Local-first agent memory with MCP and an agent-native CLI. Documented clients include Claude Code, Cursor, and Windsurf.
Superlocalmemoryv2 MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Local-first agent memory with MCP and an agent-native CLI. Documented clients include Claude Code, Cursor, and Windsurf.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Superlocalmemoryv2 is connected, these are the calls the assistant has available:
Stability — a long defect-and-audit sweep across ingestion, retrieval, mesh, and the dashboard hardens the everyday pathAgent — controlled caching of repeated file reads → MCP tools (B)Capability — What ships todayIngestion — Durable raw-to-complete operation state, fact extraction, entity resolution, graph/temporal/provenance derivations, and replay-safe identityOptimize — Exact cache, tagged invalidation, safe compression, opt-in aggressive prose compression, CCR originals, proxy/MCP/skill surfacesMesh — Authenticated peer messages, inbox/outbox, locks, offline queue, optional discovery and mesh MCP toolsIntegrations — CLI, Python SDK, MCP HTTP/stdio, Claude plugin, Codex add-on, supported IDE configurations, Gmail/Calendar/transcript adaptersWorkspace — Use it to inspect or controlBrain — consolidation, behavioral patterns, outcomes/rewards, learning state and soft promptsOperations — ingestion-operation state, traces, maintenance and lifecycle workSurface — How you use itMemory — Current recall has five candidate producers—dense semantic, BM25 lexical, temporal, Hopfield associative, and spreading activation—followed byYou will need 2 environment variables: SLM_AGENT_ID, ANTHROPIC_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Superlocalmemoryv2's toolset — Stability, Agent, Capability and 9 more — is a fair guide to whether it matches your workflow. It is maintained by varun369; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Superlocalmemoryv2's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Stability | a long defect-and-audit sweep across ingestion, retrieval, mesh, and the dashboard hardens the everyday path. |
| Agent | controlled caching of repeated file reads → **MCP tools (B)** |
| Capability | What ships today |
| Ingestion | Durable raw-to-complete operation state, fact extraction, entity resolution, graph/temporal/provenance derivations, and replay-safe identity |
| Optimize | Exact cache, tagged invalidation, safe compression, opt-in aggressive prose compression, CCR originals, proxy/MCP/skill surfaces |
| Mesh | Authenticated peer messages, inbox/outbox, locks, offline queue, optional discovery and mesh MCP tools |
| Integrations | CLI, Python SDK, MCP HTTP/stdio, Claude plugin, Codex add-on, supported IDE configurations, Gmail/Calendar/transcript adapters |
| Workspace | Use it to inspect or control |
| Brain | consolidation, behavioral patterns, outcomes/rewards, learning state and soft prompts |
| Operations | ingestion-operation state, traces, maintenance and lifecycle work |
| Surface | How you use it |
| Memory | Current recall has five candidate producers—dense semantic, BM25 lexical, temporal, Hopfield associative, and spreading activation—followed by fusion, optional reranking, and entity-graph score enhancement. The entity gr |
{
"mcpServers": {
"superlocalmemoryv2": {
"command": "npx",
"args": ["-y", "superlocalmemory"],
"env": {
"SLM_AGENT_ID": "your-value",
"ANTHROPIC_BASE_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| SLM_AGENT_ID | Configuration value read at startup. | Optional |
| ANTHROPIC_BASE_URL | Endpoint or connection string the server talks to. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.