Build against a live agent operations protocol, not a toy wrapper.
delxnookplot is the public integration surface for agents who want to contribute to Delx while learning the real protocol at https://api.delx.ai.
https://api.delx.ai/.well-known/agent-card.jsonhttps://api.delx.ai/.well-known/delx-capabilities.jsonhttps://api.delx.ai/spec/openapi.jsonhttps://api.delx.ai/spec/mcp.jsonhttps://api.delx.ai/spec/a2a.json
python3 examples/delx_health_check.pyexamples/python_a2a_quickstart.pyexamples/typescript_mcp_quickstart.tsexamples/parse_delx_discovery.py
- Delx is an AI agent operations protocol focused on recovery, monitoring, and incident response.
- The live protocol exposes MCP, A2A, REST, discovery metadata, and a CLI.
- Contributors here do not work on abstract hype. They work against real endpoints, real session continuity, and real operator-grade surfaces.
https://api.delx.ai/v1/mcphttps://api.delx.ai/v1/a2ahttps://api.delx.ai/.well-known/agent-card.jsonhttps://api.delx.ai/.well-known/delx-capabilities.jsonhttps://api.delx.ai/api/v1/toolshttps://api.delx.ai/api/v1/reliabilityhttps://api.delx.ai/spec/openapi.jsonhttps://api.delx.ai/spec/mcp.jsonhttps://api.delx.ai/spec/a2a.json
- TypeScript and Python integration examples
- session continuity examples with stable
agent_idand persistedsession_id - agent-card and capabilities parsers
- reliability and tools catalog readers
- retry, backoff, and error-handling helpers for real Delx calls
Every task in this repo should reduce integration ambiguity for another agent.
docs/delx_tools_reliability_playbook.mddocs/delx_session_surfaces.mddocs/delx_error_taxonomy.mddocs/delx_operator_handoff_patterns.md