GitHub Copilot adds native MCP integration
GitHub Copilot’s page now emphasizes native MCP server integration, custom and third-party agents, and broader agent-driven workflows. That lands the same day Microsoft Agent Framework moves up to 11/36, with Microsoft’s new cybersecurity model still carrying a hidden agentic capability, and search demand keeps clustering around “best coding agent.” The pattern is clear: operators are no longer just comparing chatbots, they are checking which stacks can actually plug into tools and workflows. That makes integration depth the thing to verify first.
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.
|
18/36 · Adaptive Collaborator
Goose appears to transfer to the aaif-goose organization and AAIF branding — The Goose GitHub listing now shows the aaif-goose organization instead of the prior Michael Neale owner, suggesting an ownership/governance transition.
Source: the tool's own site — detected 2026-07-29 by agentic.ai's daily recrawl.
|
|
7/36 · Guided Assistant
Personal AI adds AI Training Studio with streamlined uploads… — Personal AI’s site now highlights an AI Training Studio with batch uploads, automatic file naming, upload history, auto-memory/document cleaning tools, and direct Gmail, Google Drive, Outlook, and OneDrive syncs tied to personas.
Source: the tool's own site — detected 2026-07-29 by agentic.ai's daily recrawl.
|
|
5/36 · Reactive Tool
HyperWrite revamps its subscription tiers with a new Ultra plan — HyperWrite appears to have reworked its paid offering, replacing prior Premium messaging with an Ultra subscription and updating plan benefits.
Source: the tool's own site — detected 2026-07-29 by agentic.ai's daily recrawl.
|
|
18/36 · Adaptive Collaborator
GitHub Copilot adds native MCP server integration and expands agent workflows — The Copilot marketing page now highlights native MCP server integration, custom and third-party agents, and broader agent-driven workflows.
Source: the tool's own site — detected 2026-07-29 by agentic.ai's daily recrawl.
|
|
3/36 · Reactive Tool
C3 AI adds Generative AI for Sales with MCP-backed integrations and agentic… — C3 AI appears to have launched a new sales-focused generative AI product page featuring AI-driven pricing, meeting prep, account prioritization, upsell insights, and support for integrating agents with third-party systems via MCP.
Source: the tool's own site — detected 2026-07-29 by agentic.ai's daily recrawl.
|
|
11/36 · Guided Assistant
Jasper surfaces MCP support and a new Translation agent in its platform… — The homepage/nav was updated to add Jasper MCP alongside Jasper APIs, Image APIs, Grid, and AI Studio, and the Agents section now labels Translation as new.
Source: the tool's own site — detected 2026-07-28 by agentic.ai's daily recrawl.
|
Score activity
|
11/36 · Guided Assistant
Score re-evaluated after: Microsoft said this week it launched its first cybersecurity model, but its new agentic system's key capability is still hidden.
Trigger: TechCrunch AI — "Microsoft said this week it launched its first cybersecurity model, but its new agentic system's key capability is still hidden.".
|
In the news
|
8/36 · Guided Assistant
Tines launched Tines 3B on July 28, 2026 as an AI-native platform for building, running, and governing enterprise workflows, apps, and agents. The company says it rebuilt the platform after tripling its enterprise customer base. For those tracking agentic AI, this points to a market moving from experiments to controls, oversight, and scale. The big question is whether Tines can make orchestration simple enough for every employee to build with AI safely.
Source: Taiwan News — "Tines 3B promises one place to run and govern enterprise agents after tripling its customer base.".
|
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.
|
Cyabra
product launch
Cyabra announced Coordinated Activity, an AI agent that automatically investigates coordinated online behavior and delivers a single evidence-backed verdict. The launch was reported on July 28, 2026 and is aimed at governments and enterprises that need faster digital trust checks. For those tracking agentic AI, this shows agents moving into judgment-heavy workflows, not just task automation. The interesting part is how the system copies an analyst's method and then packages the result into one call.
