Semantic Kernel is being superseded; Replit changed the math
Semantic Kernel’s page now says it is being superseded by Microsoft Agent Framework, with stable APIs, long-term support, multi-agent orchestration, and cross-runtime interoperability. At the same time, Replit Agent updated plan details and added publishing, reserved VMs, security scanning, Auto-Protect, Slack agents, and an integrations hub, while Google pushed Gemini in Chrome toward auto browse and a new side panel. If you build on Semantic Kernel or ship browser-heavy agents, today’s check is your migration path and where execution now lives.
See what changed on Semantic Kernel's listing →
What changed on the ground
Changes we detected on each tool's own pages — pricing, features, platform reach — via our daily crawls. Often ahead of any press coverage; each links to the scored listing.
|
12/36 · Guided Assistant
Google details major Gemini in Chrome updates, including auto browse… — The page now announces major updates to Gemini in Chrome for MacOS, Windows, and Chromebook Plus, including a new side panel experience, auto browse, and deeper Google app integrations.
Source: the tool's own site — detected 2026-08-12 by agentic.ai's daily recrawl.
|
|
13/36 · Adaptive Collaborator
Semantic Kernel rebrands as Microsoft Agent Framework, adds production-ready… — The Semantic Kernel page now says the project is being superseded by Microsoft Agent Framework, describing MAF as the enterprise-ready successor with stable APIs, long-term support, multi-agent orchestration, cross-runtime interoperability…
Source: the tool's own site — detected 2026-08-11 by agentic.ai's daily recrawl.
|
|
12/36 · Guided Assistant
Replit updates Agent pricing and adds new publishing, security… — Replit’s Agent page now includes revised plan details plus new product capabilities around publishing, reserved VMs, security scanning, Auto-Protect, Slack agents, and an integrations hub.
Source: the tool's own site — detected 2026-08-12 by agentic.ai's daily recrawl.
|
|
21/36 · Domain Specialist
Gobii adds a new Team tier and updates Pro/Scale pricing with task-based limits — Gobii’s pricing page now includes a new Team plan at $50 per seat/month, alongside updated Pro and Scale tiers, revised task allowances, overage pricing, and a refreshed comparison table.
Source: the tool's own site — detected 2026-08-12 by agentic.ai's daily recrawl.
|
|
11/36 · Guided Assistant
Julius launches Notebooks, Browser Agent, and MCP integrations in a major… — The Julius homepage and feature pages were overhauled to emphasize a new workspace-oriented product, with launches including Notebooks (renamed from Workflows), Browser Agent, website/video/image/excel/slide creation, and MCP-based data ac…
Source: the tool's own site — detected 2026-08-11 by agentic.ai's daily recrawl.
|
|
10/36 · Guided Assistant
Dust repositions its homepage around "multiplayer AI" and human-agent… — Dust’s homepage has been substantially rewritten to frame the product as a collaborative AI workspace for teams and agents.
Source: the tool's own site — detected 2026-08-12 by agentic.ai's daily recrawl.
|
Score activity
|
5/36 · Reactive Tool
Score re-evaluated after: Island launches enterprise vibe publishing for employee apps
Trigger: SecurityBrief Asia — "Island launches enterprise vibe publishing for employee apps".
|
What's new in the directory
|
15/36 · Adaptive Collaborator
driftless turns paired PRDs and tech specs into tracked, gated delivery work. It uses persistent agents to write, test, and verify software instead of just tracking tasks.
Source: published listing, rubric-scored on ingest.
|
|
10/36 · Guided Assistant
Auto-Respond is a voice agent platform for answering calls, collecting details, and booking appointments through connected scheduling systems. It supports live call flows with real availability, voice selection, and built-in or external calendar integrations.
Source: published listing, rubric-scored on ingest.
|
|
23/36 · Domain Specialist
Bernstein runs multiple CLI coding agents in isolated git worktrees, then verifies and merges only the diffs that pass checks. It is designed for reproducible, on-prem agent workflows with signed audit logs and offline review.
Source: published listing, rubric-scored on ingest.
|
From Agentic-News.ai
Agentic-AI industry signal we're tracking — launches, releases, and research from across the ecosystem. The directory rubric hasn't scored these yet; awareness now, evaluation next pass.
|
RiskProfiler
product launch
RiskProfiler launched KnyX Autonomous Investigations to automate threat investigation, verdict generation, and policy-based remediation. The company is showing the feature at Black Hat USA and DEF CON 34. For those tracking agentic AI product launches, this is a concrete move from detection toward automated response. The hook is that the system is built to act on threats, not just summarize them.
