The pgEdge AI DBA Workbench is 4 companies on a shared Postgres datastore: a collector, a server, an alerter, and a React shopper that renders the dashboards and the chat panel the place Ellie lives. Ellie is an agentic loop that drives any LLM you select (Claude, ChatGPT, Ollama, or something OpenAI-compatible) by way of a set set of database-aware instrument calls. The mannequin by no means queries Postgres immediately, which is somewhat the purpose. Anomaly detection runs three tiers: z-score baselines, pgvector similarity in opposition to historic patterns, and LLM escalation for the residual circumstances. Supply on GitHub below the PostgreSQL Licence.
The Workbench is 4 Go and TypeScript companies: The collector daemon connects to every monitored occasion and pulls dozens of metric probes masking pg_stat_statements, pg_stat_activity, replication state, and OS-level useful resource utilization. Every probe writes to a devoted time-series desk listed on connection_id and collection_time, with cadence configurable per scope.
The server exposes a JSON-RPC 2.0 MCP and REST endpoints over HTTPS and brokers each interplay between the LLM and your databases. The alerter runs anomaly detection and threshold analysis. The shopper is a React SPA.
Ellie is an agentic loop applied within the shopper that talks to a configurable LLM backend by way of the server. We at present assist Claude, ChatGPT, and native Ollama fashions, in addition to different suppliers with an OpenAI suitable API similar to LM Studio or EXO. The selection of mannequin issues lower than individuals are likely to assume as a result of the LLM by no means queries your database immediately. As an alternative, it returns instrument calls that the shopper dispatches to /api/v1/instruments/execute, and the server executes them below the caller’s bearer token in opposition to per-token connection swimming pools in order that no two customers share state.
The identical agentic loop drives the AI Evaluation button on each chart, alert, and dashboard panel. Clicking it runs a one-shot model of the loop, seeded with the panel’s knowledge, time vary, server context, and timeline occasions in that window; the outcome drops right into a modal you may learn or obtain as Markdown, no dialog wanted.
GitLab introduced managed GitLab providing on Google Cloud
The providing is delivered by way of GitLab-certified managed service suppliers, enabling organizations to deploy GitLab in safe, sovereign environments whereas sustaining larger management over infrastructure and compliance necessities.
“We’re within the agentic engineering period, and it’s by no means been simpler and sooner to generate code. That pace brings with it a stage of chaos that enterprises can’t afford,” stated Manav Khurana, chief product and advertising officer at GitLab. “Reliability incidents, unpredictable spend, and compliance publicity in agent actions gradual organizations down after they transfer quick with out the controls they require. GitLab is the platform the place enterprises already construct and ship software program, which implies we sit on the intersection of each human and agent workflow touching code, pipelines, or manufacturing. With these new capabilities, GitLab is the agentic infrastructure that turns the pace of agentic coding into ruled, auditable software program supply at enterprise scale.”
The important thing factors of the information are:
- Subsequent Era Supply Code Administration, now in non-public beta, replaces repository clones with structured API entry to mission intelligence, delivering as much as 50x sooner process execution per agent.
- GitLab Orbit, now in public beta, is a context graph for the whole software program lifecycle that permits brokers to ship 11x sooner responses requiring as much as 4.5x fewer tokens.
- Governance for Brokers, now in non-public beta, provides new AI auditing and management capabilities to fulfill compliance necessities.
- GitLab Flex is one annual dedication that covers platform seats, GitLab Credit, and new eligible capabilities as they turn out to be accessible, with month-to-month reservations that may be reshaped with no contract modification.
- GitLab and Google Cloud go-to-market groups are working with licensed managed service suppliers, together with Past and Digital Future, to assist enterprises transfer to a scalable, dependable DevSecOps structure on GitLab and Google Cloud. Additionally, the most recent variations of Google’s Gemini fashions, together with Gemini 3.5, are actually accessible in GitLab Duo Agent Platform, and Google’s Gemma fashions, together with Gemma 4, are actually accessible for GitLab Duo Self-Hosted clients.
