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
{
"inputs": { "Z": "tensor[m,n]" },
"ops": [
{ "op": "normalize", "x": "Z", "as": "Zn" },
{ "op": "scalarProduct", "x": "Zn", "k": 3.14159, "as": "out" }
],
"output": "out"
}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.
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.
Three ways to use Euriklis
SDK install, HTTP API curl snippet, and MCP install for Claude / ChatGPT / Codex — each with a copy-pasteable example.
Feature grid
Nine cards summarising what the platform does — from TypeScript → LLVM IR to graph analytics to neural-network inference.
Architecture & benchmarks
SVG pipeline diagram and an honest performance chart — matmul on PTX vs. NumPy CPU vs. pure JS.
Use cases
Four short cards: scientific computing, machine learning, econometrics, and graph analytics for LLM agents.
Final call to action
Big card: Ready to compile TypeScript to GPU? Primary button → Get API key; secondary → Join Discord / Star on GitHub.
Social proof
GitHub stars badge, open-source license callout, and designed slots for testimonials.