Agents
Verified ACP agents the runtime supports.
Each agent runs in a sandboxed environment with hardened verifiers, mounted skills, and host subscription auth where available. Web tools are disabled by default. Click any tile to jump into the upstream registry on GitHub.
Claude Code
ACPclaude-agent-acp
Claude Code via Anthropic's Agent Client Protocol.
- Auth
- ANTHROPIC_API_KEY
- Skills
- $HOME/.claude/skills
registry source
Codex
ACPcodex-acp
OpenAI Codex agent through the Zed ACP package.
- Auth
- OPENAI_API_KEY
- Skills
- $HOME/.agents/skills
registry source
Gemini CLI
ACPgemini
Google Gemini CLI running with `gemini --acp --yolo`.
- Auth
- GOOGLE_API_KEY or GEMINI_API_KEY
- Skills
- $HOME/.gemini/skills
registry source
OpenCode
ACPopencode
Open-source TypeScript coding agent through `opencode acp`.
- Auth
- Inferred from model/provider
- Skills
- $HOME/.opencode/skills
registry source
OpenHands
ACPopenhands
OpenHands agent via ACP with multi-model provider support.
- Auth
- LLM_API_KEY
- Skills
- $HOME/.agents/skills
registry source
OpenClaw
ACP shimopenclaw
OpenClaw agent wrapped by BenchFlow's ACP shim.
- Auth
- Inferred from model/provider
- Skills
- $HOME/.claude/skills
registry source
Pi
ACPpi-acp
Pi coding agent using the Pi ACP launcher.
- Auth
- Inferred from model/provider
- Skills
- $HOME/.pi/agent/skills
registry source