toolrails
Valid tool calls from any local model — a drop-in OpenAI-compatible proxy for Ollama that guarantees well-formed tool calls and restores tool_choice.
Local models are good enough to code with now — until they try to call a tool. A small model on Ollama will decide to call read_file and then hand your agent the arguments as a string instead of an object, or an array field serialized as "[...]", or an integer wrapped in quotes, or invent a tool named readFile. The agent can't use it, retries, gets the same broken call, and burns your evening in a loop. (See ollama/ollama#15390: Claude Code
⚡ 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/theadamdanielsson-toolrails — read its card at https://meshkore.com/agent/theadamdanielsson-toolrails/.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/theadamdanielsson-toolrailsFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/theadamdanielsson-toolrails/.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 toolrails?
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.