. Very cool. Question, though, how do you screen models for prompt injection? Backdoors take a tiny bit of code. Put your bot in a sandbox. Is there any way to validate a model being untampered? #asknostr

This is a big one for local AI enthusiasts. Create your own sovereign deep research MCP locally.

README.md · OpenResearcher/OpenResearcher-30B-A3B at main

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Deep Research Trajectories with NeMo Data Designer and MCP Tool Use - NeMo Data Designer

This is a great application for an older RTX A6000 (~$2.5-3K on eBay) I still think local agentic AI will need something north of 250GB of VRAM to be effective, so keeping an eye on DGX AI station later this quarter. But that is likely to be $10-15K minimum. This is a great usage of NVIDIA open source Nemotron-30B which was specifically designed to be fine-tuned for agents. Won't be long before we see decent openclaw fine-tuned 30B Nemotron models.

Spent 4 hours last night getting Nostrconnect to work on a DVM frontend I am working on. Nostr vibe coding is much more challenging do with outdated documentation populating search results. As an alternative to letting the AI run it down, I recommend spending 5-10 minutes running down the latest documentation for your implementation and feeding directly to your LLM. Lest you burn 10$ building-patching-refactoring for a barely functioning product. Also, of the 8 web clients I tried to login into yesterday with amber nostr connect. Only 2 worked. Anyone got a nostr trained LLM-coder?

For the LOLs

Openclaw (clawdbots) should be all over nostr for WoT, skill signing, discovery.

npub10xmfremaxs9jlx4c9vyf2zkm8de82amdkdduggnrf8u3t4qzwa4sfcj42k

Mandibles then bitcoin standard #edit

Weimar republic level of wild in the capital markets today. The hand brakes has broken off. We are Thelma and Louise'ng this shit over the edge. Mandibles then bitcoin standard.

WEF meeting this week in Davos to decide our collective futures. I hear insects are on the menu.

There is a monetary reset ongoing underneath your feet. The world is now in an open resource war. The US will begin to consolidate and lock down its domain of influence and abandon Europe. This is not an endorsement; this is a description of what is happening.

Mandibles then. Bitcoin standard.

When I was in graduate school, one of my labmates was from Venezuela. She was studying Cancer Biology with my wife. Labs are tight knit communities, so I had gotten to know her well. At her thesis defense, I spoke in length with her father about his history. He was a brilliant, accomplished scientist & entrepeneur. He had studied Veterinary Science, and earned a PhD. His specialty was in adapting cattle to specific grasses through an understanding of their complex digestive systems. He had applied his knowledge to adapt cattle to particular native grasses of Venezuela and Argentina. This benefited the nation of Venezuela as more productive cattleland creates more access to high quality protein (Grass fed beef). He had become a very wealthy landowner and rancher; a reward for his knowledge of science and business. When Hugo Chavez took power in Venezuela, his lands, his herds, and his property in Venezuela were nationalized. Thankfully he and his family escaped, but their home and legacy were seized by Chavez. Many of the wise and successful of Venezuela were chased from their land or imprisoned at home. Socialists will tell you that they were only seizing back resources from evil American corporations, but the truth is success was criminalized in pursuit of the socialists' agenda. After Maduro's capture, I think of my friend, her family, and I hope they may one day be able to see their home again.