cal/claude-memory
1
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity
89e3ebd240
claude-memory/CORE.md
Cal Corum 7d9f95339f core: regenerate CORE.md
2026-03-05 00:00:29 -06:00

61 lines
11 KiB
Markdown
Raw Blame History

# Memory Core (auto-generated)
> Last updated: 2026-03-05 | Active memories: 223/712 | Next refresh: daily (systemd timer)
## Critical Solutions
- [N8N + Claude Code Automated Server Monitoring System](graph/solutions/n8n-claude-code-automated-server-monitoring-system-62ee21.md) - Built automated server health monitoring with N8N and Claude Code headless mode. (n8n, claude-code, automation)
- [Claude Scheduled Tasks: headless Claude Code on systemd timers](graph/solutions/claude-scheduled-tasks-headless-claude-code-on-systemd-timer-cb5e88.md) - Built a "Claude Cowork"-style scheduled task system using systemd timers and... (claude-scheduled, systemd, automation)
- [Claude Scheduled Tasks: headless Claude Code on systemd timers](graph/solutions/claude-scheduled-tasks-headless-claude-code-on-systemd-timer-cb5e88.md) - Built a "Claude Cowork"-style scheduled task system using systemd timers and... (claude-scheduled, systemd, automation)
- [Migration Script: Default-to-Named-Graph Memory Transfer](graph/solutions/migration-script-default-to-named-graph-memory-transfer-5fb6b3.md) - `/mnt/NV2/Development/cognitive-memory/scripts/migrate-memories.py` (cognitive-memory, migration, multi-graph)
- [Refactor: issue-poller.sh — replaced 5 of 6 Haiku+MCP calls with direct curl+jq Gitea API calls](graph/solutions/refactor-issue-pollersh-replaced-5-of-6-haikumcp-calls-with-436e13.md) - claude-scheduled / issue-poller automation (issue-poller, gitea-api, curl)
- [Docker MCP Gateway secrets workaround for headless Docker Engine (no Docker Desktop)](graph/solutions/docker-mcp-gateway-secrets-workaround-for-headless-docker-en-d82c52.md) - `docker mcp secret set` requires Docker Desktop's `docker-pass` CLI plugin (l... (docker-mcp-gateway, mcp, secrets)
- [Expanded health monitoring to 6 servers with per-server SSH user support](graph/solutions/expanded-health-monitoring-to-6-servers-with-per-server-ssh-e32b20.md) - Expanded CT 302 health check coverage from 3 to 6 monitored servers. (monitoring, claude-runner-monitoring, homelab)
- [Cognitive Memory v3.0: Rich Edges + Hybrid Embeddings + MCP Server](graph/solutions/cognitive-memory-v30-rich-edges-hybrid-embeddings-mcp-server-9ea720.md) - Major upgrade to cognitive-memory skill. (cognitive-memory, mcp, architecture)
- [Proxmox 7 to 8 upgrade completed successfully](graph/solutions/proxmox-7-to-8-upgrade-completed-successfully-f79b6b.md) - Successfully upgraded Proxmox from PVE 7.4-20 (kernel 5.13.19) to PVE 8.4.16... (proxmox, homelab, upgrade)
- [Agent Swarm Orchestrator: architecture decisions and lessons learned](graph/solutions/agent-swarm-orchestrator-architecture-decisions-and-lessons-99f446.md) - Built a lightweight orchestration system using Claude Code native primitives. (orchestrator, swarm, claude-code)
## Active Decisions
- [Docker Tags Composite Action: Three-Channel Branch-Based Tag Resolution](graph/decisions/docker-tags-composite-action-three-channel-branch-based-tag-f67518.md) - Created `docker-tags/action.yml` in the `cal/gitea-actions` shared composite... (gitea-actions, docker, ci-cd)
- [Extracted cognitive-memory app from skill dir to standalone project](graph/decisions/extracted-cognitive-memory-app-from-skill-dir-to-standalone-a41644.md) - Moved all application code (~6K lines) from `~/.claude/skills/cognitive-memor... (cognitive-memory, architecture, extraction)
- [Cognitive memory data dir moved to XDG-compliant path (~/.local/share/cognitive-memory/)](graph/decisions/cognitive-memory-data-dir-moved-to-xdg-compliant-path-locals-dc9c26.md) - Moved default data directory from hardcoded `~/.claude/memory/` to XDG Base D... ([\\\"cognitive-memory\\\", xdg, architecture)
