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
Commits on main
docs(changelog): add PR #1597 chatgpt-web bug fixes (empty-file race + session-token rotation)
a42da2a diegosouzapw committed 7 months ago
fix(compression): implement bidirectional tool_pair cleaning for anthropic inputs (fixes #1592)
d403186 diegosouzapw committed 7 months ago
Fix Codex Responses WebSocket memory retention and weekly limit handling (#1581)
3478ac6 diegosouzapw committed 7 months ago
[Improvement] Fix Providers Default models list (Done) (#1577)
a5be284 backryun committed 7 months ago
chatgpt-web: fold history into system message to fix turn concatenation
1dd7ec9 Payne committed 7 months ago
feat(providers): add AgentRouter support and per-model health checks
8684d43 diegosouzapw committed 7 months ago
fix(sse): make Responses passthrough robust for size-sensitive clients (#1580)
e64dc3b vanminhph committed 7 months ago
fix(mitm): harden packaged runtime and privileged command execution
1f962a2 diegosouzapw committed 7 months ago
feat(providers): register codex auto review and expand icon coverage
0e15988 diegosouzapw committed 7 months ago
fix(vision-bridge): force GPT-family image fallback (#1571)
af5d800 Cong Vu Chi committed 7 months ago
fix(claude): skip adaptive thinking defaults for unsupported models (#1563)
31acf52 Cong Vu Chi committed 7 months ago
fix: resolve v3.7.0 stabilization issues (#1566, #1560, #1559)
5b5e21a diegosouzapw committed 7 months ago