Sabitlenmiş Tweet
I used to feel anxious whenever I was away from my laptop.
Not because I wanted to be online 24/7 - but because when I stepped away, progress on my work stopped.
That feeling is a big part of why I built @OpenLegion.
English
Curious Cake
18.2K posts
Curious Cake
@TheCuriousCake
Building @OpenLegion & AFKCrypto 🚀 Exited Founder (1M+ deliveries/yr - NA) 📦 Scaling AI Agent Teams + Connecting DeFAI 🤖 Road to a $1B Solopreneur 🦄
Katılım Mart 2016
2K Takip Edilen3.6K Takipçiler
Curious Cake retweetledi
OpenLegion is now listed on @everyshell's Shelldex - a platform for discovering and comparing AI agent projects.
Check out our profile:
shelldex.com/projects/openl…
English
Biggest release yet! 🚀
What matters most is not just the feature list.
OpenLegion feels much more like real infrastructure now - more secure, more usable, and much closer to something teams can build on top of in production.
OpenLegion@OpenLegion
🎉 OpenLegion v0.3.0 is out. 🚀 Our biggest release yet. - Major browser architecture overhaul - Complete dashboard redesign - Deeper production security hardening - Improved multi-agent coordination - Secure EVM + Solana wallet support - Custom + local LLM provider support Nearly 300 PRs since the last release. 👀 A big step toward agent infrastructure built for real-world work.
English
A lot of agent products still feel like demos.
This release pushed OpenLegion much closer to real infrastructure.
We rebuilt the browser stack, redesigned the dashboard, hardened security across the platform, improved multi-agent coordination, added secure wallet support, and expanded support for custom + local LLMs.
Nearly 300 PRs since the last release.
Still early - but this feels like a big step toward agents teams can actually trust to do real work.
English
@OpenLegion If you are using Oauth method - make sure to rotate those credentials too!
English
🚨 Important security notice:
A supply chain attack compromised litellm versions 1.82.7 and 1.82.8 on PyPI. both versions contained a malicious payload that ran automatically on python startup and exfiltrated environment variables, ssh keys, cloud credentials, and other secrets to an attacker-controlled server.
if you are self-hosting, check your installed version:
pip show litellm | grep Version
if you are on 1.82.7 or 1.82.8, assume compromise and:
update your pin to litellm>=1.60.0,<=1.82.6 and reinstall
check for and remove litellm_init.pth in your python site-packages
rotate all api keys, ssh keys, and cloud credentials on the affected system
check for persistence: ~/.config/sysmon/sysmon.py and related systemd services
review outbound traffic logs for connections to models.litellm.cloud
if you are not on 1.82.7 or 1.82.8, no action is required. full details: github.com/BerriAI/litell…
English
🚨 If you are self-hosting OpenLegion - make sure to downgrade your litellm versions to 1.82.6 and rotate your API Keys ASAP!
OpenLegion@OpenLegion
🚨 Important security notice: A supply chain attack compromised litellm versions 1.82.7 and 1.82.8 on PyPI. both versions contained a malicious payload that ran automatically on python startup and exfiltrated environment variables, ssh keys, cloud credentials, and other secrets to an attacker-controlled server. if you are self-hosting, check your installed version: pip show litellm | grep Version if you are on 1.82.7 or 1.82.8, assume compromise and: update your pin to litellm>=1.60.0,<=1.82.6 and reinstall check for and remove litellm_init.pth in your python site-packages rotate all api keys, ssh keys, and cloud credentials on the affected system check for persistence: ~/.config/sysmon/sysmon.py and related systemd services review outbound traffic logs for connections to models.litellm.cloud if you are not on 1.82.7 or 1.82.8, no action is required. full details: github.com/BerriAI/litell…
English
Agents can already turn vague goals into executable work.
A lot of people in sales, marketing, and other knowledge-work roles still think AI taking jobs is exaggerated.
That’s exactly how many software engineers sounded a year ago.
Now they’re among the first being displaced.
It makes sense:
Engineers adopt cutting-edge AI tools first, build the automations first, and accelerate disruption in their own industry first.
Other industries are not exempt.
They’re just behind.
Adapt fast or get replaced.
English
OpenClaw is the single most important software release ever
It is critical you use it to its max potential
In this video I cover EVERY aspect of OpenClaw you need to know
From set up to use cases to local models. EVERYTHING
This is the only OpenClaw video you'll ever need:
English
It’s still early, but this feels like an important step toward usable on-chain agent execution. Excited to see what gets built!
English
We use public RPC URLs by default, with bring-your-own-RPC support, so teams can plug in their own endpoints for better reliability.
English
Due to popular request, we’ve just deployed crypto wallet infrastructure into @OpenLegion! 🚀
Now supporting Ethereum-compatible (EVM) blockchains and Solana. 👇🧵
English
If you are not using AI to level up your business as superhuman speed you will be left behind. Get started today!
English
This is the kind of thing that gets really interesting.
We’re not just giving agents wallets.
We’re giving them a structured way to hold wallets, restrict chain access, interact with contracts, and generate more specialized onchain skills when needed.
Public RPC by default for now.
BYO RPC next.
OpenLegion@OpenLegion
We now have built-in crypto wallet infrastructure. How it works: 1. Initializing system wallets generates a master seed 2. Agent wallets are derived from that seed 3. Wallet access can be enabled per agent 4. Allowed chains can be configured per agent 5. Each agent also has built-in smart contract execution skills. That means agents can interact with contracts out of the box - and generate more specific protocol skills when needed, like trading via Uniswap contracts. Currently using public RPC URLs by default. Bring-your-own RPC support is next for better stability and control.
English
@TheDazzleNovak I believe when you setup the llm provider - you can select to use API or Oauth token
English
I am just over a week into my AI Agent journey running my own agent on a Raspberry Pi 5 with OpenClaw using Claude as the LLM
Lots of lessons learned so far as it’s INCREDIBLY EASY to burn through tokens and cost lots of money as you explore and talk with it.
Should I do a video or write up breakdown of adjustments I’ve made and lessons I’ve learned so far?
English