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.
11 entries matching filters
Agent capability
Kilo Desktop, available to download now, is a desktop app that runs the same agent engine as the Kilo CLI and VS Code extension. It adds workspaces that group several folders, agents that plan before they build, agent editing of Python notebooks, and built in management of local models and conda environments.
Teams that mix application code and data science get one agent client that works in notebooks and can run open models on local hardware so prompts stay on the machine.
Workflow orchestration
Several Kilo cloud agent chats can now work on the same branch at once, each with its own context, so one can plan while another implements. Each session also gets a diff viewer where line comments are gathered into a review and sent back to the chosen chat.
Teams can split planning, building and fixes across parallel agents on shared code and send precise corrections without pulling the branch locally.
Workflow orchestration
Kilo Code CLI 7.7.9 added a goal tool that lets the agent start or resume a session goal and continue execution after the current turn. The tool is allowed by default, with ask and deny permission options. The same release added recurring or single session schedules through cron_create, cron_list, and cron_delete; tasks survive session resumption and expire after seven days.
Engineering teams can assess unattended coding work with explicit controls over whether an agent may initiate continued execution. The default permission policy becomes a rollout decision for teams that require human oversight.
Workflow orchestration
Kilo's mobile app now lets users run cloud agents, control VS Code and CLI sessions, and review pull requests from iOS and Android.
Supervising agents from a phone keeps work moving, and it also means approving changes on a small screen. Teams should decide what can be approved from mobile.
Workflow orchestration
Kilo updated its VS Code extension with Swarm, which lets subagents message each other, plus browser use so the agent can drive a web browser, and GitHub reviews inside the editor.
Subagents that talk to each other can split larger tasks, and they can also multiply cost and errors. Teams should watch how Swarm reports what each subagent did.
Pricing / packaging
Kilo Code Teams and Enterprise editions are now available as SaaS subscriptions on the AWS Marketplace.
Organizations can streamline procurement by billing Kilo Code seats directly to their existing AWS accounts, leveraging pre-approved vendor contracts.
Security / enterprise
Kilo Code disclosed a security incident involving its business intelligence provider, Metabase, which impacted Kilo Code customer data. The company was notified of the breach on August 6, 2026, and subsequently alerted its users.
Enterprise buyers and security teams must account for third-party supply chain risks and evaluate how Kilo Code manages customer data exposure during vendor breaches.
Integrations
Kilo Code released version 7.0.7 of its JetBrains plugin to add native support for custom OpenAI-compatible model providers. The release also improves setup validation, error dialog handling, and provider disconnection workflows.
Development teams using JetBrains IDEs can now connect to self-hosted models or corporate proxy endpoints that conform to the OpenAI API specification. This ensures feature parity with the VS Code extension and expands local deployment flexibility.
Security / enterprise
Kilo Code added network restriction enforcement for sandboxed agent commands running on Linux environments. The update blocks unauthorized network access across TCP, UDP, IPv4, IPv6, and descendant processes, while giving administrators the ability to whitelist specific external network destinations.
Security and IT teams can confidently deploy the agent in locked-down or isolated environments by tightly controlling its network egress. This mitigates the risk of unauthorized data exfiltration or unintended API calls during autonomous execution.
Funding / partnership
Anaconda acquired Kilo Code to integrate its open-source agentic engineering capabilities directly into the Anaconda Platform. Kilo Code will remain free and open-source for individual builders, while Anaconda focuses on adding enterprise-grade governance, intelligent agent routing, and centralized monitoring for organizational users.
Enterprise buyers can deploy Kilo Code within Anaconda's secure infrastructure to gain centralized visibility over AI development activity and token costs. Existing users and independent developers face no workflow disruption and retain full model-agnostic flexibility.
MCP / tool calling / API
Kilo Code added dependency gating for experimental agents: the CLI blocks execution if declared skill, MCP, or VS Code extension prerequisites are missing, and the extension shows requirement groups with Marketplace shortcuts. ACP integrations moved to acp-next.
For complex agents, gating prevents mid-task failures by enforcing dependencies before a run starts. The expanded Agent Context Protocol support deepens custom tooling and telemetry integration.
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