GitHub Copilot adds custom agents and MCP servers
GitHub Copilot rewrote its landing page around custom agents, third-party agents, MCP servers, Copilot Spaces, governance controls, and a dedicated Copilot app. Augment Code is pushing in the same direction, now centering Cosmos and a larger MCP ecosystem with updated pricing, while Kilo Code is widening into a broader platform with KiloClaw, Kilo Console beta, session forks, and one-click deploy. The common thread is clear: coding tools are no longer pitching a single assistant, but a governed platform that can plug into the rest of the stack, so operators should check which one can actually fit their workflow and controls.
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.
|
17/36 · Adaptive Collaborator
Augment Code expands into Cosmos and MCP tooling, with pricing updated — Augment Code’s site now centers on Cosmos and a large Model Context Protocol ecosystem, with new MCP registry content and updated product messaging.
Source: the tool's own site — detected 2026-07-19 by agentic.ai's daily recrawl.
|
|
15/36 · Adaptive Collaborator
Kilo Code expands into a broader Kilo platform with new products, features… — Kilo Code’s site now highlights several new platform capabilities, including KiloClaw, Kilo Console beta, session forks, one-click deploy, JetBrains autocomplete, and expanded integrations like Slack, Gateway, Code Reviewer, and Gastown.
Source: the tool's own site — detected 2026-07-19 by agentic.ai's daily recrawl.
|
|
9/36 · Guided Assistant
CrePal updates pricing page with new credit tiers, team plan, and billing… — CrePal’s pricing page now highlights updated credit-package tiers, monthly/yearly plan comparisons, a Team offering, and expanded billing/refund/commercial-use details.
Source: the tool's own site — detected 2026-07-20 by agentic.ai's daily recrawl.
|
|
7/36 · Guided Assistant
Sudowrite highlights Muse 1.5 fiction model and novel-aware chat on homepage — Sudowrite’s homepage now prominently promotes a new Muse 1.5 model for fiction plus a chat experience built around story context. The page also emphasizes expanded drafting/editing capabilities like Describe, Story Bible, Write, and Expand.
Source: the tool's own site — detected 2026-07-20 by agentic.ai's daily recrawl.
|
|
7/36 · Guided Assistant
Otter.ai adds Chrome extension and Claude MCP integration to its integrations… — Otter.ai’s integrations pages now surface a Chrome extension quick-start and a Claude integration that connects meeting transcripts and action items via MCP, indicating broader platform support for AI assistants and browser-based capture.
Source: the tool's own site — detected 2026-07-20 by agentic.ai's daily recrawl.
|
|
19/36 · Domain Specialist
GitHub Copilot highlights custom agents, MCP servers, and a Copilot app… — The Copilot landing page was rewritten to emphasize broader agent workflows, including third-party agents, custom MCP servers, Copilot Spaces, governance controls, and a dedicated Copilot app.
Source: the tool's own site — detected 2026-07-19 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.
|
social.plus
product launch
social.plus launched Vise on July 14, 2026 as a governance layer for AI-assisted SDK integration. The company says the tool turns a build that compiles into a checked record a reviewer can verify. For those tracking agentic AI product launches, this addresses one of the biggest blockers for autonomous coding systems: proof that the work actually works. The useful twist is that Vise focuses on trust evidence, not just code generation speed.
Via Agentic-News.ai — WBOC TV-16. Read: https://www.wboc.com/online_features/press_releases/social-plus-launches-vise-workflow-governance-for-ai-coding-agents-building-sdk-integrations-with-social/article_59fc96f9-7926-5ab0-a209-fc925158baa9.html
|
|
InstaLILY AI
product launch
InstaLILY AI has announced a $60 million Series B round led by Energize Capital, with participation from Insight Partners and new strategic investors. The company also launched Lily, which it calls the world's first AI Forward Deployed Engineer. For those tracking agentic AI, this combines fresh capital with a product aimed at real workflow execution across several industries. The standout detail is the claim that Lily is already tied to 5x revenue growth.
Via Agentic-News.ai — FinanzNachrichten.de. Read: https://www.finanznachrichten.de/nachrichten-2026-07/69023207-instalily-raises-dollar-60-million-series-b-and-launches-lily-the-world-s-first-ai-forward-deployed-engineer-200.htm
|
|
Markifact
product launch
Markifact launched a Google Ads MCP server that connects campaign data with Claude, ChatGPT, Cursor, and other MCP-compatible assistants. The service lets marketers analyze performance and manage campaigns while keeping human approval on account changes. For those tracking agentic AI products, this is a concrete sign that tool-using assistants are moving into paid ad workflows. The catch is that the agents can act, but the user still has the final say before anything changes live.
Via Agentic-News.ai — Barchart.com. Read: https://www.barchart.com/story/news/3256395/markifact-launches-google-ads-mcp-server-for-claude-and-chatgpt-with-human-approved-changes
|
Biggest movers this week
Listings with the largest week-over-week jump in outbound-click interest
- OpenHands · +6.3% week-over-week. 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).
- Cursor · +3.1% week-over-week. 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.
Biggest declines this week
Listings with the largest week-over-week drop in outbound-click interest
- v0 · -28% week-over-week. v0 helps you design, iterate, and scale full-stack web apps with a collaborative AI interface. It starts from prompts, templates, and attachments, then lets you keep refining the result in the browser.
- CorvinOS · -16.7% week-over-week. CorvinOS is an open-source AI operating system for teams that need pluggable engines, audited workflows, and compliance controls. It combines browser-based chat, voice and messaging bridges, data connectors, and multi-step orchestration in one platform.
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.
- Windsurf · 19/36 · Domain Specialist · L3
Windsurf Editor is an AI-powered IDE for developers that blends chat, autocomplete, and agentic code actions into the editor itself. It’s available for Mac, Windows, and Linux, and is aimed at speeding up day-to-day coding work on real codebases.
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.
Codex CLI is OpenAI’s coding agent that runs on your computer from the terminal. It can also be used in VS Code, Cursor, Windsurf, or as a desktop app.
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.
- "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"
- "self-hosted open-source AI agents I can run locally"
Learn: MCP (Model Context Protocol)
MCP is a shared plug standard for agents. Instead of building a custom connector for every file system, database, or API, you expose each one in a common format and the agent can talk to it the same way each time. Think of it like USB-C for software connections. A support agent, for example, could use one MCP server to read tickets from a database, another to pull a customer’s files from cloud storage, and a third to create a Jira issue. Without MCP, each link needs its own hand-built integration. With MCP, the agent still needs access rules and setup, but the connection pattern is the same across tools.
What agentic AI actually means →
One tool worth testing
Today's signal didn't produce a clear single-tool pick worth a test session. Tomorrow's read picks it back up.
Our pick: Claude Code
The use case: coding agents.
Tops our independent /36 — strongest on action and autonomy, narrowly ahead of Cursor. Subscription.
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 →
|