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
TypeScript a2aai-agentsai-gatewayanthropicclaudeclaude-codeclinecodexcopilotcursordeepseekfree-aigeminikimillm-gatewaymcpopenaiopenai-proxyqwentoken-saver
# Codecov — WS5.6/D7 of the v3.8.49 quality/velocity plan.
# Philosophy: strict patch, lenient project — the project floor/ratchet already
# lives in quality-baseline.json + the c8 60% gate; Codecov adds the DIFF view
# ("new lines in this PR are covered"), which the global ratchet cannot see.
# INFORMATIONAL during calibration: nothing here blocks a PR. Promote by flipping
# informational to false after ~2 weeks without false blocks (owner decision).
coverage:
status:
project:
default:
informational: true
patch:
default:
target: 70%
informational: true
comment:
layout: "condensed_header, diff"
behavior: default
require_changes: true