Via Agentic-News.ai — The Manila times. Read: https://www.manilatimes.net/2026/07/28/tmt-newswire/globenewswire/cyabra-launches-ai-agent-that-automatically-investigates-coordinated-online-activity-and-delivers-a-verdict/2393144
|
|
Torq
product launch
Torq launched SOC Brain, a new layer for its AI SOC Platform that learns from historical investigations, analyst decisions, and organization-specific security operations. The company says the system builds a self-learning security operations center from day zero rather than relying on static rules alone. For those tracking agentic AI, this is a clear example of memory and precedent shaping autonomous decisions. The key detail is how the platform turns old investigations into operational judgment for new cases.
Via Agentic-News.ai — FinanzNachrichten.de. Read: https://www.finanznachrichten.de/nachrichten-2026-07/69144456-torq-unveils-the-soc-brain-the-ai-soc-that-learns-not-just-remembers-004.htm
|
|
BridgeApp
product launch
BridgeApp introduced an orchestration layer on July 27, 2026 that connects people, AI agents, tasks, and context in one workspace. The system is built to move software work from a to do item to a finished pull request with no tool switching. For those tracking agentic AI product launches, this signals a push toward tools that can own more of the development cycle. The catch is whether BridgeApp can really learn a codebase well enough to ship production-ready changes safely.
Via Agentic-News.ai — Barchart.com. Read: https://www.barchart.com/story/news/3490771/bridgeapp-launches-ai-orchestration-layer-that-automates-the-full-software-development-cycle
|
Biggest movers this week
Listings with the largest week-over-week jump in outbound-click interest
- Cline · +15.2% week-over-week. 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.
- Claude Code · +4.3% week-over-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.
Biggest declines this week
Listings with the largest week-over-week drop in outbound-click interest
- Factory AI · -54.5% week-over-week. Factory provides Droid, an AI agent you can use in coding workflows and IDE integrations like Zed. It connects through login or API key setup and charges usage with Standard Tokens across multiple models.
- Wingman by Emergent · -46% week-over-week. Wingman is a messaging-first autonomous AI agent by Emergent. It connects to your email, calendar, Slack, CRM, and GitHub, then handles scheduling, research, sales support, and admin tasks through WhatsApp and Telegram conversations.
- Bolt.new · -37.5% week-over-week. Bolt is an AI coding environment for building websites, apps, and prototypes from a prompt. It also connects to Figma and GitHub so you can start from an existing design or codebase.
- Replit Agent · -35% week-over-week. Replit is a cloud-based development platform for building, running, and publishing apps. Its AI tools can help you set up projects, answer code questions, and troubleshoot issues inside your workspace.
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.
- Cline · 19/36 · Domain Specialist · L3
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.
Devin Desktop (formerly Windsurf) is Cognition's 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.
- 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.
Wingman is a messaging-first autonomous AI agent by Emergent. It connects to your email, calendar, Slack, CRM, and GitHub, then handles scheduling, research, sales support, and admin tasks through WhatsApp and Telegram conversations.
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"
- "Agent IA qui analyse les documents comptables, prépare les écritures et les valide avant export vers Octopus."
- "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"
Learn: How Refinery actually works
Refinery is a data wrapper, not an agent that plans or acts on its own. Based on the description, it takes DeFi and network intelligence and packages it into JSON bundles for other systems to read. That means its job is to supply fresh, structured market context to agents or trading workflows, not to decide trades, execute transactions, or hold a long-running plan.
In plain English: it feeds information into an autonomous system, then hands control back. The system that uses Refinery would still need its own logic for decisions, memory, and execution. A 3/36 score fits that picture - this looks narrow and input-focused, with little evidence of broader autonomy.
See Refinery's full scorecard →
One tool worth testing
GitHub Copilot — GitHub Copilot is the tool to test if you need a coding agent that can sit inside a real workflow, not just autocomplete. Today’s site change adds native MCP server integration and expands custom and third-party agent support, which is a meaningful step toward tool-connected execution. Run a 30-minute pilot against your current coding assistant on one repo task that needs external context or actions, and see whether Copilot can traverse the same steps with less manual glue.
Our pick: ChatGPT Deep Research
The use case: research & deep analysis.
Tops our independent /36 — strongest on autonomy and planning, ahead of Gemini Deep Research. Pricing: Subscription (quotas undisclosed).
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 →
|