Skip to main content
Glama
ClickHouse Loom

ClickHouse Loom

Official

Related Servers

Alternatives to ClickHouse Loom

  • A
    license
    A
    quality
    D
    maintenance
    A server that provides data retrieval capabilities powered by Chroma embedding database, enabling AI models to create collections over generated data and user inputs, and retrieve that data using vector search, full text search, and metadata filtering.
    13
    87,391 PyPI
    602
    Apache 2.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that provides Claude CLI with a Graphiti knowledge-graph memory backed by Neo4j, featuring synchronous writes and no silent ingestion failures.
    Apache 2.0
  • A
    license
    A
    quality
    C
    maintenance
    Enables Claude Desktop to interact with Windows Subsystem for Linux (WSL) environments, allowing command execution, file management, and distribution inspection from natural language.
    7
    MIT

Related Servers

  • A
    license
    A
    quality
    C
    maintenance
    Self-hosted MCP-native agent memory server. Gives AI agents persistent, decay-weighted memory via 83 MCP tools — no cloud, full control. RocksDB+HNSW backend. Works with Claude Code, Cursor, and any MCP-compatible agent.
    14
    9
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Local-first MCP server that gives any AI coding agent per-project memory, workflow intelligence, and always-on, lossless token & context optimization.
    37
    65 npm
    6
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Self-hosted AI Agent Memory + Code Intelligence Platform providing persistent memory, AST-aware code search, and quality enforcement via a single MCP endpoint.
    105
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    A local-first MCP server that gives AI coding agents persistent memory and controlled commands. Features a git-backed markdown knowledge vault with FTS5 search, surgical section edits, token-aware context budgeting, and a sandboxed command engine with human approval gates. Works with Claude Code, Cursor, Copilot, Gemini, and more.
    58
    196 npm
    1
    Apache 2.0

TDQS

A4.1/5.0

Scored across 13 tools

Disambiguation3/5

The set has several overlapping write/mutate paths — memory_set vs memory_update vs memory_pin vs memory_apply vs memory_lock — that all touch stored facts, and delete vs blacklist_add vs apply(delete) all remove data. The WHAT/WHEN/WHEN NOT structure does a lot of work to separate them, but an agent must read carefully, and the descriptions refer to phantom names (memory.set, memory.update, memory.delete) that are not the actual tool names, adding a misselection hazard.

Naming Consistency4/5

All tools are snake_case under a uniform loom_ prefix, and the memory CRUD family (loom_memory_set/get/update/delete/history) is consistently verb-last. Minor deviations exist — loom_activate and loom_search drop the resource segment while loom_context_pack is noun-only — and the bodies reference tools by a different dotted naming scheme than the actual tool names.

Tool Count5/5

13 tools is well within a healthy range for a memory service covering reads, writes, bulk apply, locking, history, and session bootstrap. Each tool earns its place: no obvious duplicates that could simply be folded together.

Completeness4/5

Core lifecycle is strongly covered — create (set/pin), read (get/search/history), update, delete, bulk apply, locking, blacklist, plus a context pack and activation primer. Gaps (whole-namespace clear, erasure requests, related/evidence/digests) are handled only through the generic loom_op escape hatch, whose arguments are not documented in the tool surface.

Maintenance

ActivityActive
ResponsivenessNo recent community issues