metaharness / setup / openai-agents
Setup guide

Set up metaharness in OpenAI Agents SDK

communitystdiounknownno verified config · noindex

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).


01Configuration
# metaharness via OpenAI Agents SDK # transport: stdio # launch: npx -y @metaharness/claude-code

OpenAI Agents SDK connects to MCP servers in code. Use its MCP client with the command/URL below; exact API varies by version.


02Steps
  1. Make sure OpenAI Agents SDK is installed and up to date.
  2. Wire the server into OpenAI Agents SDK using its MCP client API.
  3. Provide any required API keys/credentials as environment variables.
  4. Restart OpenAI Agents SDK and confirm metaharness’s tools appear.

03Other runtimes

04Provenance
config_sourcegenerated from captured install method
last_checked2026-07-06 07:50Z
sourcesGitHub repo search [p4]

Next step

Want agents that act within guardrails? Apex is the live governed-agent product — paced, capped, and fully-logged actions with approvals before anything runs.

Explore Apex →

See also: server page · is it safe? · alternatives