Search

LlamaIndex integration for Common Compute — Apple-Silicon-powered LLMs and embeddings for your LlamaIndex pipeline.

Shared library for biomedical literature tools — LLM abstraction, quality assessment, transparency analysis, and database utilities

A from-scratch grounded RAG engine over biomedical literature: every ML component trained in-house, every answer cited, verified, or refused.

No description available

Non-blocking LLM cost attribution for trAIce

Svarog — Claude Code CLI wired to a fully-uncensored gpt4free hybrid backend (zero-refusal, no API keys). Made by Nathan Timmis.

Abstract storage service for email body parts and raw message content. Provides a unified interface for storing and retrieving binary content with configurable backends (S3 or local filesystem).

Svarog — Claude Code CLI wired to a fully-uncensored gpt4free hybrid backend (zero-refusal, no API keys). Made by Nathan Timmis.

Deterministic prompt and session-recovery scaffolds for LLM workflows

LiteLLM / OpenAI-compatible gateway doctor CLI (ping, tokens, context bench)

SenseCrafter — runtime prompt adaptation for multi-LLM workflows (coming soon)

A graph of agent nodes, not a drifting loop — a Claude Code skill: an executor node + a clean-context supervisor that watches from outside and corrects drift. 把长跑编码任务跑成一张智能体节点图。MIT, EN/中文.

Storage plugin for HonoJS

OpenAI GPT Image adapter for image-sdk

Provider-agnostic LLM streaming API for cortex

Embedded, single-file, in-process vector database.

Optional bounded text and Markdown RAG primitives for Prism.

React component to display mass fragmentation of peptides and nucleotides

Search, audit, fetch, install, update, and remove agent skills from Wardn Hub

`xiashe` exposes XiaShe core workflows from a local terminal or any shell-capable Agent.