github Python analyzed 996ca6e

Who-Visions/NouGenShards

github

Local-first AI memory for coding agents. NouGenShards stores reusable "shards" in a local SQLite + FTS5 database with outcome-weighted retrieval, so agents recall what worked instead of re-prompting. Your agents have prompts — mine have shards.

maintainer
Who-Visions
licence
NOASSERTION
first seen
2026-06-11
last seen
2026-09-08
releases · 30d
0
short id

Who-Visions/NouGenShards is an MCP server distributed on github, maintained by Who-Visions, tracked here since June 2026. It has shipped 3 releases and exposes 38 tools. Tools include agy_ask, apply_skills, ask_agent, ask_dav1d, ask_iris, ask_rhea, and 32 more. Its composite risk grade is D — an inferred review prompt computed from observed signals, not a verdict.

what we found

Reading the source raised one review prompt — dangerous code — each a pattern worth a human look rather than a finding of fault.

Its 38 tools appear to reach filesystem, shell / exec, network, secrets and database, inferred from tool names, descriptions and input schemas rather than from observed behaviour.

Since the previous scan on 2026-09-08: 24 tools added.

full security breakdown →
tools 20 of 38
  • agy_ask
  • apply_skills
  • ask_agent
  • ask_dav1d
  • ask_iris
  • ask_rhea
  • ask_xoah
  • capture_experience
  • dav1d_exec
  • evaluate_quota
  • evolve_skill
  • execute_sandboxed_code
  • get_memory_stats
  • get_shard
  • link_shards
  • list_agents
  • list_skills
  • load_skill
  • log_context_event
  • mark_utility
All 38 tools →
release cadence · 90d 3 releases
06-13 00:00 07-27 00:00 now
recent releases last 3
version date src
v1.3.0 2026-08-01 github
v1.2.0 2026-08-01 github
v1.1.0 2026-06-15 github

view all →