shinglokto/openclaw-claude-bridge

Registry

Summary

OpenClaw Claude Bridge is an HTTP bridge that powers AI agents via the Claude Code CLI. It manages persistent sessions, auto-resume, extended thinking, and provides a real-time React dashboard with per-agent cost tracking, exposing an OpenAI-compatible API.

Key features

• HTTP bridge for Claude Code CLI
• Persistent session management with auto-resume
• Extended thinking support
• Real-time React dashboard with per-agent cost tracking
• OpenAI-compatible API exposure

Use cases

• Powering AI agents with Claude Code CLI
• Building multi-agent systems with cost monitoring
• Integrating Claude into custom workflows via OpenAI-compatible API
• Managing long-running AI sessions with auto-resume

README excerpt

# openclaw-claude-bridge [](LICENSE) [](https://nodejs.org/) [](https://docs.anthropic.com/en/docs/claude-code) [繁體中文](README.zh.md) | English An OpenAI-compatible HTTP proxy that lets [OpenClaw](https://github.com/openclaw/openclaw) agents use Claude through [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code) — with tool calling, session memory, and extended thinking. --- ## Why This Exists OpenClaw speaks the OpenAI API format. Claude Code CLI speaks its own format. This bridge sits in between and translates — so your OC agents can talk to Claude without either side needing to change. ``` OpenClaw agent Bridge Claude CLI (Discord/Telegram) │ │ │ │ POST /v1/chat/ │ │ │ completions │ Translate messages │ ├──────────────────────────▶│ Inject tool protocol │ │ │ Map thinking level │ │ │ │ │ │ stdin ──▶ claude --print │ │ │ stdout ◀── stream-json │ │ │ │ │ SSE stream │ Parse response: │ ◀──────────────────────────│ ├─ text → clean output │ │ │ └─ <tool_call> → OpenAI fmt │

Topics