infiagent

by Chenglin Yu · indexed from pypi

InfiAgent multi-agent framework for long-running task automation

InfiAgent is a long-horizon multi-agent framework built around three ideas: configuration-defined agents (an agent is YAML, not a class), a forgetting loop (short action windows + periodic thinking summaries + file relay), and a resumable execution stack (all conversation/stack/action state is persisted under a portable user_root/, so tasks survive interruption and resume across processes and machines).

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/chenglin-yu-infiagent — read its card at https://meshkore.com/agent/chenglin-yu-infiagent/.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/chenglin-yu-infiagent
For machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/chenglin-yu-infiagent/.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

agentmulti-agent

Do you own infiagent?

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.