@iceman00008 @vultisig Very very cool… just another breakthrough like this for the vault share management and it becomes the absolute best wallet out there.
English
RSGB / ⚡️
1.3K posts
@RaymondMontreal @vultisig where did you see that thorguards take you from gold to platinum?
English
I just learned about holding #Thorguards in @Vultisig
0.06 ETH or $110 takes you from gold to platinum tier
Swap 0.15 Bitcoins in wallet and the NFT pays for itself, or... buy 7500 more $VULT at $0.24 = $1800
Have people not done this math yet? opensea.io/collection/tho…
English
RSGB / ⚡️ retweetledi
Update on the $10/month AI bot experiment -
reality hit hard!
Here is how it went down.
I'm running a multi-agent setup:
- Chiti (coordinator)
- Vasi (dev)
- Sana (marketing)
- Nila (content)
- Boran (finance)
Yesterday Sana did SEO research for @TweetsMashApp marketing and updated in Notion.
Everything smooth. Beautiful.
Then I asked Chiti to automate invoices for monthly taxes.
BOOM.
Continuous "Context overflow" issue. All agents crashed. Massive blackout.
Gemini CLI OAuth? Soft-banned within hours.
OpenAI Codex OAuth? Soft-ban Jail.
Free models? "Model not allowed" errors.
The fallback wasn't switching automatically.
Had to manually dig into config.json and debug.
Switched to openrouter/moonshotai/kimi-k2.5.
Bot's alive again but experiencing latency issues.
Current status:
- OpenRouter credit: $5.63 left of $10
- Total spent debugging: ~$4
- Primary model: kimi-k2.5 (working but slow)
- OAuth: disabled for now (soft-ban risk)
The hard truth from @ImNotTheWolf - "It can't be cracked cheaply yet. Clawdbot basically NEEDS Opus 4.5 or GPT-5.2-Codex for reliability. Need to wait for another 6 months to make it less cost".
But I'm not giving up. Let me try fixing the context management first.
Chiti coordinating 5 subagents = context exploding to 50K+ tokens.
OAuth won't save you if your agents keep bloating the context window.
What I'm trying next:
1. Qdrant vector memory - externalize context so prompts stay small, bot queries on-demand instead of carrying 50K+ tokens (h/t @mej26vPIJx22495 for this suggestion in Tamil 🙏)
2. QMD local search - lightweight on-device doc search to reduce API calls
3. Heartbeat + Auto-Doctor - batch non-urgent tasks, monitor context size, auto-restart before overflow (h/t @ImNotTheWolf for sharing these scripts 🙏)
4. One model per subagent - isolate context per agent instead of shared bloating.
Maybe @ImNotTheWolf is right. Maybe cheap models can't handle complex multi-agent coordination.
Truth is, output from Opus 4.5 is extraordinary. Nothing beats it right now.
But we can't wait until it's affordable for everyone. Until then, let's figure out how to power our bots with less cost.
What if the problem isn't the model intelligence - it's how we manage memory?
Will find out. Experimenting with $5.63 left.
Will share the Qdrant + QMD setup once I test it.
Any recommendations/suggestions on this is appreciated.
Ramya Chinnadurai 🚀@code_rams
Yeah Chris, I realised it in few moments. But now Im running a hybrid setup. 1. Google Gemini CLI (OAuth) 2. OpenAI Codex (OAuth) 3. OpenRouter free tiers 4. OpenRouter paid Bot picks models based on context. OAuth handles 95%+ of traffic. OpenRouter's $10 credit barely gets touched. I don't want to touch this setup again, Let this run for next 1 day, I will share you what happens. To know about oAuth limits, run openclaw models. At end it will show OAuth/token status. I don't commit this works best, i'm still experimenting this and will share the updates.
English
@IncroyableNom @gmoneyNFT I'm running openclaw on ubutu, inside a AWS EC2 instance, having to type openclaw gateway restart several times, although updating the openclaw version has brought more stability.
English
@gmoneyNFT I guess you're on Windows, Windows often terminated the process for me as well. Run your bot inside of a WSL or virtual machine or VPS Linux/MaxOS. The gateway never stops running.
English
I think I type “openclaw gateway restart” like 8-10 times a day. Am I the only one?
English
RSGB / ⚡️ retweetledi
Finally cracked the $10/month AI bot spend after today's epic chaos.
Here is how it went down.
