Tiered memory system for cognitive continuity across agent sessions. Manages hot cache (session context loaded at boot) and deep storage (loaded on demand). Use when: (1) starting a session and loading context, (2) deciding what to remember vs forget, (3) promoting/demoting knowledge between tiers, (4) user says 'remember this' or asks about project history.
From memory-managementnpx claudepluginhub richfrem/agent-plugins-skills --plugin memory-managementThis skill is limited to using the following tools:
acceptance-criteria.mdassets/resources/memory_architecture.mmdassets/resources/memory_lookup_flow.mmdassets/resources/memory_session_lifecycle.mmdevals/evals.jsonevals/results.tsvfallback-tree.mdreferences/acceptance-criteria.mdreferences/diagrams/architecture/memory_architecture.mmdreferences/diagrams/architecture/memory_lookup_flow.mmdreferences/diagrams/architecture/memory_session_lifecycle.mmdreferences/fallback-tree.mdGuides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Designs KPI dashboards with metrics selection (MRR, churn, LTV/CAC), visualization best practices, real-time monitoring, and hierarchy for executives, operations, and product teams.
Transforms raw data into narratives with story structures, visuals, and frameworks for executive presentations, analytics reports, and stakeholder communications.
Tiered memory system that makes an AI agent a continuous collaborator across sessions.
The memory system has six tiers, configurable per project:
Tier 1: HOT CACHE (always loaded at boot -- ~200 lines target)
+-- <primer_file> Role, identity, constraints
+-- <boot_digest_file> Tactical status, active tasks
+-- <boot_contract_file> Immutable constraints
+-- <snapshot_file> Cognitive Hologram (1 sentence per file)
Tier 2: RLM SUMMARY LEDGER (fast keyword lookup -- loaded on demand)
+-- <summary_cache_file> Pre-generated text summaries: docs, protocols, research
Plugin: rlm-factory | Skill: rlm-search | Profile: project
+-- <tool_cache_file> Pre-generated text summaries: plugins, skills, scripts
Plugin: rlm-factory | Skill: rlm-search | Profile: tools
Tier 3: VECTOR STORE (semantic embedding search -- loaded on demand)
+-- <vector_db_backend> ChromaDB via vector-db plugin / vector-db-agent skill
Profile: knowledge | Port: configured in vector_profiles.json
Tier 4: DEEP STORAGE (filesystem -- authoritative source, loaded on demand)
+-- <domain_data_dir>/ Research topics: {topic}/analysis.md
+-- <design_docs_dir>/ ADRs, RFCs
+-- <governance_dir>/ Protocols, playbooks
Tier 5: VAULT (Obsidian -- linked knowledge graph, loaded on demand)
+-- <vault_dir>/ Plugin: obsidian-integration
Skills: obsidian-vault-crud, obsidian-canvas-architect,
obsidian-graph-traversal, obsidian-bases-manager
Env: VAULT_PATH or OBSIDIAN_VAULT_PATH
Tier 6: SOUL (external persistence -- optional, synced at session seal)
+-- <traces_file> Plugin: project-specific (e.g. huggingface-utils)
e.g. lineage/, data/, soul_traces.jsonl on HF Hub
Projects define their own file paths for each slot. Tiers may be omitted or added based on project complexity.
When searching for information, ALWAYS escalate in order. Never skip ahead.
Query arrives ->
1. HOT CACHE Instant. Boot files cover ~90% of context needs.
2. DEEP STORAGE (topic/decision) Load specific domain dir or design doc by subject.
3. RLM SUMMARY LEDGER (Phase 1) Keyword search via rlm-factory:rlm-search skill.
4. VECTOR STORE (Phase 2) Semantic search via vector-db:vector-db-search skill.
5. GREP / EXACT SEARCH (Phase 3) rg/grep scoped to paths from Steps 3 or 4.
6. Ask user Unknown? Learn it and persist it.
RLM is amortized prework: each file read ONCE, summarized ONCE, cached as plain text JSON. Searching summaries is O(1) keyword lookup -- no embeddings, no inference.
Trigger the rlm-factory:rlm-search skill, providing the profile and search term.
Use Phase 1 when: You need to understand what a file does, find which file owns a feature, or navigate the codebase without reading individual files.
Escalate to Phase 2 when: The summary is insufficient or no match found.
Embedding-based nearest-neighbor search across all indexed chunks. Returns ranked parent chunks with RLM Super-RAG context pre-injected.
Trigger the vector-db:vector-db-search skill, providing the query, profile, and limit.
Use Phase 2 when: You need specific code snippets, patterns, or implementations.
Escalate to Phase 3 when: You have a file path (from Phase 1 or 2) and need an exact line.
