Ori Memory vs StashBase
A side-by-side look at the Ori Memory and StashBase MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
S
StashBaseKnowledge & MemoryAn open-source, local-first writing workspace where you can write with Claude Code and Codex, drawing on your own sources and past work.49FairAuth: not declaredVerdict: choose Ori Memory for knowledge & memory work as a local process; choose StashBase for knowledge & memory. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Ori Memory when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- You want tools like
ori_wake, ori_update, ori_update_decision.
SChoose StashBase when
- You need dedicated capabilities in the Knowledge & Memory domain.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | S StashBase | |
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 64/100 · Good | 49/100 · Fair |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | Not declared | Not declared |
| Pricing | Not declared | BYOK (pay the provider) |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 332 | 1,109 |
| Directory activity | 2 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 15 | Not listed |
| Full listing | View Ori Memory | View StashBase |
Tools & capabilities
Ori Memory tools 15
ori_wakeSession boot: bounded briefing, plus onboarding on a fresh vaultori_updateWrite to identity, goals, methodology, daily, or remindersori_update_decisionRecord the user's answer to an update noticeori_whats_newRelease notes for the installed version, or any versionmemory_sqlRead-only SQL over the index — anything the ranking tools cannot expressori_healthFull diagnosticsori_addCapture to inboxori_promotePromote with classification, linking, and area assignmentori_validateSchema validationori_query_rankedFull retrieval with Q-value reranking, co-occurrence PPR, and stage meta-learningori_query_similarSemantic search (vector only, faster)ori_warmthInspect the associative warmth field- +3 more on the listing page
StashBase tools
No tool names declared yet. Check the project README from the listing page.
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.
Ori Memory
{
"mcpServers": {
"ori-memory-2": {
"command": "npx",
"args": [
"-y",
"ori"
]
}
}
}
StashBase
No confirmed install command for StashBase yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
Ori Memory is categorized under Knowledge & Memory and uses a local stdio subprocess. StashBase belongs to Knowledge & Memory and uses an install path we have not confirmed yet. Pick Ori Memory for knowledge & memory work and StashBase 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. StashBase has no confirmed install command yet — follow its own setup instructions.
Ori Memory has no declared pricing — check the project's own site. StashBase is bring-your-own-key: usage is billed by the API provider you supply a key for. 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 ori-memory-2 and stashbase-2 as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Ori Memory has a quality signal of 64/100 (Good) with 2 views, 0 installs and 332 GitHub stars. StashBase has 49/100 (Fair) with 0 views, 0 installs and 1,109 GitHub stars.