AxonHub is a production-grade, multi-provider LLM API gateway that routes, transforms, and manages requests to a wide range of AI providers (OpenAI, Anthropic, Gemini, DeepSeek, xAI, and 60+ others). It provides a unified API surface for chat completions, embeddings, moderations, audio, images, and video generation, with sophisticated features like load balancing (latency-aware, weighted round-robin, circuit breaker), per-channel rate limiting, provider quota enforcement, streaming, and reasoning token handling. The backend is written in Go using Gin, Ent ORM, gqlgen, and Uber Fx for dependency injection, supporting PostgreSQL, MySQL, and SQLite with automatic migration. The frontend is a comprehensive React/TypeScript SPA (Vite, TanStack Router/Query, Tailwind, shadcn/ui) that provides administration of channels, models, API keys, users, roles, projects, and system settings. It includes analytics dashboards, request tracing, usage logs, and OIDC SSO. The system is designed for multi-tenancy with fine-grained RBAC (scope-based permissions) and privacy policies enforced at the Ent ORM layer. Deployment is supported via Docker, Docker Compose, and Helm charts. The codebase exhibits strong engineering practices: extensive unit and integration tests (including race-condition tests and E2E Playwright tests), pipeline middleware for request transformation, generic caching abstractions, stream processing utilities, and a Zanzibar-inspired authorization framework. While there are minor issues (duplicate utility packages, a typo in a folder name, and some frontend boilerplate repetition), the overall architecture is clean, modular, and well-documented. The project is actively maintained with frequent commits, issue triage, and a clear release process.
hermes-claude-auth is a runtime patching tool that enables hermes-agent to use Claude Code subscription credentials by bypassing Anthropic's server-side OAuth validation. It works through a Python import hook that monkey-patches hermes-agent's anthropic adapter to modify outgoing API requests with proper billing headers, system prompt restructuring, and Claude Code fingerprint matching. The tool consists of three main components: the core bypass logic (anthropic_billing_bypass.py) that implements complex request transformation, an import hook mechanism (sitecustomize_hook.py) for runtime patching, and installation/uninstallation scripts. The bypass handles billing header signing, system prompt relocation, tool name namespacing, Stainless header spoofing, tool pair repair, effort stripping for haiku models, temperature fixing for Opus 4.6, and account metadata mapping. It's designed to be idempotent and tracks upstream changes from the opencode-claude-auth project.