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 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# Build the image (ships with dashboard assets prebuilt)
docker build -t ccflare .
# Start the server inside Docker
docker run -d \
--name ccflare \
-p 8080:8080 \
-v ccflare_data:/data \
-e PORT=8080 \
-e LB_STRATEGY=session \
ccflareThe container stores configuration and the SQLite database under /data (mapped to
ccflare_CONFIG_PATH=/data/config/ccflare.json and ccflare_DB_PATH=/data/storage/ccflare.db).
Mount a volume there (shown above) to persist settings between restarts. See
docs/deployment.md for compose examples
and advanced options (health checks, reverse proxies, custom networks, etc.).
ccflare loads agents from Markdown files inside .claude/agents/ folders. To keep
your container in sync with projects scattered across Linux, WSL, or Windows:
# One-time automation: scan, capture workspaces, restart container with minimal mounts
bun run agents:setup
# Manual scan if you want to keep the container running
bun run agents:scan -- /host /mnt/c --max-depth 8- The setup script stops
ccflare-dev, launches a helper container with wide mounts, runs the scanner, and restartsccflare-devwith only the discovered bind mounts plus/data, while sharing accflare-workspacesvolume that persists/root/.ccflare/workspaces.jsonbetween restarts. - The dashboard now includes a Register Workspace Paths card (Agents tab) so
you can add absolute paths on the fly. Behind the scenes it calls
POST /api/workspaces(documented indocs/api-http.md). - For more examples (mount tables, environment variables, troubleshooting) see
docs/agent-workspaces.md.
- Session-based - Maintain conversation context (5hr sessions)
- 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
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


