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.
Follow this change log by RSS
Free for your reader, newsletter or automation tool. One feed covers the whole index, and every category has its own.
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.
6 entries matching filters
Agent capability
Harness acquired Cosmos, the Auggie CLI and the Code Context Engine from Augment Code and made Harness Cosmos available now. Its agents start from events such as ticket updates, pull requests, schedules and webhooks, and use prebuilt Experts (PR Author, Deep Reviewer, Risk Analyzer and Verifier) to take a ticket through to a reviewed pull request.
Harness now covers writing code as well as shipping it, so a buyer can run ticket to pull request agents and the deploy pipeline with one vendor's policy, approval and audit controls.
Integrations
A new Harness connector brings its delivery pipelines into ChatGPT and Codex. After signing in, the assistant can summarize pipeline runs, find and explain failed steps and, where allowed, create, change or run pipelines under the user's own Harness permissions.
Teams that work in ChatGPT or Codex can investigate and act on delivery pipelines without building their own MCP setup, with access still bound to Harness roles and per action approval.
MCP / tool calling / API
Harness MCP Server 3.2.30 adds advisory failure classification to harness_diagnose, returning a category and confidence for failed pipeline steps. With a configured TypeSafe API key, it evaluates failure messages and available log snippets against six categories covering infrastructure, tests, configuration, dependencies, permissions and timeouts. Missing credentials, errors or low confidence omit the triage field; the feature does not trigger retries or block execution.
Engineering teams can give connected agents a structured starting point for incident investigation while retaining control over remediation. Buyers should assess the transfer of failure messages and log snippets to TypeSafe; the credential configuration is rejected in multi user and OAuth modes.
Human approval / guardrails
Harness released an Agent-Ready Code Repository and AI Code Review system built to handle the increased volume of code produced by AI agents. The review layer evaluates agent-generated pull requests to identify potential risks and provides context-aware feedback for human reviewers.
Platform engineering and security teams can use this repository to govern AI coding agents at scale. It prevents the review process from becoming a bottleneck by automatically surfacing the specific risks of agent-generated changes before human approval.
Agent capability
Harness launched a suite of AI-driven security agents designed to handle vulnerability response across the software lifecycle. The release includes AI SAST, agentic triage and remediation, a dedicated Zero-Day Agent, and virtual patching capabilities.
Security and engineering teams can automate the identification, prioritization, and remediation of software vulnerabilities directly within their delivery pipelines. This reduces the manual overhead of triaging security alerts and accelerates patch deployment for critical threats.
Agent capability
Harness published its July 2026 product update, encompassing 71 new features including the Agent Development Lifecycle (DLC) and CLI 3.0. The update introduces a dedicated permission system for Worker Agents and integrates the full AI agent lifecycle into the core Harness platform.
Engineering teams can now build, deploy, and govern AI agents using the same platform they rely on for traditional software delivery. The addition of strict permission systems for Worker Agents provides necessary guardrails for secure AI automation in production environments.
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 1648 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 Oct 21, 2026, covering Equal AI, Kognitos, Findem.
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. The same entries are published as a free RSS feed at agenticindex.io/feeds/changes.xml, with one feed per ranking category listed at agenticindex.io/use-this-data.
Last updated: Oct 21, 2026 · 1648 tracked changes across 550 vendors