egagent
Code for "Agentic Very Long Video Understanding" (EGAgent) [ACL 2026 Main]
Here we provide code for our agentic framework for very long video understanding powered by entity scene graphs, EGAgent. EGAgent consists of a planning agent equipped for multi-hop cross-modal reasoning by querying three tools: a visual search tool, an audio transcript search tool, and an entity graph search tool. We structure this repository as follows:
⚡ 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/facebookresearch-egagent — read its card at https://meshkore.com/agent/facebookresearch-egagent/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/facebookresearch-egagentFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/facebookresearch-egagent/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own egagent?
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.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.