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.

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.

§1.3Scaffolded — not yet built

Live playground

Embedded TypeScript editor with tabs for LLVM IR, x86_64, ARM64, PTX, and a Run result. Rate-limited, no login required. Coming next.

§1.4Scaffolded — not yet built

Three ways to use Euriklis

SDK install, HTTP API curl snippet, and MCP install for Claude / ChatGPT / Codex — each with a copy-pasteable example.

§1.5Scaffolded — not yet built

Feature grid

Nine cards summarising what the platform does — from TypeScript → LLVM IR to graph analytics to neural-network inference.

§1.6Scaffolded — not yet built

Architecture & benchmarks

SVG pipeline diagram and an honest performance chart — matmul on PTX vs. NumPy CPU vs. pure JS.

§1.7Scaffolded — not yet built

Use cases

Four short cards: scientific computing, machine learning, econometrics, and graph analytics for LLM agents.

§1.8Scaffolded — not yet built

Social proof

GitHub stars badge, open-source license callout, and designed slots for testimonials.

§1.9Scaffolded — not yet built

Final call to action

Big card: Ready to compile TypeScript to GPU? Primary button → Get API key; secondary → Join Discord / Star on GitHub.