Memory and context

11,749 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

claude-faf-mcp

721

Wolfe-Jam/claude-faf-mcp

MCP server Claude CodeCodexCursor +2

Persistent project context for Claude. IANA-registered .faf format. Runs locally from the claude-faf-mcp npm package.

not rated 22 2d ago A tokens not measured original MIT

mnemos

722

polyxmedia/mnemos

Plugin Claude Code

Bundles 1 skill · 127 tokens together

Persistent memory and learning-loop skills for AI coding agents. MCP-native with 20 tools, single Go binary, ships with measured efficacy harness.

not rated 22 1mo ago A tokens not measured original MIT

chain-link

723

advpropsys/tinymem

Skill Claude CodeCodex

Save a work checkpoint to preserve context for multi-session projects. Use when pausing work on a feature, completing a milestone, or before ending a session.

not rated 22 8mo ago A 34 tokens

justokenmax

724

Kalmantic/jusTokenMax

Plugin Claude Code

Bundles 5 skills, 11 commands, 2 hooks, 1 MCP server · 555 tokens together

jusTokenMax — token-reduction toolkit for Claude Code. Compresses attachments (PDF→Markdown, images), verbose logs, and provides a code symbol index plus chat-branching workflows so the agent reads and writes fewer tokens.

not rated 22 2mo ago A tokens not measured

zeno

725

anth0nylawrence/zeno

Skill Claude Code

Persistent structured memory + telemetry + audit trail for Claude Code sessions. Use when the user wants automated capture, durable context, and standardized turn-by-turn logging.

not rated 22 8mo ago A 34 tokens

memory

726

rjyo/memory-search

Skill Claude Code

Project memory system - save and search past decisions, preferences, context, and notes. Use when user says "remember this", asks "what did we decide about X", or wants to recall/store information.

not rated 22 7mo ago A 43 tokens

spine

727

Nodewarrior/spine

Plugin Claude Code

Bundles 7 skills, 3 hooks · 263 tokens together

A self-developing knowledge management system for Claude Code. Bridges AI memory to an Obsidian vault with feature-organized spine notes, auto-capture skills, and color-coded graph visualization.

not rated 22 15d ago A tokens not measured original MIT

create-current

728

Louismao8888/girlfriends-skill

Skill Claude Code

A skill for turning information about a current partner into an AI skill containing relationship memories and a personality description. It can use chat histories, photos, and social-media posts, and supports later updates.

not rated 22 5mo ago C 68 tokens original MIT

reference

729

Kuberwastaken/reference

Skill Codex

Install, set up, and use Reference — one MCP server that lets an AI agent search the past session transcripts AND memory files (CLAUDE.md, AGENTS.md, memory/.md) of every AI coding tool on the machine (Claude Code, Codex CLI, Cursor, VS Code, …). Use this skill when the user wants cross-tool recall ("what did we…

not rated 22 1mo ago B 135 tokens original MIT

srsa-review

730

cheanus/SRSA

Skill Claude CodeCodex

Use when running Spaced Repetition Systems for AI Agents (SRSA) daily review sessions, grading cards with again/hard/good/easy, and proposing explicit memory add/delete/update actions after each review.

not rated 22 5mo ago A 46 tokens original MIT

agent-harness-setup

731

charlie947/agent-harness-starter

Skill Claude CodeCodex

Interactive walkthrough that builds the user's agent harness — Personalisation (/.claude/CLAUDE.md), Context (project CLAUDE.md), Memory (/.claude/memory/), Skills (/.claude/skills/), Agents (/.claude/agents/), and suggested MCP connectors. Use when the user asks to "set up my agent harness", "build my CLAUDE.md from…

not rated 22 3mo ago A 112 tokens original MIT

proactive-agent

733

halthelobster/proactive-agent

Skill Claude CodeCodex

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞.

not rated 22 7mo ago A 50 tokens

git-wiki

735

rarce/git-wiki

Skill Claude CodeCodex

Maintain a personal, LLM-curated knowledge wiki in a git repo using the Karpathy LLM-wiki pattern. Use this skill when the user wants to ingest a source (article, paper, notes, URL) into their wiki, query accumulated knowledge ("what do I know about X?", "what did I learn from Y?"), or lint the wiki for drift.…

not rated 22 3mo ago B 165 tokens original MIT

infimium

736

infimium-ai/infimium-agent

MCP server Claude CodeCodexCursor +2

Private context layer MCP for AI agents. Runs locally from the infimium npm package.

not rated 22 24d ago A tokens not measured original MIT

ai-memory

737

ctxpipe-ai/ctxpipe

Cursor rule Cursor

Local .ai/memory load order, indexes, and candidate-first capture.

not rated 22 today A 552 tokens

cursorrules

738

s60yucca/mnemos

Cursor rule Cursor

Use Mnemos automatically during this workspace session.

not rated 22 +1 1mo ago A 287 tokens original MIT

qmd-knowledge

739

hjanuschka/pi-qmd

Skill Claude CodeCodex

Knowledge management with QMD (Quick Markdown Search). Search, retrieve, and organize your personal knowledge base, notes, docs, and meeting transcripts. Use when asking about past notes, documentation, meetings, or when needing to recall information from your indexed markdown files.

not rated 22 7mo ago A 57 tokens

agentdir

740

jstxn/agentdir

Skill Claude CodeCodex

Use AgentDir as a local-first flight recorder for non-trivial coding-agent work in software repositories. Load at the start of coding tasks, before tests/lint/build/typecheck, and when asked about AgentDir evidence, audits, session replay, memory, context packs, adoption, or handoffs.

not rated 22 19d ago A SkillSpector: pass 63 tokens original MIT

wiki

741

cclank/lanshu-wiki-skill

Skill Claude CodeCodex

A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.

not rated 22 +1 3mo ago A 137 tokens original MIT

mem-port

742

rsl-innovation/mem-port

MCP server Claude CodeCodexCursor +2

A portable, long-term agentic memory MCP server — a thumb drive for your AI context. Runs locally from the @rsl-innovation/mem-port npm package.

not rated 22 +2 9d ago A tokens not measured original MIT

claude-memory

743

mkupermann/throughline

Skill Claude CodeCodex

Access the persistent memory database (PostgreSQL claudememory) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the…

not rated 21 changed 5d ago A SkillSpector: pass 81 tokens original MIT

skill-memory

744

memodb-io/skill-memory

Skill Claude CodeCodex

Use skill-memory to download, view and edit agent skills in memory. TRIGGER by 'skill', 'memory', 'learn'.

not rated 21 7mo ago A 29 tokens

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: