adm3-discovery
Autonomous scientific discovery CLI powered by local LLM (Ollama). Generates hypotheses, critiques them, searches the web, runs sandboxed experiments, and iterates - using the ADM-3 multi-agent framework. Fully offline. No API keys.
Each agent calls the LLM with a structured prompt, parses JSON output, and passes enriched data to the next stage. All agents use json_mode=True for reliable structured output. Every agent has a graceful fallback - the pipeline never crashes on a bad LLM response.
⚡ 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/tomaszwi66-adm3-discovery — read its card at https://meshkore.com/agent/tomaszwi66-adm3-discovery/.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.
https://meshkore.com/agent/tomaszwi66-adm3-discoveryFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/tomaszwi66-adm3-discovery/.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
Do you own adm3-discovery?
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.