LoginSign Up
← Back to all sparks
A

Agno

DEVOPS
Velocity10.0

Agno keeps building the operations layer around its agents, not just the agents.

agentosobservabilitydurable-stateprovider-integrationsproduction-readiness
◆Current state
Agno is an agent framework that spent this window shipping the surfaces a deployment needs rather than new agent abstractions: aggregate latency and error stats in traces, a status endpoint for background metrics refreshes, a durable FileSystem that survives process restarts, and AgentOSTools, which lets an agent read its own platform's traces. Provider work continues in parallel — Smallest AI text-to-speech, OpenSearch as a vector store, Moonshot thinking toggles and multimodal input. The newest release moves in a different direction, adding followup suggestions an agent hands back to its user at the end of a response.
◆Where it's heading
The centre of gravity is AgentOS. Most of what shipped assumes an Agno deployment that is already running, already traced, and now needs to be inspected, kept durable, and reported on. Integrations are additive and follow a consistent pattern — a toolkit or vectordb slotted in without changing what agents can do. Followup suggestions is the first entry here aimed at the person using an agent rather than the person operating one, and it is built the same way the rest is: an optional flag, a second model call, a field on the response.
◆Prediction
Expect the AgentOS surface to keep widening — the ops toolkit reads from the database today, so a live handle or write-capable operations are the obvious next step. Whether followup suggestions signals a broader end-user layer or is a one-off convenience is not clear from these entries.

◆Recent moves

  1. 7d ago

    Followup suggestions in Agno: give users their next question

    Setting followups=True on an Agent or Team returns ready-to-run next prompts on response.followups, generated by a second model call after the main response. It is the first thing in this window built for the end user of an agent rather than its operator, but the mechanism is the same optional-flag pattern the rest of the release notes follow.

  2. 20d ago

    Run knowledge search on OpenSearch, with hybrid built in

    OpenSearch joins the supported vector stores with vector, keyword and hybrid search in sync and async form. The argument is consolidation: teams already running OpenSearch for logs can back a knowledge base with it instead of standing up a second store.

  3. 20d ago

    Give your agents a voice with Smallest AI

    SmallestTools adds text-to-speech through Smallest AI's Lightning models, running on Agno's own HTTP client so there is nothing extra to install. Another provider slotted into the toolkit surface rather than a change in what agents can do.

  4. 20d ago

    Poll the status of background metrics refreshes

    Adds a way to poll whether a background metrics refresh has finished. Plumbing for a job that already ran on its own schedule.

  5. 23d ago

    Ask your AgentOS how it's doing, in plain English

    ⚡ SPARK

    The platform becomes something an agent can interrogate about itself, which is a different posture than shipping a dashboard for humans to read.

  6. 23d ago

    Break down agent latency and errors in your traces

    Traces gain a breakdown of where latency and errors accumulate across an agent run. Useful once runs are long enough that a single duration number stops explaining anything.