mooncite
481WhenMoon-afk/claude-memory-mcp
Skill Claude CodeCodex
Use when an agent needs past Pi, OMP, Claude Code, Codex, or ChatGPT context.
not rated 69
changed 1mo ago A SkillSpector: warn 26 tokens
original MIT
k-kolomeitsev/data-structure-protocol
Skill Claude CodeCodex
Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents. Stores entities (modules, functions), their dependencies (imports), public API (shared/exports), and reasons for every connection. Use when: (1) project has a .dsp/ directory, (2) user asks to set up…
not rated 68 2mo ago A SkillSpector: pass 133 tokens
original Apache-2.0
pkm-vault-master
483Skill Claude CodeCodex
This skill should be used when organizing and structuring Personal Knowledge Management (PKM) vaults, particularly Obsidian vaults using the Linking Your Thinking (LYT) methodology. Use this skill when the user asks to analyze notes, create MOCs (Maps of Content), find related notes, organize folders, generate…
not rated 68
+3 11mo ago A 105 tokens
claude-mem-lite
484Plugin Claude Code
Bundles 8 commands, 7 hooks, 1 MCP server · 509 tokens together
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. FTS5 BM25 keyword search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-mem (episode batching + a smaller model; cost savings are an…
not rated 68
changed 3d ago A
tokens not measured
original MIT
MCP server Claude CodeCodexCursor +2
MCP server that exposes Project AI Memory (memory.md) as resources and tools for Cursor, Claude, and other MCP clients. Runs locally from the mcp-memory-server Python package.
not rated 68
+9 1y ago A
tokens not measured
sessions
486Command Claude Code
Manage Gemini Code session history, aliases, and session metadata.
not rated 68 yesterday A 12 tokens
original Apache-2.0
toonify-mcp
487Plugin Claude Code
Local context compression for Claude Code workflows, including structured data and debug-heavy output.
not rated 67 2mo ago A
tokens not measured
original MIT
memory-vault
488MCP server Claude CodeCodexCursor +2
MCP server "memory-vault" as configured in MihaiBuilds/memory-vault. Runs in Docker (ghcr.io/mihaibuilds/memory-vault-mcp:1.6.1). Needs 5 environment variables to run.
not rated 67
+2
changed 10d ago A
tokens not measured
original MIT
farnsworth-ai
489MCP server Claude CodeCodexCursor +2
Self-evolving companion AI with MemGPT-style memory and LangGraph agent swarm. Runs locally from the farnsworth-ai Python package.
not rated 67 2mo ago A
tokens not measured
proactive-agent
490Skill Claude CodeCodex
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.
not rated 67
+2 6d ago A SkillSpector: warn 46 tokens
original Apache-2.0
serena
491MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP proxy that compresses prose fields (tool descriptions, etc.) using caveman rules. Same accuracy, fewer context tokens. Runs locally from the caveman-shrink npm package.
not rated 67 1mo ago A
tokens not measured
@tekmidian/pai
492Plugin Gemini CLI
Personal AI Infrastructure — persistent memory and session continuity for AI coding assistants.
not rated 67
+8
changed 7d ago A
tokens not measured
original MIT
agent-builder
493Skill Claude CodeCodex
A builder for persistent coding-agent assistants that keep their own instructions, memory, and data files between conversations. It creates agents for a defined role, such as a mechanic assistant.
not rated 66 8d ago A 52 tokens
original MIT
enzyme
494Skill Claude Code
Use Enzyme in an already activated Obsidian, Markdown, or Hermes workspace for working-memory retrieval, source-grounded exploration, semantic search by concept rather than keyword, runtime note-writing, and refresh. If the workspace is not initialized, follow the first-time setup section before normal retrieval.
not rated 66
changed 12d ago A 60 tokens
zettelforge
495Skill Claude CodeCodex
ZettelForge v2.0.0 — Production CTI agentic memory system. Hybrid TypeDB (STIX 2.1 ontology) + LanceDB (vector search). Zero external AI dependencies: fastembed for embeddings, llama-cpp-python for LLM. 75% accuracy on CTI queries, 18% on LOCOMO. Use when agents need persistent memory, threat intel retrieval, entity…
not rated 66 8d ago A SkillSpector: pass 97 tokens
original MIT
clickmem
496Skill Claude CodeCodex
Local memory store for AI coding agents — explicit-only, no auto-extraction. Use when: You just refined a conclusion worth keeping across sessions → call clickmemremember Starting a task → derive projectid + tags, call clickmemrecall, load hits into context, then work The user asks "what did we decide about X" → call…
not rated 66 4mo ago A 187 tokens
original MIT
cc-session
497Mapleeeeeeeeeee/cc-session-reader
Skill Claude Code
A command-line helper for reading past Claude Code conversations without loading their full raw log files.
not rated 66
changed 2mo ago A 76 tokens
original Apache-2.0
honcho-memory
498Skill Claude CodeCodex
Persistent cross-session memory via Honcho — recall what you know about the user before working, and save durable insights after.
not rated 66 2mo ago A SkillSpector: warn 28 tokens
original MIT
cubox
499Skill Claude CodeCodex
Cubox CLI is a callable personal reading memory system that enables you to search, read, and use saved content, perform semantic (RAG-based) queries, access articles, highlights, and metadata, save URLs, update content states, and retrieve annotations and structure such as folders and tags. Use this tool when a task…
not rated 66
+1 2mo ago A Socket: passSnyk: warnSkillSpector: warn 83 tokens
original MIT
kaeru
500Skill Claude CodeCodex
Recall, capture and inspect persistent project memory through the kaeru MCP server. Use for cross-session project continuity, durable decisions, standing constraints, open work and saved reasoning.
not rated 66
+11
changed 16d ago A 37 tokens
automem
501Cursor rule Cursor
AutoMem persistent memory - validated two-phase recall, curated storage, mandatory associations.
not rated 66
+1 yesterday A 2,201 tokens
original MIT
agent-wiki
502Skill Claude CodeCodex
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
not rated 65
changed 1mo ago A SkillSpector: pass 89 tokens
original MIT
agent
503Plugin Claude Code
Bundles 21 skills, 10 hooks, 1 MCP server · 1,296 tokens together
Turn Claude Code into a persistent agent — memory, personality, voice, messaging, and more.
not rated 64
+1
changed 1mo ago A
tokens not measured
original MIT
sessionend
504Skill Claude CodeCodex
End-of-session ritual that turns sessions into institutional memory via Zengram. Detects repeatable workflows worth capturing as skills AND mistakes/corrections worth capturing as CLAUDE.md rules. Reflects honestly, stores to Zengram, updates local memory, spots workflow patterns, and proposes rule updates. Use when…
not rated 64 yesterday A SkillSpector: warn 147 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: