Search

Python SDK for the SD Attention Server (SAS). Streams microphone and webcam to the inference server and emits typed events for predictions, VAD, conversation state, and speech audio ready for downstream LLM use.

A reusable RAG core library built on FAISS and Ollama

Share-conscious HTML exporter for AI coding-assistant conversations (Claude and Codex).

tfo2kc: Terraform/Terragrunt/openTofu Output 2 KubeConfig: CLI to merge kubeconfig obtained from TF output as string into ~/.kube/config

Self-hosted Telegram budgeting assistant with envelope-budget discipline. Local data, your own Anthropic key (or local Ollama).

Respan instrumentation plugin for CrewAI

Pure Storage module for the utilization in Cambridge University

A domain-agnostic adaptive query router for RAG systems. Routes queries using multi-signal retrieval score analysis, not vocabularies.

Preflight checks for LLM prototypes.

AgentIC — Autonomous AI-Driven Chip Design: Natural Language to GDSII (npm wrapper)

A python based SDK developed for interacting with Ostium, a leveraged trading application for trading currencies, commodities, indices, crypto and more.

Highly Parallel CoPy / HPC coPy: A simple script optimized for distributed file store / NVMe / SSD storage medias for use in High Performace Computing environments.

Global Infinite Memory Framework para LLMs.

Global Infinite Memory Framework para LLMs.

Placeholder for the litellm-dev development channel of BerriAI/litellm. Real dev builds are published by the LiteLLM release pipeline.