Automation tailored to a process
A multi-agent build for the client’s specific process, without rewriting code for every task.
Agent orchestration · YAML → LangGraph
xteam-agents Active Development
Assembling multi-agent automation from YAML specifications without rewriting code: the specification produces the graph and the agent topology.
The problem
Multi-agent automation for a specific process is expensive to build and change if every edit means rewriting code.
Why existing solutions fail
Hard-coded pipelines do not carry over to a new process without rework; the topology cannot be changed declaratively.
How it works
YAML specification → LangGraph graph → Mermaid topology; an agent registry queried by role and capability. We show the topology and the names; the routing heuristics are not disclosed.
Demo
Technology
- Python
- LangGraph
- YAML
- Mermaid
Use cases
Declarative topology
The agent topology changes by editing YAML, not code — the process carries over to a new environment declaratively.
Evidence
YAML → LangGraph graph → Mermaid topology + a registry of 29 agents
A working graph is built from the specification and the topology is rendered; a registry of 29 agents queried by role and capability. We show the topology and the names.
Reproduce: graph_builder.build(spec) → Mermaid
Green test run: 197 passed
A snapshot of a run at a pinned revision: 197 passed with the known non-green tests excluded — an honest boundary of maturity, not “everything is green”.
Reproduce: pytest
Integration
Agent topologies are described in YAML and assembled into a working graph for the client’s process.
Cost the effect on your own figures
AVA is a process-economics calculator. In a couple of minutes it shows whether this pays off in your case — before any call, with no commitment.
Estimate with AVALet us look at your task
Tell us what needs solving. If it cannot be solved or will not pay off, we will say so up front, before any work starts.
or write to us directly: hello@xteam.pro