- [Skill organization: scoped user skills over symlinks](graph/decisions/skill-organization-scoped-user-skills-over-symlinks-6cc417.md) - When skills need to be shared across multiple projects but not all projects,... (claude-code, skills, organization)
- [Auto-edge creation on memory_store in MCP server](graph/decisions/auto-edge-creation-on-memory-store-in-mcp-server-ee85bf.md) - Implemented auto-edge creation in `mcp_server.py` that runs after every `memo... (cognitive-memory, edges, mcp)
- [Multi-graph support: named, segregated memory namespaces for cognitive memory](graph/decisions/multi-graph-support-named-segregated-memory-namespaces-for-c-b1ba1b.md) - Implemented multi-graph support for cognitive memory (Gitea issue #1). ([\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"cognitive-memory\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\", multi-graph, architecture)
- [Removed CORE.md auto-loading from sessions — rely on MCP recall instead](graph/decisions/removed-coremd-auto-loading-from-sessions-rely-on-mcp-recall-42c9a0.md) - Removed the MEMORY.md symlink mechanism that auto-loaded CORE.md (~3K tokens)... ([\\\\\\\"cognitive-memory\\\\\\\", core-md, optimization)
- [PR Reviewer: Scheduled Poller over Webhook Trigger](graph/decisions/pr-reviewer-scheduled-poller-over-webhook-trigger-231645.md) - Chose **Approach C (scheduled poller)** over webhook-triggered (Approach A) o... (pr-reviewer, claude-scheduled, architecture)
- [PR Reviewer: Review All PRs Including AI-Generated](graph/decisions/pr-reviewer-review-all-prs-including-ai-generated-bb05e1.md) - The PR reviewer agent reviews **ALL** open PRs, including those created by th... (pr-reviewer, issue-worker, safety)
- [Issue Worker Agent: Phased Workflow Architecture](graph/decisions/issue-worker-agent-phased-workflow-architecture-45c219.md) - Rewrote the issue-worker agent at `~/.claude/agents/issue-worker.md` from a f... (claude-configs, issue-worker, agent-design)
## Key Fixes
- [Fix: Issue-poller infinite loop — PRs returned as issues by gitea-mcp list_repo_issues](graph/fixes/fix-issue-poller-infinite-loop-prs-returned-as-issues-by-git-c1a50f.md) - claude-scheduled / issue-poller automation (issue-poller, gitea, gitea-mcp)
- [Fix: SteamCMD in LXC - Missing Config and DNS Resolution Failures](graph/fixes/fix-steamcmd-in-lxc-missing-config-and-dns-resolution-failur-0381e6.md) - Cause:** SteamCMD inside LXC does not auto-detect platform. (steamcmd, lxc, proxmox)
- [Fix: N8N MCP partial updates corrupt workflows via typeVersion bumps](graph/fixes/fix-n8n-mcp-partial-updates-corrupt-workflows-via-typeversio-c30705.md) - Using `n8n_update_partial_workflow` to bump `typeVersion` values on nodes (e.... (n8n, mcp, n8n-mcp)
- [Fix: Claude Code PostToolUse hook correct JSON format](graph/fixes/fix-claude-code-posttooluse-hook-correct-json-format-be0bda.md) - Claude Code hooks were not firing because the configuration used incorrect fi... (sba-scouting, rust, claude-code)
- [Fix: sqlx in-memory SQLite pool requires max_connections=1](graph/fixes/fix-sqlx-in-memory-sqlite-pool-requires-max-connections1-1b71b1.md) - Integration tests using `:memory:` SQLite failed with "no such table" errors... (sba-scouting, rust, sqlx)
- [Fix: N8N Master Loop Discord Summary node missing URL caused silent failures](graph/fixes/fix-n8n-master-loop-discord-summary-node-missing-url-caused-401ef2.md) - The "Server Health Monitor - Master Loop" workflow (ID: `p7XmW23SgCs3hEkY`) w... (n8n, server-diagnostics, discord)
- [[gitea-actions] Add shared docker-tags composite action for multi-channel Docker tag resolution](graph/fixes/gitea-actions-add-shared-docker-tags-composite-action-for-mu-fe94f6.md) - Commits made: 1 (gitea-actions, commit, configuration)
