Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
Release process — @omniroute/opencode-plugin-v2
Publishing
One package, no ordering: bump @omniroute/opencode-plugin-v2 (npm version patch) and publish it. The plugin carries its own copy of the mapping logic, so a release never has to be coordinated with another package.
Migration note (opencode-X → X)
The v1 plugin published provider id opencode-X (native-adapter gate). The v2 plugin publishes X bare. Sessions pinned to opencode-X/... resolve ModelUnavailableError — users must re-select the model under X/....