Precise keyword or regex match. Always scope to paths discovered in earlier phases.
# Scoped to a specific path (use paths from Phase 1/2)
grep_search "VectorDBOperations" ../../skills/
# Ripgrep for regex
rg "def query" ../../ --type py
Anti-patterns: Never run a full-repo grep without scoping. Never skip Phase 1.
rlm-factory -- RLM Summary Ledger (Tier 2)| Component | Value |
|---|---|
| Plugin | .agents/skills/ (rlm-curator, rlm-search, rlm-init, rlm-distill-agent) |
| Skill (write) | skills/rlm-curator/ -- distill, inject, audit, cleanup |
| Skill (read) | skills/rlm-search/ -- query the ledger |
| Skill (Phase 1 search) | rlm-factory:rlm-search |
| Skill (write/inject) | rlm-factory:rlm-curator |
| Skill (audit coverage) | rlm-factory:rlm-curator |
| Skill (shared config) | rlm-factory:rlm-curator |
| Cache files | .agents/learning/rlm_summary_cache.json (docs), .agents/learning/rlm_tool_cache.json (tools) |
vector-db -- Vector Store (Tier 3)| Component | Value |
|---|---|
| Plugin | .agents/skills/ (vector-db-search, vector-db-ingest, vector-db-launch, vector-db-init) |
| Skill | skills/vector-db-agent/ -- ingest, query, operations |
| Skill (Phase 2 search) | vector-db:vector-db-search |
| Skill (ingest files) | vector-db:vector-db-ingest |
| Skill (operations) | vector-db:vector-db-search |
| Skill (config) | vector-db:vector-db-search |
| Backend | ChromaDB (chromadb.HttpClient with PersistentClient fallback) |
obsidian-integration -- Linked Vault (Tier 5)| Component | Value |
|---|---|
| Plugin | .agents/skills/ (obsidian-vault-crud, obsidian-init, obsidian-canvas-architect, obsidian-graph-traversal) |
| Skill: vault setup | skills/obsidian-init/ -- prerequisites, .obsidian/ config, exclusion filters |
| Skill: read/write notes | obsidian-integration:obsidian-vault-crud -- atomic create/read/update/append |
| Skill: CRUD operations | obsidian-integration:obsidian-vault-crud |
| Skill: parse markdown | obsidian-integration:obsidian-vault-crud -- shared markdown parser |
| Requires | pip:ruamel.yaml (lossless YAML frontmatter), Obsidian Desktop |
| Env | VAULT_PATH -- absolute path to the vault root |
| Type | Hot Cache | On-Demand Tier |
|---|---|---|
| Active tasks | Boot digest | -- |
| Identity/role | Primer file | -- |
| Constraints | Boot contract | -- |
| Session state | Snapshot file | Tier 6 Soul (traces) |
| Research topics | Summary in snapshot | Tier 4: domain_data_dir/{name}/ |
| Design decisions | Referenced by ID | Tier 4: design_docs_dir/{id}_{name}.md |
| Governing docs | Referenced by ID | Tier 4: governance_dir/{id}_{name}.md |
| Plugins/scripts/tools | -- | Tier 2: RLM Summary Ledger (tool cache) |
| Docs/protocols/research | -- | Tier 2: RLM Summary Ledger (summary cache) |
| System docs | -- | Tier 2 RLM + Tier 3 Vector Store |
| Linked notes, canvases | -- | Tier 5: Vault (Obsidian) |
| External persistence | -- | Tier 6: Soul (HuggingFace or equivalent) |
<domain_data_dir>/{topic}/lowercase-hyphens/Projects configure the memory system by setting file paths in their project-specific plugin:
| Variable | Purpose |
|---|---|
MEMORY_PRIMER_FILE | Path to cognitive primer / role definition |
MEMORY_BOOT_DIGEST | Path to tactical boot digest |
MEMORY_BOOT_CONTRACT | Path to immutable constraints |
MEMORY_SNAPSHOT_FILE | Path to learning snapshot (hologram) |
MEMORY_DOMAIN_DIR | Directory for domain research |
MEMORY_DESIGN_DIR | Directory for design docs (e.g. ADRs) |
MEMORY_GOVERNANCE_DIR | Directory for governing docs (e.g. Protocols) |
| Diagram | What It Shows |
|---|---|
| memory_architecture.mmd | Full 4-tier memory system with exact plugin/skill/script names per tier |
| memory_lookup_flow.mmd | 3-phase search sequence: Hot Cache -> RLM Ledger -> Vector Store -> Grep |
| memory_session_lifecycle.mmd | Session Boot -> Active -> Seal lifecycle with all event types |