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.
6 entries matching filters
Security / enterprise
LiteLLM shipped its August updates featuring a new public test-status dashboard, 1-click deploy templates for the Auto-Router, and context-aware routing that reads recent conversation turns. The release also includes extensive security hardening, such as PII and PCI masking in logs and strict caller-credential enforcement for MCP tool calls.
Platform admins gain deeper visibility into release stability and tighter security controls for enterprise data privacy. The Auto-Router enhancements significantly lower the barrier to deploying cost-optimized, multi-model agent architectures.
MCP / tool calling / API
LiteLLM released version 1.96.0, introducing MCP entitlements that enforce access controls across key, team, agent, and organization scopes for tool listing and calling. The update also adds a post-call guardrail mode to mask or reject MCP tool results, implements Redis-based configuration synchronization, and adds support for OpenAI's GPT-5.
Platform teams can now enforce strict, granular access controls and guardrails on MCP tools, ensuring agents only access permitted tools and sensitive tool outputs are masked. The shift to Redis-based config invalidation also improves operational reliability by propagating changes instantly across deployments.
Agent capability
LiteLLM released version 1.94.0, introducing router plugins configurable via proxy YAML and Auto-Router v2 featuring a soft-floor adaptive mode and session affinity. The update also adds interactive SSO sign-in for Model Context Protocol (MCP) client credentials, a unified DataTable UI for resource management, and a beta Cost Optimization dashboard.
Engineering teams gain programmatic control over model routing logic and enhanced security for handling MCP tool credentials. The new Cost Optimization dashboard provides visibility into API spending by tool and cache efficiency to help control infrastructure costs.
Integrations
LiteLLM added Day 0 support for Anthropic's Claude Opus 5 model across its integrations with Anthropic, Azure, Vertex AI, and Bedrock. The update natively supports Opus 5 features including Fast mode, adaptive thinking, prompt caching, tool calling, and computer use.
Teams can immediately upgrade to Anthropic's latest frontier model via a simple configuration change without altering application code. Supporting Opus 5 across multiple cloud backends allows organizations to balance rate limits and cloud spend while using the new capabilities.
Security / enterprise
LiteLLM launched an early beta of its AI Gateway completely rewritten in Rust, along with a new AIGatewayBench testing tool. The Rust gateway reduces per-request latency overhead to 0.7ms at p99 and lowers peak memory consumption to 21.8MB.
Enterprise teams processing high-throughput LLM traffic can lower their infrastructure costs and reduce memory-related crash risks. The sub-millisecond overhead specifically accelerates fast-loop applications like autonomous coding agents.
Agent capability
LiteLLM introduced Router Plugins, enabling users to configure and chain custom plugin pipelines to determine which model processes a given input.
Platform engineering teams gain granular, programmatic control over model routing logic. This facilitates customized cost optimization, dynamic failover strategies, and compliance checks before requests are sent to an upstream provider.
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