Semantic Kernel users now need a 1.0 migration plan
Microsoft now directs Semantic Kernel users to Agent Framework, a 1.0 production release positioned as its enterprise-ready successor. The replacement brings long-term support, multi-agent orchestration, multi-provider model support, and A2A capabilities into the migration decision. That shift lands as Browser Use documents local deployment of its open-weights BU-30B-A3B model, while Composio is emphasizing governed MCP access, audit trails, and action-level policies. If you build on Semantic Kernel, map the Agent Framework migration path and its control requirements before extending your current implementation.
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.
|
10/36 · Guided Assistant
Kinaxis launches Maestro Agents for agentic supply-chain orchestration — Kinaxis has added a substantive announcement describing the launch of Maestro Agents, configurable AI agents designed to evaluate supply-chain constraints, recommend actions, and support human-in-the-loop decision-making with governance gu…
Source: the tool's own site — detected 2026-09-14 by agentic.ai's daily recrawl.
|
|
16/36 · Adaptive Collaborator
Browser Use documents self-hosting for its open-weights BU-30B-A3B browser model — Browser Use added documentation and examples for running the open-weights `browser-use/bu-30b-a3b-preview` model locally with vLLM, including a self-hosted OpenAI-compatible endpoint and Hugging Face weights.
Source: the tool's own site — detected 2026-09-15 by agentic.ai's daily recrawl.
|
|
11/36 · Guided Assistant
Casso adds interactive website features including forms, private inboxes… — Casso Websites now advertises working website capabilities beyond static pages, including contact forms that email the owner, private inboxes for bookings and orders, editable prices and hours, and visitor sign-ups and logins with user-spe…
Source: the tool's own site — detected 2026-09-15 by agentic.ai's daily recrawl.
|
|
13/36 · Adaptive Collaborator
Microsoft positions Agent Framework as the successor to Semantic Kernel — Semantic Kernel’s repository now directs users to Microsoft Agent Framework, describing it as the enterprise-ready successor with a 1.0 production release, long-term support, multi-agent orchestration, multi-provider model support, and A2A…
Source: the tool's own site — detected 2026-09-15 by agentic.ai's daily recrawl.
|
|
8/36 · Guided Assistant
Runway shifts its positioning toward general world models and agentic… — Runway’s site now introduces GWM-1, a general-purpose world model with variants for explorable environments and avatars, while highlighting Runway Dev MCP and broader MCP-based model access.
Source: the tool's own site — detected 2026-09-15 by agentic.ai's daily recrawl.
|
|
10/36 · Guided Assistant
Composio repositions as an enterprise MCP gateway for governed AI agents — Composio’s site now presents the product as an enterprise control layer for AI agents and MCP servers, adding emphasis on managed authentication, action-level access policies, unified audit trails, custom MCP servers, SSO/SCIM, reliability…
Source: the tool's own site — detected 2026-09-15 by agentic.ai's daily recrawl.
|
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.
|
Futurum
product launch
Futurum launched the Futurum API and MCP Server to bring its proprietary research and forecasts into enterprise AI tools. Customers can use the data in complex, traceable agent sessions that connect technology analysis with capital-markets strategy. For those tracking agentic AI product launches, this signals a shift from chat-based research toward agents operating on specialized intelligence inside existing workflows. The deciding detail is whether traceability covers every recommendation and action, not just the source documents.
Via Agentic-News.ai — The Montreal Gazette. Read: https://montrealgazette.com/press-releases/globe-newswire/futurum-launches-futurum-api-and-mcp-server-granting-access-to-ai-powered-institutional-grade-intelligence-directly-into-enterprise-workflows
|
|
Sidetrade
product launch
Sidetrade launched SAFE, its Sovereign Agentic Framework for CFOs and Order-to-Cash automation. The framework combines a proprietary data lake, specialized models, private data centers and owned GPU compute while tracking agent actions. For those tracking agentic AI products, this signals a push toward private, auditable systems for financial workflows. SAFE's model-selection layer is designed to match each task with the most accurate and cost-efficient open-weight model.
Via Agentic-News.ai — Taiwan News. Read: https://taiwannews.com.tw/en/news/6437617
|
|
Wisr AI Systems
product launch
Wisr AI Systems launched RiskAssure, a security assurance platform that coordinates AI agents to gather evidence and answer questionnaires. The system uses retrieval-augmented generation to analyze requirements and produce source-cited responses. For those tracking agentic AI products, this is a concrete move from chat assistance to compliance workflow execution. The important test is whether security teams trust its evidence enough to replace manual review.
Via Agentic-News.ai — wallstreet:online. Read: https://www.wallstreet-online.de/nachricht/21361814-wisr-ai-systems-launches-riskassure-agentic-ai-platform-for-security-assurance
|
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.
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.
- 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.
- OpenHands · 18/36 · Adaptive Collaborator · L2
OpenHands (formerly OpenDevin) is a fully autonomous open-source AI coding agent. MIT-licensed core, plans + executes Python actions via CodeAct, uses browser + terminal + files. ~72% on SWE-bench Verified with Sonnet 4.5 via the OpenHands Software Agent SDK (arXiv:2511.03690).
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: Self-hosting
Self-hosting means you run the agentic AI tool on your own servers, cloud account, or internal infrastructure instead of sending everything to a vendor’s hosted service. A simple example: your company installs an agent workflow on its own AWS account so customer data stays inside its network, and only your team controls access, logs, and retention. The tradeoff is real. You get more control and usually better privacy, but your team has to handle setup, updates, scaling, backups, and failures. If the vendor’s cloud goes down, you’re less exposed to their outage. If your own setup is messy, you own that too.
What agentic AI actually means →
One tool worth testing
Browser Use — Browser Use is worth testing for teams that need an agent to operate web applications from infrastructure they control. Its new documentation for self-hosting the open-weights BU-30B-A3B browser model with vLLM and an OpenAI-compatible endpoint creates a practical deployment option beyond a hosted service. Run a 30-minute pilot against a staging form-completion workflow, comparing local setup effort, browser-task reliability, and the access controls you need for internal applications.
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 →
|