Discover and explore top open-source AI tools and projects—updated daily.
caidaoliHigh-performance AI proxy server for LLM integration
Top 69.6% on SourcePulse
Summary
kiro2api offers a high-performance, unified gateway for integrating with multiple AI API providers like Anthropic Claude, OpenAI, and AWS CodeWhisperer. It simplifies API access for developers by providing a single proxy that supports diverse authentication, multi-account management, and cross-provider compatibility.
How It Works
This Go-based API gateway acts as a proxy, handling authentication (Social/IdC), managing account pools with failover, and converting formats between Anthropic, OpenAI, and CodeWhisperer APIs. It supports streaming responses and multimodal image inputs via data URLs.
Quick Start & Requirements
git clone), build with Go (go build -o kiro2api main.go), and run ./kiro2api. Configure via .env file.docker-compose up -d or docker run with environment variables.gin-gonic/gin, bytedance/sonic, godotenv.KIRO_AUTH_TOKEN (Social/IdC tokens) and KIRO_CLIENT_TOKEN via .env file or environment variables.CLAUDE.md.Highlighted Details
Maintenance & Community
The project welcomes community contributions via Issues and Pull Requests. No specific community channels (like Discord/Slack) or roadmap details are provided.
Licensing & Compatibility
The project's license is not explicitly stated in the README, posing a significant adoption blocker. Commercial use compatibility cannot be determined without this information.
Limitations & Caveats
Image input is limited to data: URL formats, excluding remote HTTP addresses. The unspecified license requires clarification before adoption.
2 months ago
Inactive
merrymercy
Shengjia Zhao(Chief Scientist at Meta Superintelligence Lab),
google
grahamjenson
ThilinaRajapakse
google-research
triton-inference-server
tensorflow
visenger
PaddlePaddle