Our own technology base
Products and libraries
Your problem is handled by the same engineers who work on these products and libraries. Balansis and Agent Native Universe are open: a numerical library where loss of precision is visible, and an agent runtime where a run can be repeated and checked. MagicBrain is open-source research. KnowledgeBaseAI builds the knowledge graph, and XTeam Agents, our agent orchestration platform, so far runs only in our lab. StudyNinja, the platform our methods run on, is in production together with the knowledge graph, so far as a closed beta. Each one carries its maturity stage, without rounding up.
In active development
Balansis
Compensated arithmetic for Python
An open library for numerically stable computation built on compensated arithmetic: loss of precision, division by zero and overflow stop corrupting a calculation silently and become a visible state. The algebra of the model is proved in Lean 4; the code is on PyPI (1.1.0, AGPL-3.0 or a commercial licence).
Research
MagicBrain
Bio-inspired network research
A line of research into bio-inspired neural networks: spiking networks and local learning. The code is open (PyPI 0.8.0) and is not used in products.
In active development
Agent Native Universe
Open agent runtime
An open-source agent runtime (MIT) in which code enforces the rules of the world, not a request in a prompt. A run can be replayed from its log to the same final event hash, byte for byte.
In active development
KnowledgeBaseAI
Knowledge graph platform
A knowledge graph engine for business and education: a domain is described as a connected model of entities and relations, and code checks the content and the diagrams. It runs the school mathematics graph in StudyNinja.
In active development
XTeam Agents
AI agent orchestration
A multi-agent framework for AI agent orchestration: an agent team is assembled from a YAML description instead of being coded for each process. So far it runs only in our lab.
In production
StudyNinja
Learning platform
A study platform for school students: a mathematics knowledge graph, gap diagnostics and the choice of the next step. It runs in production, so far as a closed beta.
Estimate the payback up front
Need something similar for your problem?
Describe it in your own words. We will work out which approach fits and tell you whether it pays off, before any work starts.
or email hello@xteam.pro