Memory and context

11,677 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.

hebb-mind

481

afx-team/hebb-mind

Plugin Claude Code

Bundles 6 skills, 3 agents · 213 tokens together

Neuroscience-inspired long-term memory for Claude Code — auto-captures and recalls cross-session context.

not rated 51 +1 1mo ago A tokens not measured original MIT

lilbee-mcp

482

tobocop2/lilbee

Skill Claude CodeCodex

Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…

not rated 51 changed 3d ago A SkillSpector: warn 95 tokens original MIT

honcho-memory

483

plastic-labs/codex-honcho

Skill Claude CodeCodex

Persistent cross-session memory via Honcho — recall what you know about the user before working, and save durable insights after.

not rated 50 +1 5d ago A SkillSpector: warn 28 tokens original MIT

obsidian-cli

485

jykim/claude-obsidian-skills

Skill Claude Code

Interact with Obsidian using the official CLI to read, search, create, and manage notes, daily notes, tasks, properties, and more. Use when the user wants to query or manipulate vault content via the obsidian command.

not rated 50 15d ago A SkillSpector: pass 51 tokens original MIT

obsidian-sync-mcp

488

es617/obsidian-sync-mcp

MCP server Claude CodeCodexCursor +2

Give AI agents access to your Obsidian vault via local files or Self-hosted LiveSync. Runs locally from the obsidian-sync-mcp npm package. Needs 11 environment variables to run.

not rated 50 8d ago A tokens not measured original MIT

@tekmidian/pai

489

mnott/PAI

Plugin Claude Code

Bundles 3 skills, 2 commands · 263 tokens together

Personal AI Infrastructure — persistent memory, session continuity, and knowledge graph for Claude Code.

not rated 50 +3 yesterday A tokens not measured original MIT

llm-wiki

490

Oshayr/LLM-Wiki

Plugin Claude Code

Bundles 5 skills, 10 agents · 634 tokens together

LLM-powered personal wiki — autonomous knowledge base with research-on-miss, ingestion, search, a browsable web UI, and universal data gravity. Saves and retrieves knowledge automatically whenever relevant.

not rated 49 4mo ago A tokens not measured original MIT

cortex-memory

491

Fozikio/cortex-engine

Skill Claude CodeCodex

Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.

not rated 49 19d ago A SkillSpector: pass 36 tokens original MIT

code-memory

493

kapillamba4/code-memory

MCP server Claude CodeCodexCursor +2

A deterministic, high-precision code intelligence MCP server. Runs locally from the code-memory Python package. Needs 2 environment variables to run.

not rated 49 +1 3mo ago A tokens not measured original MIT

second-brain

494

sean-esk/second-brain-gtd

Skill Claude Code

Personal knowledge management for Obsidian combining GTD, Zettelkasten, and PARA. Six workflows: (1) Capture - "capture this", "remember this", "save this thought", "note this down" - saves thoughts/tasks to daily inbox without categorization; (2) Process inbox - "process my inbox", "organize captures", "GTD…

not rated 49 +1 9mo ago A Socket: passSnyk: pass 247 tokens

vault-for-llm

495

zycaskevin/Vault-Agent-Memory

Skill Claude CodeCodex

Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.

not rated 49 +1 11d ago A SkillSpector: pass 46 tokens original Apache-2.0

ruflo

496

aimasteracc/tree-sitter-analyzer

MCP server Claude CodeCodexCursor +2

Ruflo - Enterprise AI agent orchestration platform. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration. Runs locally from the ruflo npm package. Needs 6 environment variables to run.

not rated 49 +1 yesterday A tokens not measured copy · 81% MIT

agentcairn-setup

497

ccf/agentcairn

Skill Codex

Install, configure, verify, upgrade, or repair AgentCairn persistent cross-agent memory. Use when a user wants shared local-first memory in Claude Code, Codex, Cursor, OpenCode, Antigravity, VS Code, Claude Desktop, or another supported harness; when AgentCairn recall or remember tools are missing; or when its plugin…

not rated 49 +1 3d ago A SkillSpector: warn 91 tokens original Apache-2.0

t2a-memory

498

t2a-protocol/T2A

Skill Codex

Use to install T2A Memory, remember a fact in local memory, and resolve the emitted T2A handoff without LLM API keys.

not rated 48 1mo ago A 35 tokens original Apache-2.0

qmd-sessions

500

wbelk/claude-qmd-sessions

Skill Claude Code

Convert Claude Code session transcripts to searchable markdown files for qmd indexing.

not rated 48 6mo ago D 18 tokens

subconscious

501

Square-Q/subconscious-skill

Skill Claude Code

A three-layer memory and reasoning setup for Claude Code, with conscious, preconscious, and subconscious parts. It stores project knowledge and past interactions, then can surface related memories during a session.

not rated 48 1mo ago A SkillSpector: pass 0 tokens original MIT

caretaker

503

jezweb/vite-flare-starter

Skill Claude Code

Day-of-week rotating proactive sweep — Mon=connections / Tue=routines / Wed=skills / Thu=memories / Fri=findings / Sat=cross-cutting / Sun=weekly summary. Forces outward scan instead of inward thrash. Routine-only; load this skill into a daily routine that fires AssistantAgent. Adapted from goanna's caretaker.

not rated 48 12d ago A SkillSpector: pass 74 tokens original MIT

sessions

504

Fmarzochi/EGC

Command Claude Code

Manage Gemini Code session history, aliases, and session metadata.

not rated 48 yesterday A 12 tokens original Apache-2.0

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: