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
address review: emit BACKGROUND_DEGRADE log + test for background:false case
8b1da7b OmniRoute Ops committed 6 months ago
address review: add MODEL_SPECS entries for new claude/kimi/mimo models
9928484 OmniRoute Ops committed 6 months ago
address review: exclude arrays from reasoning check + hoist regex constants
c83792a OmniRoute Ops committed 6 months ago
fix(cliproxyapi): rewrite mcp_* tool names to bypass Anthropic gate
83f2592 OmniRoute Ops committed 6 months ago
fix(cliproxyapi): strip Capy premium extras on Anthropic-shape bodies
05212b0 OmniRoute Ops committed 6 months ago
fix(cliproxyapi): route Anthropic-shape bodies to /v1/messages
4ee9ba9 OmniRoute Ops committed 6 months ago
feat(responses): degrade background mode to synchronous execution
970e147 OmniRoute Ops committed 6 months ago
fix(registry): cap gpt-5.5 codex OAuth contextLength at 400K (not 1.05M)
ef1022e OmniRoute Ops committed 6 months ago
chore(registry): per-model contextLength/maxOutputTokens for active providers
fa3b6d1 OmniRoute Ops committed 6 months ago
fix(registry): set kimi-coding defaultContextLength to 262144 (K2.6 native)
7395d71 OmniRoute Ops committed 6 months ago
fix(executors): sanitize reasoning_effort for non-supporting providers
21ca713 OmniRoute Ops committed 6 months ago
fix(translator): inject thinking placeholder for all Claude-shape upstreams
08de5a1 OmniRoute Ops committed 6 months ago
docs(workflow): strictly restrict cherry-pick to locked PRs only
fea8e5a diegosouzapw committed 6 months ago
docs: add contributor credits to CHANGELOG for all merged/cherry-picked PRs
f632da7 diegosouzapw committed 6 months ago
fix(openai-responses): emit reasoning summary as delta.reasoning_content (#2159)
2880155 Gioxa committed 6 months ago
feat(resilience): add model cooldowns dashboard card with real-time list and re-enable
e4c8c14 diegosouzapw committed 6 months ago
fix: Added in debug mode, support for storing raw data in json (#2156)
d3e0353 ipanghu committed 6 months ago
fix(catalog): cherry-pick type safety from PR #2152 — remove .ts imports, as any casts, add CustomModelEntry/ComboModelStep types
6fc66ea diegosouzapw committed 6 months ago
chore(models): tidy up alibaba-coding-plan and cursor provider (#2150)
6e2c5e2 backryun committed 6 months ago
fix(openai-responses): propagate include so chat clients stream reasoning summaries (#2154)
fca8904 Gioxa committed 6 months ago
fix(kiro): synthesize tools schema when history references tool_calls without body.tools (#2149)
1814d2b Gioxa committed 6 months ago
fix(kiro): avoid treating high-traffic 429s as quota exhaustion (#2153)
fdb4c63 Gioxa committed 6 months ago
refactor(catalog): replace bracket-access with CustomModelEntry interface
66d5808 Automation committed 6 months ago
refactor(catalog): remove .ts import extensions, as any casts, and normalize alias resolution
360a97b Automation committed 6 months ago
feat(resilience): expose model cooldown list with manual re-enable
66d5d40 Ramel Tecnologia committed 6 months ago
fix(types): remove extraneous config/models from AutoComboConfig returns and type seedConnection overrides
7d8b783 diegosouzapw committed 6 months ago
docs(changelog): add PR #2141 entry and update contributor credits
966e411 diegosouzapw committed 6 months ago
fix: remove duplicate cloud agent provider constants (#2141)
602f897 backryun committed 6 months ago