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
Agent capability
OpenAI released a major update to the Codex app, introducing direct Markdown and code editing, inline annotations, and cross-repository project support. The release also adds native GitHub pull request reviews in the sidebar and upgrades the Computer Use capability to leverage the faster GPT-5.6 model.
These additions significantly reduce context switching by bringing PR reviews and multi-repository workflows directly into the Codex environment. The upgrade to GPT-5.6 for Computer Use also promises faster and more reliable automated GUI interactions for testing and native app workflows.
Deployment / data residency
OpenAI launched a desktop application for Linux that includes native support for Codex. The release brings Codex capabilities directly to supported Linux distributions, including Ubuntu, Debian, and Fedora.
Engineering teams using Linux environments can now access Codex natively on their desktops. This streamlines local development workflows by reducing reliance on the web interface or CLI.
Pricing / packaging
OpenAI reduced the pricing for its GPT-5.6 Terra and Luna models and announced that GPT-5.4 and GPT-5.4 mini will be retired from Codex on August 31, 2026. Users must migrate their workspace defaults, saved model settings, and custom agents to the GPT-5.6 models before the cutoff.
IT administrators and developers must proactively update managed configurations to avoid service disruptions when the GPT-5.4 models are retired. The price reductions on the newer GPT-5.6 tier provide a cost efficiency incentive for the mandatory migration.
Browser/computer use
OpenAI shipped version 26.727 of the ChatGPT and Codex desktop app, adding an improved built-in browser with address-bar search and enhanced Chrome extension integration. The update also introduces multi-repository code review and an expanded viewer for generated images.
Developers can blend web research, open Chrome tabs, and local cross-repository code diffs within a single task without switching contexts. Enterprise security teams should evaluate this expanded integration surface, as browsing history and multi-repo code are now merged into the agent's memory.
MCP / tool calling / API
OpenAI released Codex CLI version 0.146.0, introducing Agent Plugins 1.0 for portable Model Context Protocol (MCP) servers, remote Code Mode over WebSocket, and custom-provider web search routing. The release also stabilizes proxy routing across authentication and plugin downloads.
Engineering teams can cleanly separate the agent's user interface from its execution environment using remote Code Mode. The stabilized proxy routing ensures enterprise compliance, allowing organizations to securely deploy Codex within strict network boundaries.
Human approval / guardrails
Codex CLI v0.142.0 added configurable rollout token budgets that track usage across agent threads and abort a turn when the budget is exhausted, plus an indexed web-search mode that restricts direct page access to server-approved URLs. The release also reorganized the plugin system into Curated, Workspace, and Shared sections.
Hard token budgets and an allowlisted web-access mode give operators concrete spend and controls over autonomous runs. These are the guardrails enterprises typically require before letting coding agents run unattended.
Browser/computer use
Codex added Record and Replay: the agent observes a demonstrated screen workflow on macOS and turns the recorded sequence of browser or file tasks into a reusable executable skill.
Shifts automation from heavy prompting to visual demonstration, lowering the barrier to automating repetitive work. Teams build reliable automations for routine operational tasks without writing scripts.
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