"If you’re building agents (or just using them in tools like Claude or Cursor), installing the MCP and exploring the directory is a must-try. Agent Wonderland isn’t hype—it’s working infrastructure demonstrated live in the interview."
LLMS
-
Open-Source SDK for Building Custom AI Agents Released
By
–
Now anyone can build their own custom AI agent.
— Nico (@nicos_ai) 13 mai 2026
Cline just open-sourced an SDK for building agents with:
• plugins
• MCPs
• subagents
• web fetch
• cron jobs
• agent teams
• multi-model routing
npm i @cline/sdk https://t.co/aaREgoY28F pic.twitter.com/8B4EGBvaDMNow anyone can build their own custom AI agent. Cline just open-sourced an SDK for building agents with: • plugins
• MCPs
• subagents
• web fetch
• cron jobs
• agent teams
• multi-model routing npm i @cline/sdk -
AI Agents Gaining Wallets for Commerce and Business Operations
By
–
Agent to agent commerce with Colin Gillingham, @gillinghammer, founder of https://t.co/mNywgIlI70
— Robert Scoble (@Scobleizer) 13 mai 2026
We go into what he is doing to give your AI agents a wallet so they can go shopping. Or run their own business. pic.twitter.com/6D3amN2p5SAgent to agent commerce with Colin Gillingham, @gillinghammer
, founder of https://
agentwonderland.com/agents We go into what he is doing to give your AI agents a wallet so they can go shopping. Or run their own business. -
Revenue ramp via costly tokenizer in 4.7 boosts tokens per query
By
–
i think ppl forget that rev ramp might also be driven by a more spenny tokenizer on 4.7 up to 1.3x more tokens for the same query revmaxxing by tokenizer upgrade (amongst other things ofc)
-
The hidden operational costs of AI agent evaluation
By
–
The evals setup alone is a full time job that most companies haven't budgeted for when they signed the agent deal.
-
Anthropic Tests New Model Selector and Connectors for Claude Mobile App
By
–
Anthropic is testing a new model selector for Claude on mobile, moving it directly to the prompt area. > Bottom navigation tabs are being tested as well. > Connectors Discovery is coming to mobile too, where Claude will suggest the best connector for a given task.
-
Appreciating Layers of AI Security: Beyond Prompt Injection Dangers
By
–
if your reaction to this is “haha openclaw bad, see prompt injection is the #1 danger” you:
1) havent sufficiently appreciated the layers to this tweet
2) havent seen enough ai api keys -
Tolaria: A New Mac App for Markdown Knowledge Bases Inspired by Karpathy
By
–
Karpathy's LLM wiki idea just became a real Mac app! Tolaria is a Mac app for managing markdown knowledge bases. Your notes are plain markdown files stored in a git repository. No cloud, no subscriptions, completely offline. The core idea: knowledge bases work better when
-
Governed intelligence infrastructure: beyond self-improving AI
By
–
The market is validating self-improving AI. But the larger category is not only AI that improves AI. It is governed intelligence infrastructure: agents that discover,
validators that prove,
memory that preserves,
governance that controls,
and capability that compounds. -
CIO shocked as Claude bill triples for 30 seats
By
–
"Holy cow."
That's the Telaid CIO watching his Claude bill triple in 30 days for 30 seats. Anthropic was already the priciest frontier lab. Claude Opus runs richer per token than anything OpenAI or Google ships. And now Anthropic has moved enterprise customers from flat fees to