Skip to main content
Glama
124,822 servers. Updated
Browse by product
20 Best Memory MCP Servers: compared and ranked, November 2026Ranked from 5,520 matching servers on stars, growth, downloads and maintenance. Updated .

Matching MCP tools:

Matching MCP Connectors:

"Finding the best memory MCPs for in-session management" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    C
    maintenance
    Exposes remote, agent-facing MCP endpoints over Streamable HTTP for web search, webpage parsing, local knowledge-base retrieval and document creation, and delegation of tasks to configurable LLM providers. Also bundles an admin console with onboarding, provider/model configuration, API-key management, and call logging.
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    A local, read-only MCP server (plus CLI) over your own stock/ETF transaction log. A deterministic core computes drawdown-first risk with bootstrap confidence intervals and validates targets with walk-forward verdicts. The assistant narrates, but the number fence makes it structurally impossible for the model to produce a figure.
    8
    1
    AGPL 3.0
  • A
    license
    B
    quality
    D
    maintenance
    A fully local persistent memory layer for LLM coding agents (Claude Code, Codex, Gemini CLI, OpenCode). A shell wrapper intercepts tool invocations, fires hooks on every tool call, then runs a 3-layer pipeline (extract → compress to ≤500-token digest → merge into project memory doc) at session end. The next session gets prior context injected automatically.
    6
    1
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    Enables users to describe their LLM fine-tuning job once and get the cheapest, fastest, and most balanced GPU options across a dozen cloud providers in seconds.
    7
    104
    MIT
  • A
    license
    C
    quality
    C
    maintenance
    Persistent project memory for AI models and coding agents. Memory MCP stores architecture, decisions, tasks, warnings, preferences, and session state in Supabase so OpenCode, Claude Code CLI, Qwen Code, Codex, or any MCP-compatible client can resume work without losing context.
    22
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A lightweight MCP server that gives Claude Code Channels on Telegram persistent memory by storing facts, conversation logs, and session summaries in Supabase.
    9
    MIT
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning workload and receive ranked, cost- and runtime-optimized GPU recommendations across multiple cloud providers by estimating VRAM and FLOPs.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning job once and receive the cheapest, fastest, or most balanced GPU hardware options across a dozen cloud providers by calculating required VRAM/FLOPs and aggregating live pricing.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning workload once and get task-aware VRAM/FLOPs estimates plus ranked cheapest, fastest, and balanced GPU recommendations across multiple cloud providers.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning job and receive ranked GPU recommendations across a dozen cloud providers based on estimated VRAM/FLOPs, live pricing, cost, and speed. It returns cheapest, fastest, and balanced hardware options without manual comparison.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning workload once and get ranked, cost- and speed-optimized GPU recommendations across multiple cloud providers by estimating VRAM/FLOPs requirements.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning job once and receive VRAM/FLOPs-aware recommendations for the cheapest, fastest, or most balanced GPU options across a dozen cloud providers.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    It enables users to describe an LLM fine-tuning workload once and receive task-aware VRAM/FLOPs estimates plus ranked cheapest, fastest, or balanced GPU recommendations across multiple cloud providers.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe a fine-tuning workload once and receive task-aware VRAM/FLOP estimates plus ranked cheapest, fastest, and balanced GPU options across multiple cloud providers. It can be used from Claude Code/Desktop or CLI/API to identify viable hardware options without manually comparing provider pricing.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning job in natural language and receive ranked GPU recommendations from a dozen cloud providers, based on estimated VRAM and FLOPs requirements. It surfaces the cheapest, fastest, and most balanced hardware options while disclosing the source and freshness of each price.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning workload once and receive ranked, task-aware GPU recommendations across a dozen cloud providers based on required VRAM/FLOPs, cost, and runtime. It surfaces the cheapest, fastest, and balanced options through MCP so coding assistants can plan training hardware without manual price comparison.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning workload once and get task-aware VRAM/FLOPs calculations with cheapest, fastest, and balanced GPU recommendations across a dozen cloud providers. It supports CLI, REST API, and natural-language MCP integration without manual price comparison.
    -
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to describe an LLM fine-tuning workload and automatically estimate VRAM/FLOPs to recommend the cheapest, fastest, and balanced GPU options across multiple cloud providers. It supports natural-language requests through MCP, returning structured ranked hardware recommendations without manual price comparison.
    -
  • A
    license
    A
    quality
    C
    maintenance
    Real human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.
    7
    47 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    A vendor-agnostic cognitive persistence layer for AI agents. Eliminate the "repetition tax" by transporting your context, preferences, and history across sessions. Features an auto-adaptation engine that syncs global instructions to ensure operational cohesion and optimize token usage across any LLM or multi-agent workflow.
    38
    6
    Apache 2.0
  • A
    license
    A
    quality
    D
    maintenance
    Provides persistent memory for AI assistants via MCP, enabling them to store and recall facts, preferences, and tasks across conversations using either local file storage or a cloud backend with semantic search.
    5
    7 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables AI assistants across Claude Code, Claude Desktop, Codex CLI, and Gemini CLI to remember and automatically apply user-confirmed behavioral instruction presets, with a trust curve for scheduled re-confirmation and one-command uninstall.
    9
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables AI agents to maintain a three-layer memory that decays, consolidates offline through dreaming, and revises impressions, with tools for observing, recalling, tracing, pinning, compacting, and exporting diary entries.
    9
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Two-layer memory for AI agents. Episodes compress into identity. The only MCP memory server with an immune system. Patterns earn permanence through evidence, false knowledge gets caught and demoted, and stale information fades — so your agent's memory gets smarter over time, not just bigger. Zero dependencies. 5 tools. Works with any MCP client.
    17
    2,731 PyPI
    12
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP clients to lint stored agent facts for duplicates, contradictions, and staleness (including implicit conflicts found via local embeddings), and to gate a new fact for admission before it is persisted. It runs read-only over stdio, never writing to a store or calling the network.
    2
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables MCP clients to give AI agents persistent long-term memory with remember, recall, forget, and list operations over local SQLite storage, using Ollama embeddings for semantic search and keyword fallback when needed.
    4
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Cognitive memory engine for AI agents with 5,100+ knowledge modules, circadian rhythm awareness, emotional state tracking (PAD model), and hybrid semantic search. Supports persistent per-user memory, project-scoped contexts, and multi-protocol access.
    26
    23
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides AI coding agents with a local knowledge-graph memory, enabling cross-project retrieval via PageRank diffusion and tools to retrieve, write, extract, update, and view recent knowledge over MCP.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables local ingestion, querying, consolidation, keyword search, and statistics of agent memories through upstream Google ADK memory agents backed by SQLite, exposed over Streamable HTTP.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to store, search, and recall semantic memories with three memory types (semantic, episodic, procedural) and auto-consolidation, compounding intelligence over time.
    21 npm
    MIT