Aisbf, a self-hostable OpenAI-compatible AI proxy/router
LiteLLM and OpenRouter already solve multi-provider routing better and have production users.
Content-based JSON schema routing for YAML LSP (Neovim/Helix/Emacs)
Content-aware schema routing kills YAML LSP guesswork; elegant stdio proxy architecture.
Terminal-based YAML editors (Neovim, Helix, Emacs users)
yaml-language-server · SchemaStore
LiteLLM and OpenRouter already solve multi-provider routing better and have production users.
Fixes Claude Code's .venv restart annoyance with smart backend pooling. Niche but precise.
Smart LLM routing cuts costs, but competing against established OpenRouter and vLLM ecosystems.
Specialized routing logic for MoE models without a demo or benchmarks.
If you're burning through Claude/OpenAI credits, this is a low-friction stopgap: it classifies prompts in ~10ms and routes trivial tasks to cheaper/local models while reserving premium APIs for complex work. The agentic-task detection, reasoning-aware routing, session pinning and context-window fallback are practical touches that avoid mid-thread model bouncing and 429 failures. It isn't reinventing the space (OpenRouter and others exist), but it's focused on real-world cost tradeoffs and drop-in compatibility.
LLM cost routing with LoRA awareness when LiteLLM already handles basic proxying.