Track Every Request. Go Low-Level. Never Hit Rate Limits Again.
The ultimate Claude API proxy with intelligent load balancing across multiple accounts. Full visibility into every request, response, and rate limit.
video_compressed.mp4
- 🚀 Zero Rate Limit Errors - Automatically distribute requests across multiple accounts
- 📊 Request-Level Analytics - Track latency, token usage, and costs in real-time
- 🔍 Deep Debugging - Full request/response logging and error traces
- ⚡ <10ms Overhead - Minimal performance impact on your API calls
- 💸 Free & Open Source - Run it yourself, modify it, own your infrastructure
# Clone the repository
git clone https://github.com/snipeship/ccflare
cd ccflare
# Build and run with Docker
docker build -t ccflare .
docker run -p 8080:8080 ccflare
# Configure Claude SDK
export ANTHROPIC_BASE_URL=http://localhost:8080
# Clone and install
git clone https://github.com/snipeship/ccflare
cd ccflare
bun install
# Start ccflare (TUI + Server)
bun run ccflare
# Configure Claude SDK
export ANTHROPIC_BASE_URL=http://localhost:8080
- Strategies Supported:
- session – Maintain session stickiness for up to 5 hours per account.
- Token usage tracking per request
- Response time monitoring
- Rate limit detection and warnings
- Cost estimation and budgeting
- Interactive TUI (
bun run ccflare
) - Web dashboard (
http://localhost:8080/dashboard
) - CLI for account management
- REST API for automation
- Automatic failover between accounts
- OAuth token refresh handling
- SQLite database for persistence
- Configurable retry logic
- Authentication (default credentials are ccflare_user : ccflare_password)
- Docker deployment
Full documentation available in docs/
:
Real-time Dashboard | Request Logs |
Analytics & Usage Tracking |
- Bun >= 1.2.8
- Claude API accounts (Free, Pro, or Team)
We welcome contributions! See CONTRIBUTING.md for guidelines.
MIT - See LICENSE for details
Built with ❤️ for developers who ship