npm Python analyzed 1.2.5 no deep scan

syncable-dev/memtrace-public

v1.2.5
npm

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.

maintainer
syncable-dev
licence
NOASSERTION
first seen
2026-06-07
last seen
2026-09-17
releases · 30d
93
short id

Drift inferred · capture-to-capture

tool count over time

06-14 04:33 now
22t
22t
capabilities 22 tools
transport stdio counts 22 tools · 0 res · 0 prompts permission surface via README inference

tools

  • analyze_relationships

    callers, callees, hierarchy, imports

  • calculate_cyclomatic_complexity
  • detect_changes

    diff-to-symbols scope mapping

  • execute_cypher

    direct graph queries

  • find_api_calls
  • find_api_endpoints
  • find_bridge_symbols

    betweenness centrality

  • find_central_symbols

    PageRank / degree

  • find_code

    hybrid BM25 + semantic + RRF

  • find_dead_code

    zero-caller detection

  • find_most_complex_functions

    complexity hotspots

  • find_symbol

    exact / fuzzy with Levenshtein

  • get_api_topology

    cross-repo HTTP graph

  • get_evolution

    6 scoring modes

  • get_impact

    blast radius with risk rating

  • get_repository_stats
  • get_symbol_context

    360° view in one call

  • get_timeline

    full version history

  • index_directory

    parse, resolve, embed

  • list_communities

    Louvain modules

  • list_processes

    / get_process_flow

  • watch_directory

    live incremental

skills & danger signals github-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v1.2.5 · analyzer v33 · 1d ago

skills & prompt files 30

code evidence v1.2.5 · github-tarball
evidence-backed findings quoted directly from the published source artifact — not inferred

code files: 166

No code evidence — the analyzed source reached for no tracked permissions, tools, or hooks.