Memory and context

11,848 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.

supamem

961

dzmitrys-dev/supamem

Skill Claude CodeCodex

Project-agnostic dual-memory tooling — semantic + structural memory for AI coding agents.

not rated 12 22d ago A 20 tokens original MIT

MSiccDev/ai-context-kit

Plugin Claude Code

Lists 1 plugin

Context-aware AI collaboration skills for creating and validating user context, project AGENTS.md files, and skill artifacts across LLM providers.

not rated 12 changed 4d ago A tokens not measured original MIT

local-agent-toolkit

963

jnMetaCode/local-agent-toolkit

Plugin Claude Code

Bundles 3 skills · 118 tokens together

Local-first memory, skills and tracing for your agent: engram (recall/remember your notes via MCP), skillet (search/install agent skills via MCP), plus skills that teach the agent to use them — nothing leaves your machine.

not rated 12 3mo ago A tokens not measured

knowit

965

ismaelkedir/knowit

MCP server Claude CodeCodexCursor +2

Shared team memory for AI coding agents — MCP server and CLI for persistent, queryable knowledge across sessions and teammates. Runs locally from the knowit npm package.

not rated 12 1mo ago A tokens not measured original MIT

AGENTS

966

yonro/memory-os-cli

Cursor rule Cursor

Use XMemo for durable project memory, coding preferences, decisions, TODOs, and cross-session context through the hosted MCP server.

not rated 12 yesterday A 26 tokens original MIT

memex

967

STiFLeR7/memex

MCP server Claude CodeCodexCursor +2

Temporal engineering context for agents via MCP. Runs locally from the stifler-memex-mcp npm package. Needs 4 environment variables to run.

not rated 12 5d ago A tokens not measured original MIT

akashi

968

ApiliumCode/mayros

Skill Claude Code

Connect the user's Akashi second brain (local, private, verifiable) over MCP and answer from cited vault passages with signed provenance. Query it BEFORE answering anything about the user's knowledge, projects, decisions, or conventions. Triggers - akashi, vault, my notes, second brain, remember this, what did I…

not rated 12 1mo ago A 69 tokens original MIT

dream

970

jl-cmd/claude-dream

Plugin Claude Code

Bundles 1 skill · 63 tokens together

Memory consolidation for Claude Code. Simulates the Auto Dream feature by auditing, deduplicating, and rebuilding your memory files.

not rated 12 1mo ago A tokens not measured original MIT

context0

971

SyedSibtainRazvi/context0

Cursor rule Cursor

Use context0 MCP to save and resume coding context when the user switches between AI tools (Cursor, Claude Code, Codex).

not rated 12 5mo ago A 412 tokens original MIT

crystal-kb

972

memorycrystal/memorycrystal

Skill Claude CodeCodex

Create, import, enumerate, maintain, and share Memory Crystal knowledge bases. Use when importing reference material, syncing a corpus, cleaning or auditing a KB, or managing which agents can read a KB.

not rated 12 11d ago A 45 tokens original MIT

letta-mcp-server

973

SNYCFIRE-CORE/letta-mcp-server

MCP server Claude CodeCodexCursor +2

Production-ready MCP server bridging Claude and Letta.ai agents. Runs locally from the letta-mcp-server Python package.

not rated 12 7mo ago A tokens not measured original MIT

inardini/vertex-memory-bank-mcp

MCP server Claude CodeCodexCursor +2

MCP server "vertex-ai-memory-bank-mcp" as configured in inardini/vertex-memory-bank-mcp. Runs locally from the vertex-ai-memory-bank-mcp Python package.

not rated 12 11mo ago A tokens not measured original Apache-2.0

thread-keeper

976

po4erk91/thread-keeper

MCP server Claude CodeCodexCursor +2

Multi-agent shared brain across Claude Code/Desktop, Codex, Antigravity CLI, Copilot, and VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server. Runs locally from the threadkeeper Python package.

not rated 12 +1 today A tokens not measured original MIT

dory-wake

977

deeflect/dory

Skill Claude CodeCodex

Use Dory wake once at the start of a new agent session, after context compaction, or at a real task switch to load bounded hot context with the right profile before substantive work.

not rated 12 +1 3mo ago A 43 tokens original MIT

soul-aaron

978

aaronjmars/soul-aaronjmars

Skill Claude CodeCodex

Embody Aaron's digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become Aaron—opinions, voice, worldview, the works.

not rated 12 10d ago A 38 tokens

agentic-task-system

979

renezander030/agentic-task-system

MCP server Claude CodeCodexCursor +2

MCP server giving AI agents persistent task memory across TickTick, Notion, GitHub, Linear & Beads. Runs locally from the @reneza/ats-mcp npm package. Needs 1 environment variable to run.

not rated 12 +1 4d ago A tokens not measured original MIT

adapter-authoring

980

Kromatic-Innovation/athenaeum

Skill Claude CodeCodex

Build a custom source → raw-intake adapter for Athenaeum. Use when someone wants to feed an external source (an API, an export file, a message feed, a scraper, another tool's output) into an Athenaeum knowledge base, asks "how do I write an adapter / integration for athenaeum", or wants to turn some data source into…

not rated 12 changed 6d ago A SkillSpector: warn 86 tokens original Apache-2.0

coalent

981

Vectorlink-Labs/coalent

MCP server Claude CodeCodexCursor +2

A real-time, provenance-invalidated cognitive cache layer for AI agents and RAG. Runs locally from the coalent Python package. Needs 2 environment variables to run.

not rated 12 +1 26d ago A tokens not measured original Apache-2.0

icm-builder

984

carloswecare/icm-builder

Skill Claude CodeCodex

Build and reason about projects using Interpretable Context Methodology (ICM) — a filesystem-based way to structure AI work using numbered folders and markdown files (CLAUDE.md, CONTEXT.md) instead of code-heavy agent frameworks. Use this skill whenever the user wants to scaffold a new ICM workspace, set up a…

not rated 12 +1 2mo ago A 164 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: