Memory and context

11,752 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.

using-goodmemory

817

hjqcan/GoodMemory

Skill Claude CodeCodex

Recall and persist durable project context with GoodMemory in Kimi Code.

not rated 17 7d ago A 18 tokens original MIT

logseq-brain

818

jame581/LogseqBrain

Plugin Claude Code

Bundles 5 skills · 447 tokens together

Persistent memory for Claude using a dedicated Logseq graph. Save and load project context, decisions, and progress across sessions and devices.

not rated 17 1mo ago A tokens not measured original MIT

compaction-advisor

819

vignesh07/compaction-advisor

Plugin Claude Code

Bundles 1 skill, 2 commands · 32 tokens together

Automatic context monitoring that prevents mid-task compaction. Shows real-time free space in status line and injects context state so Claude knows when to recommend /compact.

not rated 17 8mo ago A tokens not measured original MIT

agent-log

820

denysdovhan/agents

Skill Codex

Use this skill to maintain an agent log in .agents/log, a decision journal shared by the developer and agents. Trigger when the user explicitly asks to use agent-log or record/update an agent log entry; when planning, implementing, or finalizing a significant feature in a repo with an existing .agents/log; or before…

not rated 17 1mo ago A 95 tokens original MIT

memcp-analyzer

821

maydali28/memcp

Agent Claude Code

Analyze a MemCP context using the RLM peek-identify-load-analyze pattern. Use proactively when answering questions about stored content without loading it all into the main context.

not rated 17 4mo ago A 39 tokens original MIT

zettelkasten-brain

822

cx2002302-lang/zettelkasten-second-memory

Skill Claude CodeCodex

A knowledge-management system based on Zettelkasten, a method of keeping small linked notes so ideas can be found and connected later. It provides tools for searching, creating, updating, reviewing, archiving, and analyzing notes.

not rated 17 1mo ago A 36 tokens original MIT

graph-memory

823

divyanshailani/graph-memory

Skill Claude Code

Local SQLite knowledge graph for AI agent project memory. Ingests codebase AST, tracks agent decisions, detects contradictions, and produces cache-stable prompt snapshots. Install via pip, use via CLI or MCP.

not rated 17 3d ago A 45 tokens original MIT

zaxy

824

syndicalt/zaxy

MCP server Claude CodeCodexCursor +2

Coordinator memory for auditable multi-agent projects. Runs locally from the zaxy-memory Python package.

not rated 17 1mo ago A tokens not measured original MIT

memex

825

Skyfox-io/Memex

Plugin Claude Code

Bundles 17 skills · 1,017 tokens together

Structured memory for Claude Cowork. Tiered context loading, session automation, and Obsidian-compatible navigation.

not rated 17 2mo ago A tokens not measured original MIT

contextmine

826

mayflower/contextmine

MCP server Claude CodeCodexCursor +2

MCP server "contextmine" as configured in mayflower/contextmine. Runs locally from the contextmine Python package.

not rated 17 3d ago A tokens not measured original MIT

knowledge-graph

827

hilyfux/knowledge-graph

Plugin Claude Code

Bundles 1 skill · 64 tokens together

Persistent memory layer for Claude Code — tracks file operations, mines co-change patterns, generates distributed CLAUDE.md knowledge nodes. Zero dependencies beyond jq.

not rated 17 3mo ago A tokens not measured original MIT

fable5-skills

828

kpab/claude-fable-5-skills

Plugin Claude Code

Bundles 11 skills · 967 tokens together

10 Fable 5-native Agent Skills for Claude, updated for Fable 5.1 — fix over-planning, gold-plating and test bloat, fabricated progress reports, unrequested actions, stalled autonomous runs, and silent tool loops. Includes skill-refactorer for migrating pre-Fable-5 skills and re-checking Fable 5 skills on 5.1.

