euriklis
Register
MCP ready — works with Claude, ChatGPT, Cursor, Codex

AI agents need multi-step scientific computing & statistical analysis. We give them one declaration.

Declarative computation graphs for AI tools. Compose tensor operations, statistical analyses, econometric tests, and portfolio optimization in a single MCP call. Powered by LLVM. Open source.

Install in ClaudeRead the docs

Works with Claude · ChatGPT · Codex · Cursor · Zed · Open source · Powered by LLVM

claude · euriklis.compute
User → Claude
Normalize matrix Z by L2 norm, then multiply by π.
↓ MCP tool call
Claude → euriklis.compute
{
  "inputs": { "Z": "tensor[m,n]" },
  "ops": [
    { "op": "normalize",     "x": "Z",  "as": "Zn"  },
    { "op": "scalarProduct", "x": "Zn", "k": 3.14159, "as": "out" }
  ],
  "output": "out"
}
Install in 30 seconds

Add Euriklis to your AI agent

Run this command in your terminal.

claude mcp add euriklis npx @euriklis/mcp \
  --env EURIKLIS_API_KEY=eur_free_...

Need Codex or another agent? See the full install guide on /mcp.

What it does

Every operation your agent needs,
in one API call

TypeScript → LLVM → GPU

Write plain TypeScript. The runtime compiles your computation graph to LLVM IR and dispatches to CPU or NVIDIA PTX automatically.

Declarative computation graphs

Describe a DAG of operations — tensors, matrix decompositions, statistical tests — in one JSON payload. No orchestration code.

MCP-native

First-class Model Context Protocol support. Claude, ChatGPT, Cursor, Zed and Codex can call your entire math stack through a single tool.

Linear algebra & tensor ops

LU, QR, Cholesky, eigenproblem, convolutions, pooling, norms, and 100+ matrix operations — all strictly validated before execution.

Statistics & econometrics

Box-Cox transforms, Yeo-Johnson, Gershgorin circles, and econometric tools callable from the same graph as your tensor operations.

Open-source runtime

The validator, op catalog, and CPU runtime are MIT-licensed. Paid tiers add hosted GPU execution, persistent graphs, and team workspaces.

Use cases

Built for agents doing real work

Scientific computing

From prompt to matrix inverse

An agent receives a user's covariance matrix, normalises it, factors it with Cholesky, and returns the inverse — all in one tool call with no Python subprocess.

Machine learning

Tensor pipelines as data

Describe a forward pass — Conv2D, ReLU, pooling, softmax — as a JSON DAG. Euriklis validates the shapes, fuses the ops, and dispatches to PTX on Pro.

Econometrics

Statistical tests on demand

An LLM agent runs Box-Cox normalisation, fits a regression, and tests residuals for heteroskedasticity — returned as structured JSON, no code interpreter needed.

Graph analytics

Adjacency matrices at scale

Sparse graph operations, eigenvector centrality, and spectral decompositions — expressed as computation graphs and executed at native speed.

Ready to give your agent a math stack?

Free tier — 1,000 calls a month, no credit card. Install in Claude in 30 seconds.

Get your API keyRead the docs