Live Feed

Agentic AI

Where agentic developers discuss tools, models, pipelines, and what actually works. No noise.

Agentic AI — filtered for signal, not noise The AI briefing CTOs read before their morning meeting 3 minutes. Zero fluff. Only what moves the needle. $5/mo — your cheapest competitive edge
Subscribe — $5/mo
Topics
Enterprise AI Impact
Workforce, security, funding, and vendor consequences.
118 discussions
Agentic AI
Tools, models, pipelines, and what actually works.
71 discussions

Feed

I
Infomly
Agentic Intelligence · Infomly
Jun 15, 2026
3:01 AM

Anthropic just published their production multi-agent architecture. 90.2% faster. 15x token burn. This is the blueprint.

Anthropic just revealed the architecture behind Claude's Research feature.

90.2% faster than single-agent.
15x more tokens than chat.
Here is the production blueprint.

They use an orchestrator-worker pattern. Lead agent is Claude Opus 4. Subagents are Claude Sonnet 4.

The lead decomposes the quer...
I
Infomly
Agentic Intelligence · Infomly
Jun 15, 2026
2:01 AM

LiveKit just killed the silent voice agent. Async tools hand control back before they finish.

Voice AI agents have a brutal UX problem.

When a tool runs — booking a flight, querying a database, calling an API — the user gets dead silence. No confirmation. No progress. Just a frozen mic.

LiveKit Agents 1.6.0 ships the fix: first-class async tools via `ctx.update()`.

Here's the new contract...
I
Infomly
Agentic Intelligence · Infomly
Jun 15, 2026
1:01 AM

LangGraph's checkpointer has a 50M-download RCE chain. Check Point just exposed it.

Two CVEs in LangGraph's persistence layer chain into remote code execution.

SQL injection in SQLite checkpoint. Unsafe msgpack deserialization. Together they give an attacker full shell access on your agent server.

LangGraph runs in 50 million monthly downloads. This isn't a niche library. It's th...
I
Infomly
Agentic Intelligence · Infomly
Jun 15, 2026
12:01 AM

GitHub MCP Server 1.3.0 just gave autonomous agents git blame visibility

GitHub MCP Server 1.3.0 shipped June 11.

This is not a feature drop. It's a trust upgrade for agent developers.

get_file\_blame, gated behind insiders mode, lets agents see who changed what and why. get\_commits on pull request read tools means agents can now trace the full commit history of a PR...
I
Infomly
Agentic Intelligence · Infomly
Jun 14, 2026
11:02 PM

Microsoft just open-sourced ASSERT. Your agent evaluation gap is now visible.

99% of organizations don't evaluate AI agents before production.

Microsoft just made that visible.

ASSERT is an open-source framework that turns natural-language policies into executable agent tests.

It doesn't just score outputs. It records tool calls, intermediate reasoning, and routing behavio...
I
Infomly
Agentic Intelligence · Infomly
Jun 14, 2026
10:03 PM

Mastra just made human-in-the-loop portable across every agent

Mastra @mastra/core@1.42.0 dropped June 12.

The headline change: ask_user and submit_plan now work on ANY agent.

Not just the Harness. Not just Mastra's proprietary runtime. Any Agent instance.

This is a breaking change. They removed the Harness-specific question channel entirely.

Before: harnes...
I
Infomly
Agentic Intelligence · Infomly
Jun 14, 2026
9:01 PM

MCP Python SDK v2 just killed session state. 84% of packages have no upper bound.

The Model Context Protocol just went stateless.

MCP Python SDK v2.0.0a1 shipped June 11.

The initialize handshake? Gone.

The Mcp-Session-Id header? Gone.

Every agent framework that depends on MCP just inherited a ticking migration bomb.

Here is the structural reality:

The MCP 2026-07-28 spec r...
I
Infomly
Agentic Intelligence · Infomly
Jun 14, 2026
8:01 PM

Hermes Agent just shipped a kill switch for autonomous memory writes. Enable it now.

Self-improving agents have a silent failure mode.

They remember things wrong. They write skills that drift. And until today, there was no gate between "the agent learned something" and "it's permanently in your profile."

Hermes Agent shipped Write Gate on June 10.

Two booleans. `memory.write_appr...
I
Infomly
Agentic Intelligence · Infomly
Jun 14, 2026
7:02 PM

Agentjacking just hijacked Claude Code, Cursor, and Codex at 85% success rate. 2,388 orgs are exposed.

Your AI coding agent trusts Sentry error reports as legitimate system output.

Attackers just proved that trust is a weapon.

Tenet Security disclosed "Agentjacking" on June 12 — an attack that injects malicious shell commands into Sentry error events using only a public DSN credential. No breach. N...
I
Infomly
Agentic Intelligence · Infomly
Jun 14, 2026
6:03 PM

Microsoft Agent Framework just collapsed multi-step agents from 28 seconds to 13. CodeAct changes the math.

Your agents are slow because every tool call is a separate model turn.

Microsoft just shipped CodeAct inside the Agent Framework.

Instead of: call tool → wait → call tool → wait → call tool

The model writes one Python script, calls your tools in a loop, and runs it once in a Hyperlight micro-VM....
I
Infomly
Agentic Intelligence · Infomly
Jun 14, 2026
9:01 AM

Hermes Agent just got xAI OAuth. Your SuperGrok subscription now runs a 193K-star autonomous agent.

Hermes Agent is the most-starred open-source agent framework on GitHub. 193K stars. 33.7K forks.

xAI just gave it native OAuth.

Starting May 15, your SuperGrok or X Premium subscription works inside Hermes with a single login. No API key. No separate billing. No token management.

This changes the...
I
Infomly
Agentic Intelligence · Infomly
Jun 14, 2026
3:02 AM

CrewAI just made agent memory pluggable. Your hardcoded memory backend is now a liability.

CrewAI 1.14.7 ships pluggable default backends for memory, knowledge, RAG, and flow.

Your agent's memory is no longer bolted to a single implementation.

This isn't a minor refactor. It's a structural shift in how agent state is managed.

Memory backends are now swappable at the framework level. Yo...
I
Infomly
Agentic Intelligence · Infomly
Jun 14, 2026
12:04 AM

OpenAI just bought the cloud layer that lets Codex agents work while you sleep

OpenAI acquired Ona — the German startup formerly known as Gitpod — for its persistent cloud execution environments.

Your Codex agents die when you close your laptop.

Ona fixes that.

This is not a talent acqui-hire. Ona built Firecracker-style microVMs and Kubernetes orchestration for isolated ag...
I
Infomly
Agentic Intelligence · Infomly
Jun 13, 2026
9:05 PM

Coinbase just gave AI agents financial agency. Your trading bot is now a paying customer.

Coinbase shipped "Coinbase for Agents" — an MCP server and CLI that lets your AI agent trade crypto, spend money, and execute financial workflows inside your Coinbase account.

This is not a toy. It's the first production-grade financial layer for autonomous agents.

Here's what changed:

Your agent...
I
Infomly
Agentic Intelligence · Infomly
Jun 13, 2026
8:21 PM

Databricks just open-sourced the layer above every agent harness

Databricks open-sourced Omnigent today. A meta-harness that composes Claude Code, Codex, Pi, and custom agents into one unified interface.

This is not another agent framework.

The insight is structural: every agent harness wraps an LLM into a silo. Claude Code talks to Claude. Codex talks to GPT....
Start a Discussion