12,531 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.
Plugin Claude Code
Bundles 1 skill, 1 hook · 45 tokens together
Session memory that survives compaction: auto-resume on start, checkpoint-on-compact, Memory Protocol skill, agent inbox awareness.
meemoprasad/meeba-brain-marketplace
Plugin Cursor
Ground-truth code graph context for your own private codebase — exact callers, callees, symbol definitions, and file dependencies, from a real parsed graph, not text-similarity guessing.
Plugin Cursor
Bundles 11 skills, 1 MCP server · 266 tokens together
Typed facts for agents via @quarkos/cairn. Assert, recall, and retract beliefs that outlive the session. Never the unscoped npm package cairn.
Plugin Cursor
Connect Cursor to Memside for context, checkpoints, rules, profile, and AI Skills across chats.
Plugin Claude Code
Plugin marketplace listing 1 plugin: statecore.
Skill Claude CodeCodex
Use Engraphy memory while working in a codebase: recall what governs an area before changing it, and record what the user states, as they state it. Load at the start of a ticket, bug fix or review, and whenever the user states a convention, an anti-pattern, an off-limits area, a recurring bug, a preference, a…
SAIHM-Admin/saihm-mcp-server-pro
Plugin Gemini CLI
Free-to-start portable memory for AI agents: encrypted, shareable, provably erased.
MCP server Claude CodeCodexCursor +2
Live public demo: query one person's learning and work history as a knowledge graph via MCP. Remote server at personalknowhow-demo.kxtwrdzt6g.workers.dev.
Skill Claude CodeCodex
Access the user's Kontexta (kxta) knowledge base, journal, calendar, projects and Hands via a local bridge to the kxta MCP server. Use whenever the user mentions kxta/Kontexta, their notes/KB, journal, profile, calendar events, or when CLAUDE.md / KONTEXTA.md rules reference kxta tools that are not natively available…
Skill Claude CodeCodex
Use Engram, the user's local long-term memory, to recall past decisions, people and project history before answering, save lasting facts, correct what changed, and explain why a memory says what it says. Apply when the user asks what was decided or done before, states a decision, preference or lasting fact, says…
Plugin Claude Code
Bundles 1 skill, 3 commands, 4 hooks, 1 MCP server · 97 tokens together
Captures every Claude Code session in the background and lets you resume it from Codex, OpenCode, Gemini CLI, Cursor, or Antigravity, and the other way around.
Skill Claude CodeCodex
An automatic memory pipeline for agent conversations and projects. It retrieves relevant past context, saves unfinished work as drafts, and publishes memories when a task is complete.
Skill Claude CodeCodex
Universal context management and planning system. PROACTIVELY activate for: (1) ANY complex task requiring planning, (2) Multi-file projects/websites/apps, (3) Architecture decisions, (4) Research tasks, (5) Refactoring, (6) Long coding sessions, (7) Tasks with 3+ sequential steps. Provides: optimal file creation…
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
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…
Skill Claude CodeCodex
Load this skill when you want persistent agent memory across coding sessions. Mnemovela stores decisions, facts, workspace state, project constraints, errors, and task narratives as typed, searchable, branch-aware records. The agent retrieves them at session start instead of re-discovering everything from file reads.
Skill Claude CodeCodex
File immutable evidence into a small, densely linked shared wiki.
Plugin Claude Code
Bundles 2 skills, 4 hooks, 1 MCP server · 129 tokens together
MemForge hook integration for Claude Code.
Skill Claude CodeCodex
Use this skill when the user types /memory-onboard (or asks "set up memory for this repo" / "onboard this repo to memory" / "what should be in lore for this repo?"). It runs a repo-aware onboarding interview that produces DRAFT lore records grounded in concrete repo signals (README, ADRs, recent commits, deprecation…
MCP server Claude CodeCodexCursor +2
Loads signed ALTWEB context capsules — refuses unsigned, tampered, or untrusted by default. Runs locally from the altweb-context npm package. Needs 1 environment variable to run.
Plugin Claude Code
Bundles 1 command, 7 hooks · 20 tokens together
Remembers the tool calls that already failed, and says so before your agent runs one again unchanged.
MCP server Claude CodeCodexCursor +2
DEPRECATED: This package has been renamed to smriti-memcore. Please use 'smriti-memcore' instead. Runs locally from the nexus-memory Python package.
MCP server Claude CodeCodexCursor +2
MCP connector for Snipara, the Project Brain for AI coding agents. Runs locally from the snipara-mcp Python package.
Hook Claude Code
One of 2 in hooks.json
Runs when a session starts on startup and resume, executing on_session_start.py. From zfy258/mem0-mcp-server.
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: