Recursant – an open source mesh platform for governing AI agents

Hello,

I have just released Recursant to the public. I have been working on it for a while. It is a control plane for governing AI agents across stacks. It provides full observability, guardrails, and control on the network level by routing all traffic through a side car.

Problem statement: many large, regulated enterprises (think banks, telcos) have one engineering team on LangGraph, another on CrewAI, marketing on AgentForce, and data teams on Databricks Agent Bricks. They need their agents to talk to each other with consistent policy enforcement, one audit trail, and a single set of guardrails, yet allowing different functions to run on their own stacks. Recursant solves that problem using the service mesh pattern

Recursant has two components: a registry and the mesh . The registry contains all live agents. The mesh uses sidecars to route traffic and enforce on the network layer.

Aim is for Recursant to provide a real-time EU AI Act Annex IV compliance, so it is not generated from static documents. This saves time and effort for large enterprises subject to the requirement.

Linmitations:

- Recursant currently plugs in to CrewAI, Langgraph, and n8n . The aim is to support proprietary platforms such as ServiceNow and AgentForce as much as psosible. - The Recursant SDK still needs work to support as many agents as possible - I would also like to provide support for some of the 'personal agent' platforms such as OpenClaw, NanoClaw, and Hermes - Only tested on k8s, not public cloud - Documentation is sparse and needs to be developed.

I hope this project is useful to some of you.