Population-guided evolutionary research for pi — evolve hypotheses, run measured experiments, keep what works.

ATLAS — Agentic Harness Standard. ~92% fewer agent orientation tokens (measured, reproducible). Zero infrastructure. Four Markdown files every Claude/Codex/Cursor/Gemini/Zed/OpenCode/Copilot/Hermes session reads first.

bench-rest - benchmark REST (HTTP/HTTPS) API's. Node.js client module for easy load testing / benchmarking REST API' using a simple structure/DSL can create REST flows with setup and teardown and returns (measured) metrics.

Compute the cotangent of an angle measured in degrees.

Measured grounding tools for Surface audits

Make your Electron app look genuinely macOS-native: vibrancy window setup, measured sidebar & settings chrome, SF Symbols rendering.

Compute the tangent of an angle measured in degrees.

MCP server for KTRENZ K-Data — first-party measured K-pop AI-citation reach + external demand, as agent tools.

Accessible SVG renderer for measured and routed KDiagram diagrams.

Derive Chartdown feature declarations from georeferenced imagery — size=, reach=, taper= and via measured rather than remembered. Zero runtime dependencies.

Content-addressed identity, honest by construction — mint + mind, holographic merkle proofs, a reversible imprint codec, a reeducating harness, a measured billing model, pure-TypeScript ChaCha20-Poly1305 encryption under a 7d-fold envelope, and an MCP ser

Compare providers serving China's frontier models — time to first token, throughput, price and success rate, measured side by side.

Simultaneously compute the sine and cosine of an angle measured in radians on [-π/4, π/4] in single-precision floating-point format.

Compute the secant of an angle measured in degrees.

Width & height providers for React

Deterministic, LLM-free AI-drift receipts a stranger recomputes byte-for-byte: the forkable benchmark that prices agent drift (advisory premium from measured vega/breach/kurtosis), the surgeon-judgment trigger battery, day-one vega-backtest over any git l

A zero-dependency CLI for turning agent traces into measured, guarded improvements.

Let an LLM propose UPDATE/DELETE, then actually run it, measure the real before/after diff, and always roll back — so the human approves measured facts, not the model's claim.

Measured career adjacency from live job postings — which careers your skills already reach, the gap, the salary, and the honest odds.

Typed step contracts for Gherkin, so a scenario can be told wrong before it runs. The vocabulary is machine-readable for agents, and every execution leaves a step record the tool measured rather than the agent reported.