AI product Open source

HexStellar

HexStellar is an agent-first computational platform whose Cortex service executes structured optimization, decision, scientific-computing, and verification requests through a Python CLI and API. An agent submits a JSON formulation for problems such as QUBO/Ising optimization, maximum cut, traveling-salesperson routing, facility assignment, mixed-integer optimization, selection, ranking, scheduling, coloring, and business-rule feasibility; the managed service returns a structured result with execution metadata, a receipt, and an assurance label distinguishing certified optima, heuristics, operations, and abstentions. The CLI also provides free validation, estimation, service re-checks, local witness recomputation for supported families, reproducible seeds and model versions, batch and compressed-binary transport, and an MCP server over standard input/output, with read-only mode for free analysis and verification tools. The public package is a zero-dependency Python thin client: the proprietary solver runs on HexStellar-managed infrastructure rather than inside the package. A separate enterprise runtime is licensed for compatible customer-controlled compute paths under NDA; it has no public runtime download in version 1.0.

View repository Visit site Mentioned in 2 videos ↓

What HexStellar is used for

2 uses taken from transcripts — each links to the moment in the video.

  • Provides AI agents with a solver for optimization problems such as traveling salesman, graph coloring, scheduling, and portfolio allocation. Results are labeled as certified optima or heuristics and it runs as an MCP server.

  • A Python CLI and API client that lets AI agents submit difficult combinatorial and mixed-integer optimization problems to the managed Cortex solving service. It validates requests, estimates costs, returns solutions with certainty labels, and integrates with agent frameworks through MCP and tool specifications.

Videos mentioning HexStellar

2 in the library.