Skip to main content
Glama
LinkedParticles

Particles

Official
by LinkedParticles
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to Particles

No user-submitted related servers found.

    Related Servers

    • memorygraph

      xbrxr03
      A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to record, recall, correct, and forget evidence-backed factual claims with temporal history, while explaining whether remembered information is current, historical, or contested.
      5
      Apache 2.0

    • Omem

      troybrandonc-bit
      A
      license
      Not graded
      quality
      A
      maintenance
      Belief-tracking memory for AI agents. Remember, recall, and ask why: every memory carries evidence, contradictions are surfaced, and retracted facts take their conclusions with them. Zero dependencies, local, MIT.
      MIT

    • Talamus

      ampres-ai
      A
      license
      Not graded
      quality
      A
      maintenance
      Local-first, source-grounded memory for AI agents, with citations, bitemporal history, review-gated corrections, and MCP tools for search and recall.
      66 PyPI
      3
      Apache 2.0

    • mcp-haki

      GetHaki
      A
      license
      Not graded
      quality
      C
      maintenance
      Self-hosted long-term memory for AI agents on your own Postgres. Facts are dated, versioned and superseded rather than silently overwritten, every recall ships with an inspectable trace, and agents can correct wrong memories from inside the conversation.
      2
      Apache 2.0

    • al-buddy-memory-mcp

      flytomoon
      A
      license
      Not graded
      quality
      A
      maintenance
      Gives AI agents governed, provenance-tagged memory where facts are invalidated rather than deleted and every recall result carries validity dates, confidence, and replacement links. Stores memory in a local SQLite file with tools for remembering, recalling, invalidating, and pinning facts, plus policy enforcement and an audit trail.
      406 npm
      3
      Apache 2.0

    • kepta

      DamianTodorovic
      A
      license
      Not graded
      quality
      A
      maintenance
      Local memory for AI agents in one SQLite file on your own machine. Facts carry a validity window and a confidence score, so an outdated one is superseded and downweighted rather than deleted, and retrieval fuses BM25, vector similarity and a knowledge graph.
      2
      Business Source 1.1
    Deploy Server
    Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

    TDQS

    A3.7/5.0

    Scored across 16 tools

    Disambiguation4/5

    Most tools target clearly distinct operations: particle listing/show/search, subject listing/search/show, taxonomy listing, corpus listing, lint, quality reporting, event inspection, link suggestions, and graph rendering. The broad `query` tool overlaps somewhat with `particles_list` and `particle_search`, but the descriptions make the lightweight/fingerprint/semantic boundaries reasonably clear. The two link-suggestion tools are similar in naming but operate on different domains, so careful reading is still needed.

    Naming Consistency3/5

    The set mixes conventions: core tools mostly use noun_action patterns (`particles_list`, `particle_show`, `subjects_search`), but others use verb_noun (`list_taxonomies`, `list_corpus_entries`) or standalone names (`query`, `lint`, `graph_view`, `quality_report`). Singular/plural usage also varies (`particle_show` vs `subjects_show`, `events_list` vs `event_show`). All names remain readable and snake_case, but the pattern is not fully predictable.

    Tool Count4/5

    At 16 tools, the surface is slightly above the typical ideal range, but the domain is complex and each tool maps to a fairly distinct read-only inspection, query, reporting, or suggestion capability. The count feels justified rather than bloated, though a few tools could conceivably be consolidated.

    Completeness4/5

    The read-only surface covers particles, subjects, taxonomies, corpus entries, events, lint findings, quality reporting, link suggestions, and graph views, which is broad lifecycle coverage for an inspection-oriented MCP server. Minor gaps remain: there is no dedicated tool to show a full corpus entry, and `graph_view`'s manifest scope has no manifest/section discovery tool. These are workable gaps rather than severe dead ends.

    Maintenance

    ActivityActive
    ResponsivenessUnresponsive

    Resources