memory-palace

Solid

Hierarchical memory organization for multi-session context retention. Wings (projects) > Rooms (domains) > Drawers (decisions). Semantic search across all memories with zero cloud dependency.

AI & Automation 552 stars 45 forks Updated 6 days ago MIT

Install

View on GitHub

Quality Score: 91/100

Stars 20%
91
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Memory Palace Hierarchical, persistent memory system for Claude Code sessions. Organizes knowledge so agents never lose context across sessions. ## Architecture ``` Palace (global) Wing: project-name Room: authentication Drawer: "chose JWT over sessions" (2026-04-07) Drawer: "rate limiting at 100 req/min" (2026-04-06) Room: database Drawer: "PostgreSQL with pgvector" (2026-04-05) Drawer: "migration strategy: blue-green" (2026-04-04) Room: deployment Drawer: "Vercel + GitHub Actions" (2026-04-03) Wing: another-project Room: ... ``` ## Storage Format All memories stored in `~/.claude/palace/` as flat JSONL files per wing: ``` ~/.claude/palace/ index.json # Wing registry my-project.jsonl # All drawers for this wing other-project.jsonl # All drawers for this wing ``` ### Drawer Entry Format ```json { "id": "d-abc123", "wing": "my-project", "room": "authentication", "content": "Chose JWT with refresh tokens over session-based auth. Reason: stateless, mobile-friendly, scalable.", "tags": ["auth", "jwt", "architecture"], "timestamp": "2026-04-07T14:30:00Z", "session_id": "s-xyz789", "agent": "architect", "type": "decision" } ``` ### Entry Types - `decision` - Architectural or design choice with reasoning - `discovery` - Something learned about the codebase - `error` - Error encountered and how it was resolved - `constraint` - External limitation or requirement - `pattern` - Recurring code...

Details

Author
vibeeval
Repository
vibeeval/vibecosystem
Created
8 months ago
Last Updated
6 days ago
Language
C#
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

claude-mem

Persistent filesystem memory across sessions — maintains memory/ with decisions.md, context.md, glossary.md and sessions/YYYY-MM-DD.md, loads and summarizes state at session start, appends decisions and open threads at session end, compacts monthly, and refuses secrets and transient noise. Use when the user says "remember this", "what did we decide about X", "pick up where we left off", or when starting or closing a session on a long-running project.

24 Updated 6 days ago
alebgl77
AI & Automation Solid

layered-recall

4-layer memory recall system. Layer 1 (identity) always loaded, Layer 2 (critical facts) per-project, Layer 3 (room recall) on-demand, Layer 4 (deep search) when needed. Progressive context loading for token efficiency.

552 Updated 6 days ago
vibeeval
AI & Automation Listed

session-memory

Persistent memory and session-handoff protocol for Fable sessions. Maintains a decision log (why choices were made), a working notes file (current state of play), and a defined boot/handoff sequence so a fresh context window resumes work without re-deriving past reasoning. Use at the start of any session on an existing project, whenever an architectural or contract decision is made or reversed, whenever a review-loop or qa-loop ruling constrains future work, when context is running long and compaction is near, and at the end of any working session. Also use when the user asks to "pick up where we left off", resume, or continue a project.

0 Updated 3 months ago
Caelumca