AgentRecall vs NMEMORY
A side-by-side look at the AgentRecall and NMEMORY MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose AgentRecall for knowledge & memory work as a local process; choose NMEMORY for knowledge & memory. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose AgentRecall when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
session_start, remember, recall.
Choose NMEMORY when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You want tools like
memory_ingest, memory_retrieve, memory_digest.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 68/100 · Great | 45/100 · Fair |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 371 | 9 |
| Directory activity | 5 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 5 | 5 |
| Full listing | View AgentRecall | View NMEMORY |
Tools & capabilities
AgentRecall tools 5
session_startLoads corrections, insights and `watch_for` warnings for the projectrememberSaves one fact; auto-routes to journal / palace room / corrections / awarenessrecallRanked search across every store (RRF), with `useful` feedback that re-weights future rankingcheckMatches the plan against known corrections; returns `verdict: "blocked"` when one overrides itsession_endWrites the journal, promotes insights, records trajectory, optionally opens/closes a pipeline phase
NMEMORY tools 5
memory_ingestcapture with a birth certificate: no source + anchor, no storage.memory_retrieverecall as evidence: grounded, missing_evidence, or an honest abstain.memory_digestsession-start projection: what you know, what's ready, what's blocked.memory_relatethe five edges you reach for daily, out of nine declared: supersedes, derived_from, witnesses, blocks, and `falsifies` (a disproven fact stops grounding recall, but the evidence stays). The other four — `proposes`, `part_of`, `grounded_in`, `about` — are in the tool surface below.memory_forgettombstones with audit, never silent deletion.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
AgentRecall
{
"mcpServers": {
"goldentrii-agentrecall": {
"command": "npx",
"args": [
"-y",
"agent-recall-mcp"
]
}
}
}
NMEMORY
No confirmed install command for NMEMORY yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
AgentRecall is categorized under Knowledge & Memory and uses a local stdio subprocess. NMEMORY belongs to Knowledge & Memory and uses an install path we have not confirmed yet. Pick AgentRecall for knowledge & memory work and NMEMORY for knowledge & memory.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. NMEMORY has no confirmed install command yet — follow its own setup instructions.
AgentRecall is listed as free. Auth: no auth required. NMEMORY has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add goldentrii-agentrecall and nmemory as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, AgentRecall has a quality signal of 68/100 (Great) with 5 views, 0 installs and 371 GitHub stars. NMEMORY has 45/100 (Fair) with 1 views, 0 installs and 9 GitHub stars.