Yesterday many of you suggested trying Kimi-2.5 and OpenRouter free models to save costs.
Thanks for that!
I tried to implement them, but realized Kimi-2.5 needs the latest OpenClaw core to run properly.
Today, a long article & dev task caused a massive context overload. Blackouts everywhere and all models failed with rate limit errors.
$20 credits vanished in minutes.
I had to flush memory and kill processes manually. Then I officially upgraded from Clawdbot to OpenClaw:
npm install -g openclaw
openclaw doctor
npm uninstall -g clawdbot
Once upgraded, I added the OpenRouter safety net:
DeepSeek for coding
Kimi K2.5 for creative/multimodal
Grok for reasoning
Opus 4.5 & Gemini pro only when needed.
Bot now runs smooth. Mostly free models for daily pings, paid only for complex logic.
Spend is now capped at $10/month. No more token panic.
This is my current stack,
I'll update you in coming tweets, how much does it cost exactly.
Ramya Chinnadurai 🚀@code_rams
I missed my @openclaw bot, Chiti, yesterday. 🥺 For the past few weeks, I’ve been using my $20 ChatGPT subscription to power Chiti on GPT-5.2. Everything was smooth until I suddenly hit a strict rate limit and got blocked for 1.5 days. The bot went silent on Telegram. It was a wake-up call without the model, an AI agent is just an appliance without electricity. Completely useless. I tried switching to Gemini Pro as a temporary fix, but it burned through $6 within 3 hrs. I realized I needed a more sustainable architecture to manage both performance and budget. --- The Solution: A Tiered Model Strategy Instead of relying on a single model, I’ve now configured a multi-provider setup (OpenAI, Anthropic, Google, and Codex) with a tiered routing system: 1. The Daily Driver: Gemini Flash It’s incredibly cheap and fast. Chiti uses this for 80% of our interactions - basic chat, task management, and simple pings. This keeps the baseline cost near zero. 2. The Coder: GPT-5.2 (via ChatGPT Plus) This is now strictly reserved for building features or debugging. By isolating it, I avoid wasting my subscription's rate limits on simple "Hello" queries. 3. The Specialist: Claude Opus I keep this in the stack for high-level brainstorming and creative writing, used only when I need that specific reasoning edge. --- The Execution: I’ve configured Chiti to dynamically choose the right "brain" for the task. If I ask a coding question, it automatically spawns a specialist session using GPT-5.2. For everything else, it defaults to the lightweight Flash model. It’s been a fascinating experiment in balancing uptime with intelligence. I no longer worry about the bot going "dead" due to a rate limit, and my monthly spend is finally predictable. The goal isn't just to have the smartest AI, it’s to build a system that stays online and executes exactly when you need it. Hoping this works out! I’ll share more on how it performs as I use it. I’m also planning to explore other alternatives too, if you’re using a different stack, let me know!
English
🎊 @THORChain has hit a new milestone!
Maximum swap volume is now over $10.0M ($13,017,571)!
Previous milestone was $5.0M (2 years 2 months 2 days ago)
English
RSGB / ⚡️ retweetledi
Liquidating loans used to be for institutions only. @RujiraNetwork democratizes this.
Now, everyone can buy liquidated positions with a discount up to 30%.
Name another protocol that allows you to buy $BTC or $ETH at such a discount.
Placing an order with your idle stable coins and having only one fill a year would already outperform every stable coin farm around.
Rujira@RujiraNetwork
We are building the only DEX in the world where you can bid on risky loan positions at a discount of up to 30%. All risky loan positions are liquidated openly and transparently through the RUJI Trade order book. Fair access and equal opportunities for everyone 🐳
English
RSGB / ⚡️ retweetledi
claude code is fucking insane
i know literally NOTHING about coding. ZERO. and i just built a fully functioning web app in minutes
http://localhost:3000/
check it out
English
@THORChain article doesn't specify if this feature is live already, or when it will be live 🤷
English
ROUTER V6
Router v6 is a major architectural upgrade for THORChain’s EVM side.
It removes state from the Router, simplifies deposits, improves batching, and makes aggregator integrations cleaner and more reliable.
A quiet but important step forward. ⚡️
All you need to know ⤵️
blog.thorchain.org/thorchains-rou…
English
@KenduofNirvana @jpthor weird, i think my transfer didn't go through... cant find it in my wallet, also not in the block explorer etherscan...
English
