Skip to content
Agentmart
Submit a tool

Mengram

Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows

Connector by alibaizhanov · GitHub account verified by the MCP Registry

IndexedApache-2.0Remote (HTTP)★ 204
Write a review

Chalk Labs

Need help deploying Mengram?

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, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/alibaizhanov-mengram

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.

Remote endpoint

  • https://mengram.io/mcp Remote (HTTP)

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

Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows

Reviews

Write a review

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 and install config. Checked Oct 25, 2026.

Tools
20 read · 9 write · 2 delete · 1 not yet classified
Secrets
1 (API keys, tokens or passwords)
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 32

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

Read 20 · Look things up without changing anything.

  • ask
  • context_for
  • dedup
  • get_entity
  • get_feed
  • get_graph
  • get_insights
  • get_reflections
  • get_triggers
  • list_episodes
  • list_memories
  • list_procedures
Show 8 more tools
  • procedure_history
  • recall
  • recall_all
  • search
  • search_all
  • search_procedures
  • timeline
  • vault_stats

Write 9 · Create, change, send or run things.

  • checkpoint
  • dismiss_trigger
  • fix_entity_type
  • merge_entities
  • procedure_feedback
  • reflect
  • remember
  • remember_text
  • run_agents

Delete 2 · Delete, drop, revoke or wipe things.

  • archive_fact
  • delete_entity

Not yet classified 1 · We could not tell from the name and description.

  • generate_rules_file

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • Authorization

Network hosts it talks to 1

  • mengram.io · found in remote endpoint, install command

Files it touches

  • Any path the agent passes to its tools

Tools (32)

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

  • archive_fact

    Archive a specific fact on an entity — soft-delete without removing the entity. Use when a fact is outdated, wrong, or no longer relevant.

  • ask

    Get a synthesized answer to a question, grounded in the user's memory with citations. Use INSTEAD of 'recall' when the user asks a direct question and wants a direct answer (e.g. 'what programming languages do I use?', 'what was the last deploy issue?'). Returns a written answer with inline source attribution — multilingual native (works in Russian, Chinese, Spanish, etc). Premium feature: requires Pro / Growth / Business plan; free / starter accounts will receive a 403.

  • checkpoint

    Save a session checkpoint — summarize key decisions, learnings, and outcomes from this conversation. Lighter than 'remember': takes a structured summary instead of raw messages. Call at natural breakpoints: end of a task, after solving a bug, after making a decision.

  • context_forContext For Taskread-only

    Get relevant memory context for a specific task. Returns a compact context pack: related entities, procedures, and past events. Use at the START of a new task to load relevant background. More focused than 'recall' — returns structured context, not search results.

  • dedup

    Find and automatically merge duplicate entities. Scans all entities and merges near-duplicates (e.g. 'React' and 'React framework'). Use when user says 'clean up duplicates' or memory feels cluttered.

  • delete_entity

    Delete an entity and all its data (facts, relations, knowledge). Use when user explicitly asks to remove something from memory.

  • dismiss_trigger

    Dismiss a smart trigger without firing its webhook. Use when user wants to ignore or snooze a trigger notification.

  • fix_entity_type

    Fix an entity's type classification. Use when an entity was auto-classified incorrectly (e.g. a technology labeled as 'person'). Accepts any descriptive type string.

  • generate_rules_file

    Generate a CLAUDE.md, .cursorrules, or .windsurfrules file from memory. Creates structured project rules, conventions, tech stack, workflows, and known issues — perfect for AI coding assistants. Output can be saved directly to a file.

  • get_entity

    Get details of a specific entity — facts, relations, knowledge. Use when user asks about a specific person, project, or concept by name.

  • get_feed

    Get activity feed — recent memory changes and events. Use when user asks 'what's new in my memory?', 'show recent activity', 'memory changelog'.

  • get_graph

    Get the knowledge graph — all entities and their relationships. Use when user asks 'show my knowledge graph', 'how are things connected', 'map my memory'.

