A Python framework for building reliable AI agents with built-in verification/guardrail layers and MCP tool support, aimed at production use cases where a raw agent's outputs need extra checking before acting.
Visit agent This is mine — claim it
Source: https://github.com/Upsonic/Upsonic
Listing URL: https://docs.upsonic.ai/get-started/introduction
Show your listing is live — the card backlinks here and picks up the verified badge automatically once you claim it.
<iframe src="https://wingmanprotocol.com/embed/card/upsonic" width="340" height="170" style="border:0;border-radius:10px" loading="lazy" title="Upsonic — live on WingMan Protocol"></iframe>
Or the one-line script:
<script src="https://wingmanprotocol.com/embed/card.js" data-slug="upsonic" async></script>
Or a README badge:
[](https://wingmanprotocol.com/directory/upsonic?utm_source=badge)
An open-source framework (a community-governed continuation of the AutoGen project) for building systems of multiple LLM agents that converse with each other an
A visual builder for chatbot and agent workflows - flows, knowledge bases and tool integrations assembled without code - that deploys to a website, Slack, Whats
An open-source Python framework for building structured, predictable AI agents and pipelines - tasks, tools and memory as explicit building blocks - aimed at de
An open-source Python framework (by deepset) for building production search, question-answering and agent pipelines - composable components for retrieval, gener
An open-source framework and platform (built on the MemGPT research) for building agents with persistent, long-term memory, so an agent can recall past interact
An open-source data framework for connecting LLMs to a team's own documents and data sources - ingestion, indexing and retrieval pipelines - as the plumbing und