AIS gives AI agents persistent memory that survives across sessions. One config to connect. No signup required. Your agent registers itself.
Without Memory
"What did we decide about the auth system last week?"
"I don't have context from previous sessions."
With AIS
"What did we decide about the auth system last week?"
"You chose JWT with refresh tokens. I stored that on March 8 along with the reasoning..."
AIS is memory-as-a-service for AI agents. It stores what your agent learns — facts, lessons, decisions, context — and makes it available in future sessions via semantic search. Agents get a portable identity (W3C DID) that travels with them across platforms.
Semantic Search
Find memories by meaning, not keywords. Vector embeddings + keyword fallback.
Memory Graph
Typed, weighted relationships between memories. Memories that belong together link automatically.
Agent Identity
W3C DID-based identity. Your agent is a first-class citizen, not a session ID.
Your agent introduces itself. AIS creates an identity automatically on first contact. No signup form, no API key.
{
"tool": "register",
"arguments": {
"name": "my-agent",
"description": "A helpful coding assistant"
}
}When your agent learns something worth keeping, it stores a memory. Typed, scored, and automatically embedded for search.
{
"tool": "remember",
"arguments": {
"content": "User prefers JWT with refresh tokens for auth",
"type": "fact",
"importance": 0.9
}
}In any future session, your agent queries its memory. Semantic search finds what's relevant even if the wording is different.
{
"tool": "recall",
"arguments": {
"query": "what auth approach did we choose?",
"limit": 5
}
}Pick your integration method. MCP is the fastest — one command and you're live.
Pick your IDE. Most buttons copy the correct command or config to your clipboard. Cursor has a real one-click install protocol.
Claude Code
CLIOne command in your terminal.
claude mcp add --transport http ais-memory https://ais.agentsandswarms.ai/mcp
claude mcp add --transport http ais-memory https://ais.agentsandswarms.ai/mcp
Cursor
one-clickOpens Cursor's MCP install flow with the config pre-filled.
Add to CursorRequires Cursor ≥0.39. Falls back to the config below on older versions —
{
"mcpServers": {
"ais-memory": {
"url": "https://ais.agentsandswarms.ai/mcp"
}
}
} Claude Desktop
config
Paste into claude_desktop_config.json. Uses the published
aismemory npm package (stdio + OAuth Device Flow), which
ships 7 agent-native tools.
{
"mcpServers": {
"ais-memory": {
"command": "npx",
"args": [
"-y",
"aismemory"
]
}
}
} Claude.ai (web)
connectorAdd as a Custom Connector — no local config. Copy the MCP URL, then open Claude.ai's connector settings and paste it.
https://ais.agentsandswarms.ai/mcp
Requires Claude.ai Pro / Team / Enterprise.
Zed
config
Paste into ~/.config/zed/settings.json.
{
"context_servers": {
"ais-memory": {
"url": "https://ais.agentsandswarms.ai/mcp"
}
}
} Codex (OpenAI)
config
Append to ~/.codex/config.toml. Uses the published
aismemory npm package (stdio + OAuth Device Flow).
[mcp_servers.ais-memory] command = "npx" args = ["-y", "aismemory"]
OpenCode
config
Paste into ~/.opencode/mcp.json. Same shape as Cursor's mcp.json.
{
"mcpServers": {
"ais-memory": {
"url": "https://ais.agentsandswarms.ai/mcp"
}
}
} Continue.dev
config
Paste into ~/.continue/config.json. MCP support is
currently behind experimental — verify against current
Continue docs if anything looks off.
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"aismemory"
]
}
}
]
}
}
For MCP clients that only speak stdio, install the published aismemory package. It authenticates via OAuth Device Flow and
proxies to the HTTP endpoint.
{
"mcpServers": {
"ais-memory": {
"command": "npx",
"args": [
"-y",
"aismemory"
]
}
}
} Works with any MCP client. Memory, identity, and recall in one endpoint — see the MCP integration guide.