Search

Dual-mode Pandas and CSV filtration for ramen-ai RAG ingestion and MLOps dataset sanitization.

Website to Markdown converter with provenance frontmatter for LLM knowledge bases

模型接入层：封装 fetch → DeepSeek API

Drag and Drop with Angular

Add the ability to interact with Azure BlobStorage in your MCMA services

Add Google Cloud Storage to your MCMA services

Compiled HIP kernels for SnowLLM on AMD gfx1151 (Strix Halo)

Hand-written HIP kernels for Qwen3.6-35B-A3B on AMD gfx1151 (Strix Halo)

Convenient OpenAI-compatible LLM provider for the log-parser framework. Implements ILLMProvider using the Vercel AI SDK.

Browser-local LLM provider for the log-parser framework. Implements ILLMProvider using @mlc-ai/web-llm with WebGPU acceleration.

A universal, no-code RAG server for any vector database, built on the Pathway Live Data Framework.

Deterministic Go and Python sketches for high-cardinality LLM data.

Minimal package

Minimal package

Stochastic Portfolio Theory toolkit for quantitative finance — functionally generated portfolios, relative arbitrage, excess growth optimization.

Engine-agnostic N-fragment counterpoise (BSSE) job-spec generation and result combination for SEAMM

Real-time AsyncStorage viewer and editor for React Native — debug, inspect, search, and modify storage data from a web browser dashboard. Zero native dependencies.

Modern MDF Connect client with CLI, Python API, and Claude skill integration.

Per-model LLM latency monitoring — Prometheus exporter and Grafana dashboards for Claude, OpenAI, and Gemini. Name reservation placeholder; first real release coming soon.

Store LLM weights in a SQLite database. Query, diff, rollback, and merge — for free.