  • get_insights

    Get AI-generated insights about the user — patterns, connections, reflections from memory analysis. Call this when user asks 'what patterns do you see', 'what do you know about how I think', 'analyze my memory'.

  • get_reflections

    Get AI-generated reflections (insights and patterns found across memories). Optional scope filter: 'entity' (per-entity insights), 'cross' (cross-entity connections), 'temporal' (time-based patterns).

  • get_triggers

    List smart triggers — reminders, contradictions detected, and patterns. Use when user asks 'any reminders?', 'what should I know?', 'pending alerts'.

Show 17 more tools
  • list_episodes

    List or search episodic memories (events, interactions, experiences). Use when user asks 'what happened', 'show my recent events', 'find episodes about...'.

  • list_memories

    List all stored memory entities with their types and fact counts. Use when user asks 'what do you remember?', 'show all memories', or 'list everything you know'.

  • list_proceduresList Proceduresread-only

    List learned workflows/procedures from memory. Use when user asks 'how do I usually...', 'what's my process for...', 'show my workflows'. Returns procedures with steps, success/fail counts, and version info.

  • merge_entities

    Merge two entities into one — combines facts, relations, and knowledge. Use when there are duplicate entities (e.g. 'JS' and 'JavaScript').

  • procedure_feedback

    Record success or failure for a procedure. ALWAYS use this when the user reports that a workflow worked or failed. On failure with context, the system automatically evolves the procedure to a new improved version.

  • procedure_history

    Show how a procedure evolved over time — all versions and what changed. Use when user asks 'how has my deploy process changed', 'show procedure evolution'.

  • recallRecall Memoryread-only

    Semantic search through the user's memory — call it to retrieve what's known before answering a personal question. Use specific keywords: person names, project names, technologies. For broad questions like 'what do you know about me', search for the user's name. Multiple calls with different queries are encouraged.

  • recall_all

    Recall EVERYTHING from memory vault.

  • reflect

    Trigger AI reflection on memories — analyzes facts to find patterns, insights, and connections. Use when user asks 'analyze my memory', 'find patterns', 'what can you learn from my data?'.

  • rememberRemember

    Save knowledge from a conversation to memory — pass message pairs and the AI extracts entities, facts, relations, episodes, and procedures. Use after meaningful exchanges where the user shares personal info, preferences, decisions, or technical context worth remembering.

  • remember_text

    Save plain text to memory — the AI extracts entities, facts, and relations automatically. Use when user shares a note, snippet, URL content, or any freeform text to remember.

  • run_agents

    Run memory agents that analyze, clean, and find patterns in memory. Use 'curator' to find contradictions and stale facts, 'connector' to find hidden patterns and insights, 'digest' for weekly summary, or 'all' for everything.

  • search

    Advanced structured search — returns entities with relevance scores, facts, and knowledge snippets. Use instead of 'recall' when you need detailed results with scores for comparison or analysis.

  • search_all

    Unified search across ALL memory types — semantic, episodic, and procedural. Best for broad queries that might match different memory types.

  • search_procedures

    Search procedures by name, trigger, or step content.

  • timeline

    Search memory by time. Use when user asks 'what did I do last week', 'when did I...', 'what happened in January'. Returns facts with timestamps.

  • vault_stats

    Get memory vault statistics — total entities, facts, relations, knowledge items, and storage usage. Use when user asks 'how much do you remember', 'memory stats', or 'how big is my vault'.

Signals

Stars
204
Forks
36
Open issues
16
Last commit
Oct 23, 2026 (7 days ago)
Last release
Oct 23, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.alibaizhanov/mengram
Version
2.25.4
Auth
Bearer token
License
Apache-2.0
Repository
github.com/alibaizhanov/mengram
Website
mengram.io
First seen
Oct 24, 2026
Last checked
Oct 25, 2026
Source
Official MCP Registrygithub-graphql

More from alibaizhanov

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 Mengram 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 Mengram?

CallGet help
Cite this page

Mengram MCP server. Agent Mart. https://agentmart.dev/connectors/alibaizhanov-mengram (last updated 2026-10-25)