PhoenixAI, the original creator of StarRocks and the agentic AI database company, today launched Contextbase, the context infrastructure for AI agents. Company is unveiling it at NEXT QUERY 2026, its Data + AI Infrastructure Summit. Contextbase stores semantics, knowledge, memory, traces, and evaluations as context in one system so agents understand, reason, and act better with every run.
An agent only knows what is in its context. What data means, what business knows, what earlier runs learned, what this run did and whether it worked all reach agent as context or not at all. In most stacks today those pieces live in separate tools: definitions in semantic layer, documents in vector store, memory in memory service, and traces and evaluations in observability tools. Each keeps own copy and own permissions.
Contextbase holds all of it in one place. Semantic views of entities, dimensions and metrics defined by business in Semantic SQL. Typed, versioned knowledge records such as spec, incident review or playbook linked to each other. Memory that agents write from earlier work. Traces of every model call and tool call in run with prompts, outputs, tokens and cost. And evaluations from test datasets and eval runs to scores on live traffic.
"An agent is only as good as its context, and today it has to glue that context together from separate systems on every turn. What it gets is partial, inconsistent and often stale," said James Li, co-founder and CEO of PhoenixAI. "Context is next great infrastructure layer, and it belongs in one real-time system where it compounds. Every run makes it better, and every agent you ship makes next one smarter. That's flywheel Contextbase starts."
Contextbase built into PhoenixAI database so context lives on same cluster as business data and one query can reach all of it under one set of permissions. Everything in it linked, versioned, governed and directly readable by agents. Agent is non-deterministic part of system so place it reads from built to be steady: definitions verified, system enforces policies, records kept as written.
PhoenixAI building applications on Contextbase starting with ObserveStack for tracing and evaluating agents so teams can see what each run did and score whether it worked using same store their agents read from.
About PhoenixAI
PhoenixAI is Agentic AI Database purpose-built to give autonomous AI agents sub-second access to live enterprise data at massive scale. Platform unifies real-time and at-rest data in single AI-native engine combining speed and concurrency that agentic workloads demand with governance and deployment flexibility enterprises require. PhoenixAI runs in customer's own cloud account or self-managed on own private cloud or on own hardware including on-premises. Formerly CelerData and creators of StarRocks open source project headquartered in Menlo Park California.
