Skip to content
Agentmart
Submit a tool

SMRITI Memory

Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.

Connector by smriti-memcore · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 3
Write a review

Chalk Labs

Need help deploying SMRITI Memory?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/smriti-memcore-smriti-memory

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.

Use cases: agent-memory, knowledge-base

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
8 read · 8 write · 0 delete · 3 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 19

Read from the source code; the running server may list different tools.

Read 8 · Look things up without changing anything.

  • amp.recall
  • amp.stats
  • smriti_get_context
  • smriti_get_suggestions
  • smriti_how_well_do_i_know
  • smriti_knowledge_gaps
  • smriti_recall
  • smriti_stats

Write 8 · Create, change, send or run things.

  • amp.consolidate
  • amp.encode
  • amp.pin
  • smriti_consolidate
  • smriti_create_private_room
  • smriti_encode
  • smriti_pin
  • smriti_sync_obsidian

Not yet classified 3 · We could not tell from the name and description.

  • amp.forget
  • smriti_forget
  • smriti_open_ui

Network hosts it talks to 6

  • api.anthropic.com · found in code
  • api.openai.com · found in code
  • d3js.org · found in code
  • fonts.googleapis.com · found in code
  • generativelanguage.googleapis.com · found in code
  • github.com · found in code

Files it touches

  • ~/.claude.json
  • ~/.claude/settings.json
  • /tmp/locomo_repo/data/locomo.json
  • /tmp/locomo_repo/data/locomo10.json
  • /tmp/smriti_bench
  • /tmp/smriti_install_test
  • /Users/shivtatva/.smriti/global
  • /Users/shivtatva/.smriti/venv/bin/python3
  • Your home directory (~)
  • ~/.codeium/windsurf/mcp_config.json
  • ~/.continue/config.json
  • ~/.cursor/mcp.json
  • ~/.cursorrules
  • ~/.gemini/antigravity-ide/mcp_config.json
  • ~/.gemini/antigravity/mcp_config.json
  • ~/.gemini/config/mcp_config.json
  • ~/.smriti/config.json
  • ~/.smriti/global
  • ~/.smriti/global/palace/palace.json
  • ~/.smriti/personas
  • ~/Flex/Obsidian-vault/flex-vault/Palace
  • Any path the agent passes to its tools

Tools (19)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • amp.consolidate

    [Write / State-Modifying] Trigger backend consolidation. (AMP Full verb) depth: "light" (fast) or "full" (thorough). Returns {status: "ok", memories_processed: int}.

  • amp.encode

    [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"}. IMPORTANT — encoding discipline. Label unverified diagnoses as hypotheses, not facts. Cite the evidence (file:line, sha, tool output) for any factual claim. A fix that made one test pass is a hypothesis with a passing test, not a confirmed root cause. Re-label or remove memories that turn out wrong rather than le…

  • amp.forget

    [State-Modifying / Archive] Permanently forget a memory. (AMP Core verb) Returns {status: "forgotten"} or {status: "not_found"}.

  • amp.pin

    [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"}.

  • amp.recall

    [Read-Only] Retrieve memories relevant to a query. (AMP Core verb) Returns {results: [{id, content, score, timestamp, status}, ...]}. Archived memories are excluded by default.

  • amp.stats

    [Read-Only] Return backend statistics. (AMP Core verb) Always includes memory_count (int). May include episode_buffer and retrieval stats.

  • smriti_consolidate

    [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 means "let the scheduler decide" and is not useful as an explicit call.

  • smriti_create_private_room

    [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 automatically inherited by memories at encode time. Returns {"room_id": ..., "topic": ..., "visibility": "private"}.

  • smriti_encode

    [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 insufficient salience. source: "direct" (default), "user_stated" (highest trust, confidence=1.0), "inferred", or "external" modality: "text" (default), "code", "image", "structured" private: if True, memory is marked private and excluded from team consolidation sync IMPORTANT — encoding discipline. Labe…

  • smriti_forget

    [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.

  • smriti_get_context

    [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.

  • smriti_get_suggestions

    [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.

  • smriti_how_well_do_i_know

    [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, should_recall_or_ask() for the decision — these are separate MetaMemory methods.

  • smriti_knowledge_gaps

    [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.

  • smriti_open_ui

    [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.

Show 4 more tools
  • smriti_pin

    [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.

  • smriti_recall

    [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.

  • smriti_stats

    [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.

  • smriti_sync_obsidian

    [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 inside the Obsidian vault. If omitted, falls back to the SMRITI_OBSIDIAN_PATH env var. Returns an error if neither is set. Returns: { status, rooms_written, files_written, vault_path }

Signals

Stars
3
Forks
0
Open issues
4
Weekly downloads
423
Last commit
Oct 23, 2026 (8 days ago)
Last release
Oct 22, 2026 (8 days ago)
Last package publish
Oct 22, 2026 (8 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.smriti-memcore/smriti-memory
Version
1.4.28
Auth
No auth
Packages
pypi smriti-memcore
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same server elsewhere

Copies of this server published by others; search shows only one of them.

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get SMRITI Memory running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying SMRITI Memory?

CallGet help
Cite this page

SMRITI Memory MCP server. Agent Mart. https://agentmart.dev/connectors/smriti-memcore-smriti-memory (last updated 2026-10-24)