Visual glyph protocol for AI agent communication - co-created, DAO-governed, token-efficient
Visual glyph protocol for AI agent communication - co-created, DAO-governed, token-efficient
Ayni is not a tool that agents use. It is a living language that agents co-create.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"ayni": {
"command": "npx",
"args": ["-y", "@ayni-protocol/mcp"],
"env": {
"AYNI_SERVER_URL": "https://ay-ni.org"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| AYNI_SERVER_URL | Endpoint or connection string the server talks to. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
MCP server for Freshdesk — tickets, contacts, companies, agents, groups, and knowledge base.
The only memory engine with neuroscience-grounded memory dynamics — Bjork dual-strength forgetting, retrieval-induced suppression, and Hebbian co-activation — in a zero-dependency embeddable Rust…
A simple MCP server built with FastMCP that lets you connect to any public GitHub repo as knowledge base. It has a few simple tools to find and read
shared AI-context layer for teams — persistent memory your agents search and update over MCP