Skip to main content
Glama
62,291 servers. Last updated

Matching MCP tools:

Matching MCP Connectors:

"Understanding Persistent Memory and Context Management" matching MCP servers:

  • asset-management

    disin7c9
    A
    license
    A
    quality
    A
    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.
    Last updated
    10
    8
    1
    AGPL 3.0

  • mem-context

    turbyho
    A
    license
    A
    quality
    A
    maintenance
    Multi-modal RAG engine for AI assistants. Stores conversation history, conclusions, diffs, error traces, and other development artifacts in LanceDB with vector search, multi-factor scoring, and an LLM-driven consolidation pipeline.
    Last updated
    10
    MIT

  • marm-memory

    Lyellr88
    A
    license
    A
    quality
    A
    maintenance
    MARM MCP provides persistent memory and structured session context beneath any AI tool, so your agents learn, remember, and collaborate across all your workflows.
    Last updated
    14
    320
    Apache 2.0

  • repo-memory

    yubinkim444
    A
    license
    A
    quality
    B
    maintenance
    A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep
    Last updated
    5
    1
    MIT

  • anneal-memory

    phillipclapham
    A
    license
    A
    quality
    A
    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.
    Last updated
    16
    9
    MIT

  • celiums-memory

    terrizoaguimor
    A
    license
    A
    quality
    B
    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.
    Last updated
    26
    18
    Apache 2.0

  • MCP Roo Memory

    mcasdfgf
    A
    license
    -
    quality
    B
    maintenance
    Persistent, graph-based memory for Roo Code via the Model Context Protocol, enabling structured knowledge management with semantic search and context window control.
    Last updated
    17
    1
    MIT

  • Context-first

    XJTLUmedia
    A
    license
    A
    quality
    D
    maintenance
    Long AI conversations fail in predictable ways. Context-First fixes all four: Failure Mode What Goes Wrong Context-First Solution Context Drift AI forgets earlier decisions and intent as the conversation grows context_loop + detect_drift continuously re-anchor every turn Silent Contradiction New inputs silently overrule established facts — the AI doesn't notice detect_conflicts compares every inp
    Last updated
    8
    1
    MIT

  • open-context

    incu6us
    A
    license
    A
    quality
    C
    maintenance
    A high-performance MCP server providing up-to-date documentation for Go, npm, Python, Rust, Docker, Kubernetes, Terraform, and more — fetched from official sources, not training data.
    Last updated
    18
    3
    MIT

  • AI HR Management Toolkit

    XJTLUmedia
    A
    license
    A
    quality
    D
    maintenance
    Manage Job using MCP: Manage Job, Candidates, Resumes, Salaries all within this one MCP tools It can solve problems like: You have 50 resumes to screen. Your AI assistant can reason about candidates, but it can't: Read PDFs/DOCX — The AI can't open binary files Extract structured data — Copy-pasting loses formatting, metrics, and context Compare at scale — No consistent scoring across candida
    Last updated
    24
    100
    1
    MIT