Kong AI Management

Kong Konnect control plane for governing agentic AI: cost attribution, session observability, registry, token vault and agent identity.

Kong · Infrastructure and inference/serving · product

Published in Feed

Overview

On November 4, 2026 Kong expanded Kong AI Management in Kong Konnect, a single control plane for configuring, governing and observing LLM, MCP and agent traffic. The additions are AI Cost Management (attributing spend to teams, users, apps and agents with budgets, showback/chargeback, caching, compression and model routing), Advanced AI Observability (full-session tracing across models, tools, agents and MCP interactions), AI Registry (governed inventory of models, agents, MCP servers and tools), Kong Token Vault (issues downstream credentials at runtime so agents do not hold them), Kong Identity for agent identity, and Kong AI Gateway 2.3. The release does not say which features are generally available or beta.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • AI Cost Management: spend attribution, budgets, showback/chargeback, savings measurement
  • Advanced AI Observability: inspect individual turns for behavior, latency, errors and cost
  • AI Registry: governed inventory of models, agents, MCP servers and tools
  • Kong Token Vault: runtime issuance of downstream credentials for agents
  • Kong Identity: consistent identity for humans, apps and agents, including on-behalf-of actions
  • Kong AI Gateway 2.3 with model and MCP traffic policy enforcement

Use cases

  • Charging AI usage back to the team or agent that incurred it
  • Controlling which MCP servers and tools agents can discover
  • Keeping long-lived credentials out of agent runtimes

Pricing

unknown; the release links to Kong's general pricing page and states no feature-level pricing or GA/beta status.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
Not listed
Record updated
8 Nov 2026
Record last checked
8 Nov 2026

Explore the Feed

Other entries filed under infrastructure and inference/serving; inclusion does not imply equivalent features.

  • NVIDIA PAIR (Personal AI Router)

    NVIDIA's free, open-source personal AI router that spreads local model workloads across PCs on your network; out of beta Oct 13, 2026.

  • Agent37

    YC F26 startup selling low-cost agent sandboxes (gVisor or full VM) with prebuilt harnesses for Claude Code, Hermes and opencode.

  • Microsoft-Decision-1

    Microsoft's Qwen3.5-9B-based decision-scoring model returns calibrated option probabilities in one pass, at $0.042 per million input tokens.

Browse the Feed