Skip to main content
Glama
LiLara-AI

ShadowGraph

Official
by LiLara-AI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Related Servers

Alternatives to ShadowGraph

No user-submitted related servers found.

    Related Servers

    • kaeru memory

      LamantinAI
      F
      license
      B
      quality
      A
      maintenance
      Memory for LLM agents: a local graph where the agent keeps decisions, tasks, hypotheses and reasoning between sessions, and gets a summary of what is open and overdue on every return to a project. Works with Claude Code, Codex, Cursor and opencode. Single Rust binary, no embedding model or LLM calls. Source-available (BSL 1.1), commercial use permitted.
      71
      40
      -
    • litopys by litopys-dev

      litopysofficial

      litopys-dev
      A
      license
      Not graded
      quality
      B
      maintenance
      Persistent graph-based memory for AI agents, stored as plain markdown — no vector DB. Typed nodes and 11 relation types via 5 MCP tools (search, get, create, link, related), stdio and HTTP/SSE transports.
      3
      MIT

    • midas-memory-mcp

      vornicx
      A
      license
      A
      quality
      B
      maintenance
      Local-first, source-traceable memory for AI agents — no LLM at ingest, $0 per message, zero data egress. Gives Claude Code, Cursor, and any MCP client one shared persistent memory with semantic recall, belief revision, selective forgetting, and a provenance guard that blocks acting on stale or unconfirmed memories.
      23
      17 PyPI
      15
      MIT

    • robrain

      adelinamart
      A
      license
      A
      quality
      A
      maintenance
      Self-hosted decision memory for AI coding agents. Captures decisions with the alternatives you rejected, and warns before an agent re-proposes a rejected approach.
      4
      82
      Apache 2.0
    • Memryzed by memryzed

      Memryzedofficial

      memryzed
      F
      license
      Not graded
      quality
      C
      maintenance
      Local-first cross-agent memory for AI coding agents. Persistent, shared memory over MCP — what you tell one agent can be recalled by another — with all data stored in a single local SQLite file, no cloud and no API keys.
      -
    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

    A4.1/5.0

    Scored across 27 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes and the descriptions cross-reference related tools, so an agent can usually select correctly. However review vs review_signals and search/retrieve/recall are close enough that a model needs to read carefully to avoid selecting the wrong read/evaluate variant.

    Naming Consistency4/5

    All tools share the shadowgraph_ prefix and snake_case style, which gives the surface a consistent feel. But the pattern mixes bare verbs (review, rebuild, search), noun phrases (context, journal, confidence_evidence), and verb_noun forms (record_decision, purge_preview), so it is not fully predictable.

    Tool Count2/5

    27 tools is above the threshold for a heavy surface, and several clusters are over-fragmented: search/retrieve/recall/context/traverse, review/review_signals, and purge/purge_preview could be consolidated. While the domain is broad, the count feels excessive for an agent to navigate.

    Completeness4/5

    The core decision/memory lifecycle is well covered: record, recall, update, supersede, review, backup, restore, purge. The main gaps are the explicitly missing unlink operation for relationships and no direct apply tool for repair_plan, though agents can work around these via other tools.

    Maintenance

    ActivityActive
    ResponsivenessNo issues

    Resources