CC Switch

What is CC Switch

CC Switch is anopen-source cross-platform AI coding configuration management toolthat supports macOS, Windows, and Linux. As a one-stop AI coding tool Hub, CC Switch can manage in a single interface Claude Code、Claude Desktop、Codex、Gemini CLI、OpenCode、OpenClaw and Hermes Agent provider configurations, local routing, usage tracking, Skills synchronization, and cross-application session recovery for seven major applications, enabling access to third-party models with zero code modifications.

CC Switch's main features

• Unified provider management: Manage model providers, authentication information, and API endpoints for seven major Agent applications in one interface, with hot switching and backup and restore support.
• Local intelligent routing: Built-in circuit breaker, health monitoring, and failover queue automatically switch to a backup node when the primary Provider is abnormal, without interrupting the workflow.
• Usage and cost tracking: Real-time statistics on request count, Token consumption, cache hits, subscription quotas, and costs, with filtering by application and Provider.
• Secure local storage: All configurations and API Keys are stored in a local SQLite database, with full Schema migration support, and data never leaves the device.
• MCP / Skills / Prompt management: Unified management of MCP services, Skills packages, Prompts templates, and Hermes Memory, with cross-application synchronization and symlink deployment support.
• Centralized session management: Gather local session records from each Agent, with search, restore, and delete support, breaking down session silos between applications.
• Model mapping and protocol conversion : Map Claude official role IDs or Codex's GPT model names to the actual models of third-party providers, automatically completing protocol conversion between the Responses API and Chat Completions API.

How to use CC Switch

• Download and install: Visit the CC Switch official website https://ccswitch.io/ download the installation package for the corresponding system, and launch CC Switch after installation is complete.
• Select management targets: Check the Agent applications to be managed on the main interface and activate toolbar monitoring.
• Add a provider: Go to the provider configuration page, enter the third-party API endpoint address and authentication token, and automatically detect connectivity after saving.
• Enable local routing: For applications such as Codex or Claude Desktop, enable the "Requires local routing mapping" switch and keep the proxy resident.
• Configure model mapping: In the mapping settings, specify the actual third-party model names requested for Sonnet/Opus/Haiku or the GPT series.
• Sync Skills: On the Skills management page, import existing Skills packages or install from ZIP, and synchronize them in real time to each Agent's configuration directory via symlinks.
• Monitor usage: View real-time request logs, Token consumption, and cost curves on the usage statistics panel, and set quota alerts.

CC Switch's core advantages

• Full application coverage: The industry's only unified manager that simultaneously supports both Claude clients, Codex, Gemini, OpenCode, OpenClaw, and Hermes.
• Zero-intrusion access: No need to modify Agent source code; simply point environment variables to the local proxy to use third-party models.
• High-availability routing: Built-in circuit breaking and failover, switching to backup Providers within milliseconds when the primary line is abnormal, ensuring development continuity.
• Cost Transparency: Fine-grained usage tracking helps developers identify high-consumption areas, with measured savings of about 30% on API expenses.
• Open Source and Free: Fully open source under the MIT license, community-driven iteration, with no commercial licensing barriers.

CC Switch's project address

• Project Website：https://ccswitch.io/
• GitHub Repository：https://github.com/farion1231/cc-switch

Comparison of CC Switch with similar competing products

CC Switch's application scenarios

• Multi-model A/B Testing: Developers quickly compare the code generation results of models such as Claude, GPT, DeepSeek, and GLM within the same project.
• Enterprise-grade API Disaster Recovery: Through automatic switching between primary and backup Providers, it avoids development interruptions caused by rate limiting or failures from a single vendor.
• Fine-grained Cost Control: Team leaders track Token consumption by project or member dimension to optimize model invocation strategies.
• Accumulation of Skills Assets: Centrally manage custom MCP tools and Prompt templates, allowing new members to sync them to all Agents with one click.
• Cross-application Session Continuation: When switching between Claude Code and Codex, contextual sessions are preserved, reducing repeated communication costs.