Skip to content

Release Notes

Jump to bottom
Bellok edited this page Mar 28, 2026 · 7 revisions

Release Notes

Back to Home

Release history for the Neurodivergent Memory MCP Server. All 0.x releases are research previews.

v0.1.3 — 2026-03-28

First fully successful multi-channel release in this project lifecycle.

What Changed

Improves package visibility in GitHub by publishing container images to GitHub Container Registry (GHCR) in addition to Docker Hub.

Fixed

  • Release workflow now publishes container images to ghcr.io/jmeyer1980/neurodivergent-memory
  • Added packages: write workflow permissions required for GHCR publishing
  • GitHub Packages listing now available through GHCR package pages linked to this repository

Delivery Channels

Channel Package / Image
npm neurodivergent-memory@0.1.3
GitHub Release Assets Tagged release with checksum artifacts
Docker Hub twgbellok/neurodivergent-memory:0.1.3
GitHub Container Registry (GHCR) ghcr.io/jmeyer1980/neurodivergent-memory:0.1.3

Supply-Chain and Integrity Controls

  • Provenance-aware npm publishing with OIDC attestation
  • Package and container attestations
  • Checksum generation on release artifacts
  • Multi-architecture container builds (linux/amd64, linux/arm64)

Workflow Hardening Incorporated (cumulative through 0.1.x)

Fix Effect
Automatic release-branch sync on version tags main and release branches stay in sync after every release
Rerun-safe npm publish skip Reruns do not fail on already-published versions
GHCR publication with required permissions Container images are publicly visible on GitHub Packages

v0.1.2 — 2026-03-28

Release pipeline reliability and publish resiliency.

Fixed

  • Release workflow now syncs release branch with main on version tag pushes
  • Release workflow now skips npm publish when the version already exists on npm (rerun-safe)
  • Continued hardening for GitHub Actions JavaScript runtime migration to Node 24

v0.1.1 — 2026-03-28

Initial feature-complete research preview release.

Added

  • Core MCP Server — Knowledge graph storage and retrieval via Model Context Protocol stdio transport
  • 5-District Architecture — Semantic organization across logical_analysis, emotional_processing, practical_execution, vigilant_monitoring, and creative_synthesis
  • BM25 Full-Text Search — Relevance-ranked memory retrieval with configurable scoring and filtering (k1=1.5, b=0.75)
  • Graph Connections — Bidirectional edges between memory nodes for associative traversal
  • Canonical Tag Schema — Enforced tagging (topic, scope, kind, layer) for structured knowledge organization
  • Emotional Metadata — Optional emotional_valence (-1–1) and intensity (0–1) per memory
  • Memory Archetypes — Automatic archetype assignment (Scholar, Merchant, Mystic, Guard) per district
  • Persistence — JSON-based durable storage at ~/.neurodivergent-memory/memories.json
  • 11 Tools — store_memory, retrieve_memory, search_memories, delete_memory, connect_memories, traverse_from, related_to, list_memories, memory_stats, import_memories, update_memory
  • 2 Prompts — explore_memory_city, synthesize_memories
  • Resources — memory:// URI scheme for accessing memories and districts
  • Docker Support — Multi-platform container images (amd64, arm64) with provenance and SBOM attestation
  • Security — npm provenance publishing, container attestation, checksums on release artifacts

Fixed

  • Test script hang prevention: Added adaptive timeout and completion detection to prevent indefinite stdin blocking

Known Limitations (as of v0.1.1)

  • Single-file persistence — no Journal/WAL pattern; risk of data loss on unclean shutdown
  • No concurrency control — unsafe for simultaneous writes from multiple agents
  • Static districts — cannot adapt semantic organization per use case
  • Basic query language — BM25 ranking ignores agent goals or context
  • No observability — no logging, metrics, or debug endpoints
  • No resource controls — unbounded memory growth potential

These limitations are tracked on the Roadmap.

Agentic Value — Current State (v0.1.3)

Current Strengths

  • Single-agent memory workflows
  • Structured reflection and recall
  • Early-stage multi-agent experiments

Current Constraints

The project remains pre-1.0 and is not yet suitable for high-criticality production workloads due to gaps in:

  • Concurrency control
  • Durability and recovery guarantees
  • Observability and operations telemetry
  • Orchestration-native control surfaces

See also: Architecture · Roadmap · Experiment-Report · White-Paper

Home

Setup

Reference

Reports

v0.3.0 · Research Preview

npm · Docker Hub · GHCR

Clone this wiki locally