Built at Agno

Agno is an agent platform that runs in your own cloud: the SDK to build agents, AgentOS to run them. These are the parts I built.

How a production agent comes together on Agno - highlighted where most of my work sits.

AgentOS - where agents meet people

The runtime: chat interfaces, approvals, web frontends and access control.

Slack, Telegram and WhatsApp interfaces - streaming replies, media, live progress - so agents live where teams already talk.

Agents pause, people approve. Approval flows in Slack and in web frontends, for single agents and teams.

Started Agno's integration with the AG-UI protocol, connecting agents to live frontends with frontend tools.

Every user only sees their own sessions, memories and traces, permissions follow the resource, and agents only get the tools their role needs.

Context, memory, knowledge, integrations and models.

Gmail, Calendar and Drive toolkits on one shared auth layer - user sign-in or service accounts, with encrypted token storage.

Keeping long-running agents fast and on-task: compressed tool results, selective tool history, token counting and context providers.

Agents that get better every run: learning stores for users, sessions, entities and shared knowledge - for single agents and teams.

A dedicated Excel reader so agents can answer questions over spreadsheets - right sheets, right rows, with context intact.

Making agents and coding tools work together: reliable MCP results in Claude Code, docs that agents can read, and MCP-backed web research.

Kept agents working across OpenAI, Anthropic, Gemini, Bedrock, vLLM and more - including the hard concurrency bugs.

Keeping a fast-moving open-source codebase reliable.

An automated AI code-review system for every pull request, and a faster, more trustworthy test suite.