Agentic Index
Agentic AI Platform Change Log
Agentic Index tracks material changes across agentic AI platforms, including new agent capabilities, workflow orchestration updates, integrations, MCP/tool-calling changes, memory features, human approval controls, observability, deployment options, pricing, funding, and verification-status updates. This change log is the index that tracks changes to agentic AI platforms, updated weekly. If you are trying to keep up with changes to AI agent platforms without reading every vendor's release notes separately, this is the feed to read.
Public-source research. All entries are sourced from official vendor blogs, changelogs, documentation, or press materials. Support levels marked Needs Review or Publicly Claimed should be independently verified before relying on them for procurement decisions.
7 entries matching filters
Integrations
JetBrains updated its AI Assistant to natively integrate Claude Agent, powered by Anthropic's Agent SDK, directly into the IDE chat. The release also adds new spend management features, enabling users to track quota consumption and top up AI credits from within the interface.
Users can now leverage Claude's agentic capabilities as part of their existing JetBrains AI subscription without needing separate API keys. The built-in quota tracking provides organizations with better visibility and control over their AI usage costs.
Integrations
JetBrains expanded its AI ecosystem by adding support for Junie, the JetBrains AI coding agent, to ReSharper 2026.2. This integration utilizes the Agent Client Protocol (ACP) to bring agentic coding capabilities directly into the ReSharper environment.
.NET developers using ReSharper can now leverage JetBrains' native AI coding agent for automated task execution and code generation. This broadens the reach of JetBrains AI across its product suite and offers a more unified AI experience.
MCP / tool calling / API
JetBrains Air, the agentic development environment, received an update adding support for multiple ACP (Agent Client Protocol) agents, including GitHub Copilot, OpenCode, Pi, and Cline. The release also introduces Java and Kotlin IDE intelligence and the ability to run Windows tasks in Docker.
Developers can now utilize a wider array of third-party coding agents within the JetBrains Air environment without being locked into a single AI provider. The addition of Java and Kotlin intelligence also enhances the contextual accuracy of agents working on JVM-based projects.
Memory / state
JetBrains launched JetBrains Context, a repository intelligence layer that incrementally builds a semantic index of codebases for coding agents like Claude Code, OpenAI Codex, and JetBrains Junie. It enables multi-repo search and semantic retrieval, allowing agents to query related concepts instead of relying on repeated keyword searches.
Engineering teams utilizing AI coding agents can reduce execution latency and API costs by giving their tools direct semantic access to large codebases. By avoiding repetitive file exploration, agents can more efficiently validate APIs and dependencies across an organization's entire repository landscape.
Agent capability
JetBrains open-sourced Mellum2, a 12B parameter model engineered specifically for routing, Q&A, sub-agents, and private AI use in software engineering systems. The model is designed to optimize latency, throughput, and cost for production AI workflows.
Organizations requiring strict data residency or looking to reduce API costs can deploy this open-source model locally for their software engineering agents. It provides a specialized alternative to general-purpose cloud LLMs for powering private development assistants.
MCP / tool calling / API
JetBrains introduced new AI agent capabilities as part of its 2026.2 IDE release wave. The update adds an Agent Skills manager in IntelliJ IDEA for handling custom AI instructions, as well as three new database-focused agent skills in DataGrip powered by the Model Context Protocol (MCP). The 2026.2 release also brings native GitHub Copilot integration and AI completion support for third-party model providers.
Development teams can now extend their JetBrains AI agents with reusable domain knowledge and connect them directly to databases for automated querying and schema management. Support for MCP tools and third-party model providers gives organizations greater flexibility to customize their AI stack while maintaining CLI consent controls for database operations.
Agent capability
JetBrains made Codex (on GPT-5.4-mini) the recommended default agent in JetBrains AI Chat across JVM, .NET, and Python, after internal benchmarking against Junie and Claude Agent on solve rate, cost, and latency.
A vendor-chosen default removes the friction of manual model selection and sets a predictable performance and cost baseline for teams standardizing on JetBrains agents.
Current rankings
These changes feed the index. See where each category stands: the best vendors of 2026, ranked by verified capability coverage.
Capability coverage
Every change above is graded against the same 14 capability axes. Each axis has its own page showing how much of the index documents it, which categories concentrate it, and the leading platform in each.
The AI agent directory for business · The full feature taxonomy · Pricing research
Common questions
How do I keep up with changes to AI agent platforms?
Read one maintained change log instead of tracking each vendor's release notes separately. The Agentic Index change log records 981 verified updates across agentic AI platforms, updated weekly, covering new agent capabilities, MCP and tool calling changes, memory, human approval controls, observability, deployment options, pricing and funding. Every entry names the vendor, the date, the change type and an impact level, and links to that vendor's profile.
How often is the agentic AI change log updated?
Weekly. The most recent update was Sep 4, 2026, covering LivePerson, Serval, ServiceNow.
How do I track changes for one specific AI agent vendor?
Filter the change log by vendor, or open that vendor's profile page, where the same verified entries appear alongside its capability coverage across the 14 point Agentic Index taxonomy.
Where can I find a single feed of agentic AI platform updates?
This page is that feed. Agentic Index reviews vendor blogs, changelogs, documentation and press materials every week and files what materially changed, so keeping up with changes to AI agent platforms is one page rather than several hundred. Entries are filterable by vendor, change type, impact level and verification status, and each one carries the evidence basis it was graded from.
Last updated: Sep 4, 2026 · 981 tracked changes across 372 vendors