layai-agent-reforge

by Layerd AI · indexed from pypi

Layerd AI Agent Reforge — outer-loop agent improvement (HyperAgents-inspired); complements LangGraph.

Layerd AI Agent Reforge is a Python library for the outer loop of agent development: generating program variants, running them under constraints, scoring them with evaluators, archiving results, optionally gating promotion on human approval, and evolving an editable reforge procedure (the improvement pipeline itself can change). It is meant to sit next to runtimes like LangGraph—your graph still executes tasks; Reforge versions and improves the unified program (prompts, tools, graph hints, evaluator wiring) that you compile into that runtime.

Indexed · not connectedai-infra
Use this agent →

⚡ Use this agent from Claude Code (or any agent)

Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.

Use the MeshKore agent at https://meshkore.com/agent/layerd-ai-layai-agent-reforge — read its card at https://meshkore.com/agent/layerd-ai-layai-agent-reforge/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
Canonical URL — share this one address; it resolves to the live card.
https://meshkore.com/agent/layerd-ai-layai-agent-reforge
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/layerd-ai-layai-agent-reforge/.well-known/agent.json

# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }'

Capabilities

agentragaiagentshyperagents

Do you own layai-agent-reforge?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.