- [Fix: Partial UUID prefix matching in cognitive memory client (git-style)](graph/fixes/fix-partial-uuid-prefix-matching-in-cognitive-memory-client-89f32e.md) - Users had to type full UUIDs when referencing memories or edges via the client. (cognitive-memory, fix, uuid)
- [[homelab] Session: automation, configuration, creation, debugging, deployment, fix](graph/fixes/homelab-session-automation-configuration-creation-debugging-45b017.md) - Files edited (5): (homelab, automation, configuration)
- [[major-domo] Session: deployment, fix, tooling](graph/fixes/major-domo-session-deployment-fix-tooling-4001e9.md) - Work types: deployment, fix, tooling (major-domo, deployment, fix)
## Configurations
- [CT 302 claude-runner provisioned for server diagnostics](graph/configurations/ct-302-claude-runner-provisioned-for-server-diagnostics-5da446.md) - VMID:** 302, **IP:** 10.10.0.148, **Hostname:** claude-runner (proxmox, homelab, monitoring)
- [n8n-mcp server setup for Claude Code via mcp-manager](graph/configurations/n8n-mcp-server-setup-for-claude-code-via-mcp-manager-1d8200.md) - Added `n8n-mcp` (czlonkowski/n8n-mcp v2.35.3) as an on-demand MCP server mana... (n8n, mcp, claude-code)
- [PR Reviewer Agent Definition and Dispatcher System](graph/configurations/pr-reviewer-agent-definition-and-dispatcher-system-b79abd.md) - Built a complete automated PR review system using Claude Code. (pr-reviewer, claude-scheduled, gitea)
- [MCP servers go in ~/.claude.json, NOT ~/.claude/.mcp.json](graph/configurations/mcp-servers-go-in-claudejson-not-claudemcpjson-d746c5.md) - Global MCP servers** must be defined in `~/.claude.json` under the top-level... (claude-code, mcp, configuration)
- [Palworld Dedicated Server on Proxmox LXC 230](graph/configurations/palworld-dedicated-server-on-proxmox-lxc-230-e5922f.md) - LXC ID: 230 (palworld, proxmox, lxc)
- [Shared repos.json for claude-scheduled automations](graph/configurations/shared-reposjson-for-claude-scheduled-automations-da46f2.md) - Moved repos.json from a task-specific location to a shared location so all au... (claude-scheduled, repos, configuration)
- [Config: mcp-tui-driver MCP server installed globally](graph/configurations/config-mcp-tui-driver-mcp-server-installed-globally-967ad4.md) - Installed from source via cargo: (mcp, tui-testing, claude-code)
- [CT 300 claude-runner: Two-Tier Health Check Architecture](graph/configurations/ct-300-claude-runner-two-tier-health-check-architecture-061011.md) - The headless Claude server diagnostics system runs on **CT 300** (hostname: `... (ct300, claude-runner, server-diagnostics)
- [Path references updated across 6 files after cognitive-memory extraction](graph/configurations/path-references-updated-across-6-files-after-cognitive-memor-81e330.md) - After moving app code from `~/.claude/skills/cognitive-memory/` to `/mnt/NV2/... (cognitive-memory, configuration, claude-code)
- [Palworld STL Client Configuration (App ID 1623730)](graph/configurations/palworld-stl-client-configuration-app-id-1623730-9f09eb.md) - Palworld (App ID 1623730) configured for Linux via SteamTinkerLaunch. (palworld, steamtinkerlaunch, gaming)
## Key Procedures
- [Self-managing n8n server health monitor with sub-workflows](graph/procedures/self-managing-n8n-server-health-monitor-with-sub-workflows-226839.md) - Master + sub-workflow pattern in n8n for server health monitoring via CT 302... (n8n, homelab, monitoring)
- [Add a new server to n8n health monitoring](graph/procedures/add-a-new-server-to-n8n-health-monitoring-f3a41c.md) - To add a new server to the automated health monitoring system, only one file... (n8n, monitoring, homelab)
- [Cognitive-memory has no test suite — use inline smoke tests](graph/procedures/cognitive-memory-has-no-test-suite-use-inline-smoke-tests-21be13.md) - The cognitive-memory project at `/mnt/NV2/Development/cognitive-memory/` has... (cognitive-memory, testing, workflow)
Reference in New Issue View Git Blame Copy Permalink