New release from @PacktDataML @PacktPublishing "Agentic Architectural Patterns for Building Multi-Agent Systems: Proven design patterns and practices for GenAI, agents, RAG, LLMOps, and enterprise-scale AI systems" See it at http://
amzn.to/3MaHy8T ๐๐๐๐๐ ๐ ๐
TOOLS
-

Book: Agentic Architectural Patterns for Multi-Agent GenAI Systems
By
–
-

Graph Machine Learning book โ updated techniques with PyTorch Geometric
By
–
2nd Edition โ now at http://
amzn.to/45Y3LyI v/ @PacktDataML Graph Machine Learning โ Latest advancements in Graph Data to build robust #MachineLearning algorithms ๐๐ฎ๐ ๐๐ฎ๐ช๐ฝ๐พ๐ป๐ฎ๐ผ:
Master new graph ML techniques through updated examples using PyTorch Geometric and -
Sonnet 4.6 Makes AI Browser Extensions Finally Usable
By
–
AI Chrome extensions felt largely unusable because of how slow they were. Sonnet 4.6 is the first one that changes that for me. While in meetings, I am kicking off browser tasks and unlike Opus 4.5, it actually finishes before the meeting is done.
-
Abacus AI Launches Personal AI Agents on Telegram
By
–
๐จ Secure OpenClaw – Message Your Custom AI Agent From Telegram
— Abacus.AI (@abacusai) 18 fรฉvrier 2026
We are excited for our first release of personal agents. You can now use Abacus AI's DeepAgent to vibe code a personal agent on Telegram
Create and simply message the agent!
– do tasks like respond to emails
-โฆ pic.twitter.com/PEIVGgTYM4Secure OpenClaw – Message Your Custom AI Agent From Telegram We are excited for our first release of personal agents. You can now use Abacus AI's DeepAgent to vibe code a personal agent on Telegram Create and simply message the agent! – do tasks like respond to emails
– -
Codex Mobile Experience Needs Parity with Terminal Version
By
–
why is Codex on mobile so broken – it should feel similar to the experience on terminal
-
Amical launches an open-source AI dictation app
By
–
Amical launched a new open-source AI dictation app, reinforcing its position as a local-first alternative to subscription tools like Wispr Flow and Granola.
— ๐จ AI News | TestingCatalog (@testingcatalog) 18 fรฉvrier 2026
It runs entirely on your machine and includes context-aware formatting.
It uses Whisper and open-source LLMs toโฆ pic.twitter.com/esmsX2NEa5Amical launched a new open-source AI dictation app, reinforcing its position as a local-first alternative to subscription tools like Wispr Flow and Granola. It runs entirely on your machine and includes context-aware formatting. It uses Whisper and open-source LLMs to
-
AI agents can now buy services autonomously
By
–
AI agents can now buy services and products on Contra.
— God of Prompt (@godofprompt) 18 fรฉvrier 2026
If youโre too busy to search through millions of freelancers, send OpenClaw.
This is a massive advancement. https://t.co/ZNPtvE5LskAI agents can now buy services and products on Contra. If youโre too busy to search through millions of freelancers, send OpenClaw. This is a massive advancement.
-
Snorkel Releases Agentic RL Eval Environment and Finance Reasoning Benchmark
By
–
Snorkel contributed: โข An agentic RL eval environment โข FinQA-Reasoning dataset โข Finance Reasoning benchmark Full technical breakdown from the rLLM team + our enterprise takeaways here:
-

Databricks AppKit and Replit Speed Enterprise App Development
By
–
Ship enterprise apps faster with Databricks AppKit and @Replit
. AppKit is a TypeScript framework with built-in observability and seamless integration with Databricks services. The new Replit integration lets you develop data-aware apps using natural language and deploy directly -

Agentic AI Tools in Software Engineering and Risk Monitoring
By
–
Software engineering makes up ~50% of agentic tool calls on our API, but we see emerging use in other industries. As the frontier of risk and autonomy expands, post-deployment monitoring becomes essential. We encourage other model developers to extend this research.