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
MCP / tool calling / API
Kiro IDE 1.0.395 adds compatibility for third-party extensions to run alongside the Kiro agent. It also supports the latest Model Context Protocol (MCP) revision for more reliable sign-in, reduces extension host crashes during large responses, and maintains agent turns during brief network interruptions.
Allowing third-party extensions removes a major adoption barrier for developers who rely on existing IDE plugins. The MCP protocol upgrades and network resilience improvements ensure more stable uninterrupted agent workflows during complex tasks.
Deployment / data residency
Kiro CLI 2.20.0 introduces managed cloud sessions, allowing developers to run the CLI in a cloud sandbox, attach repositories, and disconnect while the agent continues working. The release also adds a full-screen task execution view for V3 spec runs with real-time progress tracking and a toggle to preserve terminal scrollback history.
Cloud sessions enable teams to offload long-running autonomous agent tasks to managed infrastructure without tying up local developer machines. The enhanced execution view provides better visibility and control over complex multi-step workflows.
Agent capability
Kiro released CLI version 2.18, adding a Voice Mode that allows users to dictate prompts using on-device transcription via the /voice command. The update also introduces opt-in Cloud Sessions and a new review step for spec runs.
Voice dictation provides a hands-free alternative for describing complex workflows to the agent. The addition of a review step for spec runs introduces a critical human-in-the-loop checkpoint before execution.
Agent capability
Kiro released version 1.0.293 of its IDE, introducing Cloud Sessions to Agent Focus Mode as a preview. The update also includes a collapsible icon-only view for the sessions rail.
Developers can offload agent workloads to the cloud rather than relying solely on local compute. The updated interface helps users manage multiple parallel agent workflows more efficiently.
Agent capability
Kiro IDE version 1.0.242 adds a Kiro submenu to the editor context menu and introduces an Ask Kiro to Fix quick action for errors and warnings. The release includes a guided form for creating hooks, persists chat history across workspace folder changes, and updates the editor to Code OSS v1.108.2.
By integrating agent actions directly into the IDE context menus, developers can trigger code fixes and documentation generation with less manual effort. The guided hook creation and persistent chat history improve usability and ensure context is maintained across different project directories.
Integrations
Kiro has introduced three tiers of OpenAI's GPT-5.6 models: Sol, Terra, and Luna, across its IDE, CLI, and Web platforms. Sol acts as the flagship model for complex multi-step tasks, Terra serves as the balanced option for routine development, and Luna provides a fast, low-cost option for high-frequency workflows.
Engineering teams now have the flexibility to choose OpenAI's newest models alongside existing Anthropic options. This allows users to directly control the tradeoff between advanced reasoning capability and cost efficiency depending on the complexity of their development tasks.
Agent capability
Kiro shipped IDE 1.0. The release adds a capability-based permissions system that evaluates every file read, command execution, and MCP call against user-defined rules, prompting for consent on anything not pre-approved and persisting decisions as workspace- or global-scoped rules. Custom agents are now defined in a single Markdown file with read/write/shell/web tool-access tags, inline MCP servers, and permission rules that are shareable via version control. Also ships: experimental Agent Focus mode for directing multiple agents working in parallel, natural-language hook creation in a structured JSON format, dockable chat tabs, and session export.
The 1.0 release pairs per-action consent controls with version-controlled custom-agent definitions and a parallel-agent mode. For buyers evaluating agentic IDEs, the permission model is a concrete governance control; shareable agent definitions give teams a path to standardize behavior across a codebase.
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