Search

Storage and tooling for 3D radiation fields with C++ core and Python bindings.

YunZhi UEBA receiver for SiteLLM callback events

Offline, zero-dependency indirect prompt injection scanner for LLM applications.

OpenAI-compatible context overlay proxy for injecting skills, memory, policies, and prompt patches.

GitHub repository reader with document chunking for RAG/LLM applications

Paste a target-weights CSV, preview the rebalance, execute it on your brokerage account. Tastytrade + Alpaca + paper.

Python (ctypes) bindings for the kernel-set LLM inference & training kernels

Minimalist AI translation CLI powered by LLMs

Lightweight self-hosted Telegram manager for Claude Code CLI

DoCoreAI is an AI prompt optimization tool for developers and teams to reduce LLM cost, improve output, and analyze GPT prompt efficiency—no fine-tuning needed.

RAG implementation pipeline with GPU support

Python adapter for "swagger-coverage" tool

Load tabular data from any storage backend (GCS, S3, Azure, local) and any common format into a pandas DataFrame with a single call.

Japanese-optimized prompt library and CLI — 50+ templates for superior Japanese LLM output

Lighthouse for RAG systems — diagnose and fix your retrieval pipeline

RICE-prioritise your Sentry issues, with AI scoring that traces each issue into your codebase (via Claude Code).

Reduce LLM API costs by up to 90% — prompt caching, smart routing, batch processing, and more

LLM observability SDK — wraps Anthropic and OpenAI Python clients and logs every call

OpenAI chatkit backend support for Google ADK

Context-driven scheduled tasks for LLMs with persistent memory — inspired by OpenClaw's Heartbeat.