Search

Local multi-profile AI SDK provider router

The complete RAG evaluation library. Scores, diagnoses, and domain-aware.

Server-side SDK for tracking LLM token usage, costs, and observability data in LLMtrack

Core MinIO storage operations for OA Drive - shared by business and infrastructure services

MinIO storage connector with fingerprinting for immutable content storage

A provider-neutral engine for building inspectable, extensible agentic products.

Vertex AI Gemini grounded web search, research, and direct URL extraction tools for Pi, using Google Cloud Agent Platform credentials.

A fast MLX inference engine and OpenAI/Anthropic-compatible server for Apple Silicon

Reusable bridge from AI-CDL protocol to OpenAI-compatible chat completions

Stellarmesh 对象存储控制面与预签名数据面客户端

Kubernetes deployment manifests for RagLeap Core, live-tested against a real cluster

A Claude-Code-shaped permission rule table as pre_tool_use / on_resume stages.

LangChain tools for Truth Bear GAUGE official-source signal data

A modular, fully local reliability layer for RAG pipelines.

Native ChatGPT Codex provider, device-code-first login, and same-origin Web integration for DeepSeek Harness

FshStorage API Wrapper written in Python

OpenAI Codex (ChatGPT Plus/Pro subscription) provider for DeepSeek Harness with DSH Web OAuth, device code, and shared Codex CLI credentials

A DeepSeek Harness provider backed by the official GitHub Copilot SDK and CLI

RAG evaluation toolkit with readable LLM-judge prompts and local-first (Ollama) support.

LangGraph checkpoint saver backed by local filesystem, GCS, or S3 via fsspec