ai-ml

Production-grade AI defense — deterministic filters + optional LLM veto verification.

Generate optimal LLM context from pandas DataFrames within a token budget

The Context Optimization Layer for LLM Applications - Cut costs by 50-90%

Upload datasets to SAP HANA, auto-generate REST APIs and query with LLM

LangSmith observability for LLM and robot SDKs

Django database backend powered by Apache Iceberg and Polars - bringing time travel, cloud-native storage, and blazing-fast analytics to Django

A minimal, fast, and type-safe Python library for LLM chat completions with OpenAI and Azure OpenAI support

Development workflow toolkit for Claude Code with issue management, code quality commands, and automated processing

Full-stack Python + React framework for building applications with workflows, tables, UIs, and LLM integration.

A tool to generate commit messages using OpenAI models.

Async-native Python framework for building production-grade LLM applications. Streaming-first, 2 dependencies, fully transparent.

Virtual Meshtastic node using mudp transport and meshdb storage.

The way to build RAG — modular, configurable, plugin-based

Flexible taxonomy management for generic items — categories, tags, and multi-parent hierarchies with pluggable storage.

OpenRouter-compatible LLM router with unified batch support. Route requests across OpenAI, Anthropic, and Google with a single API.

Persistent, emotionally-weighted memory for any LLM

Production-ready Telegram FAQ bot with Russian LLMs, RAG, and multi-provider fallback

Portable Claude Code workspace archives

A Python package for tuning vLLM hyperparameters.

Self-hosted semantic search and knowledge management for LLM-driven development