Via Agentic-News.ai — Express Computer. Read: https://www.expresscomputer.in/news/riskprofiler-launches-ai-powered-threat-investigation-capability/137417
|
|
Athelas
product launch
Athelas, powered by Commure, launched Practice Manager on Aug. 5, 2026 as an agentic practice management suite. The platform is built to coordinate AI agents across billing, scheduling, and patient communication. For those tracking agentic AI product launches, this shows healthcare ops software moving from chat to execution. The sharpest detail is the claim that 7% of US healthcare appointments already pass through Athelas.
Via Agentic-News.ai — Eagle-Tribune. Read: https://www.eagletribune.com/region/athelas-launches-practice-manager-the-worlds-first-agentic-practice-management-suite/article_c5025937-673a-581f-8ab9-135abcc2a170.html
|
Agenticness Leaderboard
This week's most-clicked tools, re-ranked by rubric score. The score is the editorial signal; the popularity is what drew the directory's traffic here this week.
Claude Code is Anthropic's agentic coding tool that lives in your terminal. It understands your entire codebase, makes multi-file edits, runs commands, manages git workflows, and uses MCP for tool integration. Built with a Unix philosophy — it reads, plans, edits, and verifies in a loop. The fastest-growing product in the coding agent category.
- Cursor · 18/36 · Adaptive Collaborator · L2
Cursor is a developer-focused AI environment that adds agents, context, and automation around your repositories. It combines an editor-like interface, a CLI, and a cloud agent API to automate code review, bug fixing, CI hygiene, and more. Designed for individual developers and engineering teams who want AI to take real actions in their code and infrastructure, not just chat.
- Cline · 18/36 · Adaptive Collaborator · L2
Cline is an AI coding assistant for VS Code that can inspect your project, edit files, run terminal commands, and use a browser while asking for permission at each step. It is aimed at developers working on real codebases who want more than code completion.
GitHub Copilot helps you write, review, and adapt code directly in GitHub, your IDE, and the terminal. It supports everything from inline suggestions to agentic coding workflows with broader model choices and enterprise controls.
Devin Desktop (formerly Windsurf, and distinct from Cognition's cloud agent Devin) is an AI-native desktop app for developers. It keeps the full IDE — editor, syntax highlighting, autocomplete, debugging — and adds a command centre for running and coordinating multiple coding agents in one place. Available for Mac, Windows, and Linux.
What operators are searching for this week
A week's demand signal — what operators are typing into the directory's search. Suggestion-chip defaults + off-topic / greetings filtered.
- "best coding agent"
- "AI agent to triage and reply to my email inbox"
- "best coding agent for a large existing codebase"
- "tools to automate customer support ticket triage"
- "AI agent that can browse the web and fill out forms"
Learn: How Amazon Alexa Routines actually works
Amazon Alexa Routines, based on the description you gave, is mainly an assistant that responds to you and carries out defined tasks in the Alexa app, on the web, and on compatible devices. It can help with chat, smart home control, shopping help, and connected services. The evidence here does not show a system that plans long projects or keeps a running memory across sessions. It looks more like a command-and-action layer than an independent worker. You ask, it acts within those supported areas, then control returns to you. The low 9/36 score fits that limited autonomy. The free tier and Prime access change who can use it, not what it can decide on its own.
See Amazon Alexa Routines's full scorecard →
One tool worth testing
Replit Agent — Replit Agent is the coding-and-shipping choice to test today. Replit just revised its plan details and added publishing, reserved VMs, security scanning, Auto-Protect, Slack agents, and an integrations hub, which makes this more than a code generator update. Run a 30-minute pilot against Cursor or Claude Code: create a small feature, publish it, verify the scan behavior, and see whether the Slack and integration hooks fit your team’s handoff loop.
Our pick: n8n
The use case: workflow automation.
Tops our independent /36 — strongest on action and reliability, ahead of Zapier. Pricing: Per-execution (not per-step).
Ranked by our 9-dimension Agenticness rubric — not by who pays us (nobody does). The full scorecard, true-cost pricing, and the reliability evidence behind every score are in the report.
Read the full report →
|