Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Nothing to run from here
SMRITI Memory is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
5
downloads a day
local
runs on your machine
338
downloads in 30d
What it does
Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user smriti-memory-mcp '--' uvx --from smriti-memcore smriti_install
# 2 — ask your agent for something these tools do
# smriti_encode, smriti_recall, smriti_get_context and 16 more
SMRITI Memory costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts SMRITI Memory as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user smriti-memory-mcp '--' uvx --from smriti-memcore smriti_installReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
19 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
[Write / State-Modifying] Encode information into SMRITI long-term memory. force=True bypasses the Attention Gate salience check and unconditionally stores. Returns the memory_id if stored, or {"memory_id": null, "status": "discarded"} if the Attention Gate determined the content has…
No parameter schema on file.
[Read-Only] Recall memories relevant to a query. Returns a list of memory dicts, strongest first. Every retrieval strengthens the recalled memories (testing effect). Returns empty list if nothing found.
No parameter schema on file.
[Read-Only] Get formatted working memory context for injection into a prompt. Returns the current capacity-bounded working memory (7±2 slots) as a formatted string ready to prepend to a system prompt or user message.
No parameter schema on file.
[Read-Only] Assess confidence about a topic. Returns 5 confidence dimensions (coverage, freshness, strength, depth, overall) and a decision: "recall_confidently", "recall_but_verify", or "admit_gap_and_ask". Uses two internal calls: confidence_map() for dimensions,…
No parameter schema on file.
[Read-Only] List topics SMRITI knows it doesn't know. Returns gap dicts with keys: topic, context, discovered_at (ISO string), resolved (bool). Gaps are registered when recall returns empty or confidence is below threshold.
No parameter schema on file.
[Write / State-Modifying] Mark a memory as permanent — it will never be decayed or forgotten. Returns {"status": "pinned", "memory_id": ...} on success, or {"error": ...} if the memory_id is not found.
No parameter schema on file.
[State-Modifying / Archive] Gracefully forget a memory by archiving it. Sets memory status to ARCHIVED (not deleted — a record remains). Returns {"status": "archived", "memory_id": ...} on success, or {"error": ...} if the memory_id is not found.
No parameter schema on file.
[Write / State-Modifying] Create a private semantic room in the palace. The room itself is marked private. Use this to organise a topic that should never be promoted to team-level consolidation sync. To store a private memory, encode it with private=True — room visibility is not…
No parameter schema on file.
[Write / State-Modifying] Run a consolidation cycle to organize and strengthen memories. depth="light": chunking + conflict detection only (fast, safe to call often) depth="full": all 8 consolidation processes (thorough, use periodically) Note: "defer" is intentionally excluded — it…
No parameter schema on file.
[Read-Only] Get comprehensive SMRITI system statistics. Returns a nested dict with 8 top-level keys: palace, working_memory, retrieval, consolidation, meta_memory, episode_buffer, vector_store, metrics. Also includes visibility counts (private_memories, shared_memories) in palace.
No parameter schema on file.
[Read-Only] Get proactive suggestions from SMRITI's ambient monitor. Returns a list of memory dicts — patterns and insights surfaced from background consolidation that may be relevant to the current context.
No parameter schema on file.
[Side-Effect / Launch UI] Launch the interactive Memory Browser UI in the user's default web browser. Use this when the user asks to see, visualize, or browse their memories. The UI runs locally and provides a visual graph of the Semantic Palace.
No parameter schema on file.
[Write / File Export] Export the current Semantic Palace to an Obsidian vault. Writes one .md per room + _index.md to vault_path. Safe to re-run — overwrites Palace/ cleanly. Call this after smriti_consolidate to keep the Obsidian vault in sync. vault_path: output directory…
No parameter schema on file.
[Write / State-Modifying] Store a new memory for an agent. (AMP Core verb) force=True bypasses the salience gate and always stores. private=True marks the memory as private (excluded from team consolidation sync). Returns {status: "stored", id: "..."} or {status: "below_threshold"}.…
No parameter schema on file.
[Read-Only] Retrieve memories relevant to a query. (AMP Core verb) Returns {results: [{id, content, score, timestamp, status}, ...]}. Archived memories are excluded by default.
No parameter schema on file.
[State-Modifying / Archive] Permanently forget a memory. (AMP Core verb) Returns {status: "forgotten"} or {status: "not_found"}.
No parameter schema on file.
[Read-Only] Return backend statistics. (AMP Core verb) Always includes memory_count (int). May include episode_buffer and retrieval stats.
No parameter schema on file.
[Write / State-Modifying] Mark a memory as permanent — it will never be decayed or archived. (AMP Full verb) Returns {status: "pinned"} or {status: "not_found"}.
No parameter schema on file.
[Write / State-Modifying] Trigger backend consolidation. (AMP Full verb) depth: "light" (fast) or "full" (thorough). Returns {status: "ok", memories_processed: int}.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install SMRITI Memory or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 1.4.25 · scanned 15 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings2 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digesta3a485eb33eac06c65385ab8d49b85e2402a5957ae40ce0796b4260569baaf69
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (19 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| smriti_encode | no tags | |
| smriti_recall | no tags | |
| smriti_get_context | no tags | |
| smriti_how_well_do_i_know | no tags | |
| smriti_knowledge_gaps | no tags | |
| smriti_pin | no tags | |
| smriti_forget | no tags | |
| smriti_create_private_room | no tags | |
| smriti_consolidate | no tags | |
| smriti_stats | no tags | |
| smriti_get_suggestions | no tags | |
| smriti_open_ui | untrusted-input | untrusted-input: keyword "browse" |
| smriti_sync_obsidian | no tags | |
| amp.encode | no tags | |
| amp.recall | no tags | |
| amp.forget | no tags | |
| amp.stats | no tags | |
| amp.pin | no tags | |
| amp.consolidate | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digesta3a485eb33eac06c
Scanned2026-10-15
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.4.25. Pin a release below and the command asks for exactly that one.
1.4.25
2 Sep 2026
latestNo release note was published with this version.
1.4.17
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish SMRITI Memory can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.