not rated 17 changed 6d ago A tokens not measured original MIT

vault-cortex

829

aliasunder/vault-cortex

MCP server Claude CodeCodexCursor +2

MCP server "vault-cortex" as configured in aliasunder/vault-cortex. Runs in Docker (ghcr.io/aliasunder/vault-cortex:0.45.0). Needs 24 environment variables to run.

not rated 17 +1 today A tokens not measured original MIT

totem-compiled-rules

830

mmnto-ai/totem

Skill Claude CodeCodex

Compiled architectural rules and lessons from the Totem knowledge base. Load this when reviewing code for pattern violations or architectural drift.

not rated 17 yesterday A 31 tokens original Apache-2.0

context-rot-cleanup

831

NickGuAI/Herd

Skill Claude Code

Examine workspace files for durable context, filter out low-value noise, and clean up stale memory or rule files that contribute to context rot.

not rated 17 today A 34 tokens AGPL-3.0

openviking-memory

832

Castor6/openviking-plugins

Plugin Claude Code

Bundles 3 hooks

Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.

not rated 17 +1 5mo ago A tokens not measured original Apache-2.0

hermes-second-brain

833

andrihakim146/hermes-second-brain

MCP server Claude CodeCodexCursor +2

MCP server "hermes-second-brain" as configured in andrihakim146/hermes-second-brain. Runs locally from the hermes-second-brain Python package.

not rated 17 2mo ago A tokens not measured original MIT

memory-recall

834

star-ga/mind-mem

Skill Claude CodeCodex needs its repo

Search across all structured memory files. Default backend: BM25 scoring with Porter stemming and domain-aware query expansion. Optional: graph-based cross-reference boosting (--graph). Optional: vector/embedding backend (configure in mind-mem.json). Returns ranked results with block ID, type, score, excerpt, and file…

not rated 17 +2 yesterday A SkillSpector: pass 0 tokens original Apache-2.0

bilibili-mcp-memory

835

XZXZZX-Ai/bilibili-mcp

Skill Claude CodeCodex

Route accepted evidence through the repository typed-memory projector and load only bounded current memory.

not rated 17 4d ago A 23 tokens original Apache-2.0

learn

836

Ramsbaby/jarvis

Command Claude Code

A command that saves reusable discoveries and lessons from a coding session as one-line JSON records. JSONL means one JSON object per line, making the file easy to append to and process.

not rated 17 +1 18d ago A 56 tokens original MIT

agent-knowledge

837

keshrath/agent-knowledge

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 96 tokens together

Cross-session memory for AI coding agents. Git-synced Markdown knowledge base with hybrid semantic + TF-IDF search, typed knowledge graph, and session auto-distillation with secrets scrubbing.

not rated 17 4mo ago A tokens not measured original MIT

evolver

838

EvoMap/evolver-claude-code-plugin

Plugin Claude Code

Bundles 1 skill, 8 commands, 3 hooks, 1 MCP server · 267 tokens together

Gives the agent a persistent, auditable evolution memory plus a bridge to the EvoMap Proxy mailbox. Recalls what worked at session start, detects improvement signals while you edit, records outcomes when a task ends, and exposes the network's genes/capsules as MCP tools — powered by the Genome Evolution Protocol (GEP).

not rated 17 +2 21d ago A tokens not measured original MIT

engram

839

20alexl/claude-engram

Skill Claude Code

Claude Engram persistent memory — quick reference for all MCP tools and automatic hook behaviors. Use when you need to remember how to store, search, or manage memories, or query session history.

not rated 16 14d ago A SkillSpector: warn 41 tokens original MIT

obsidian-web-mcp

840

Faust-Donf/chatgpt-sidebar

Skill Claude CodeCodex

Set up or maintain an Obsidian vault with a desktop ChatGPT web sidebar community plugin and a vault-scoped MCP server exposed through ngrok. Use when asked to configure Obsidian plugins, install or update a ChatGPT web sidebar, expose an Obsidian vault to ChatGPT/MCP, add read/write vault tools, add Agent…

not rated 16 2mo ago A 100 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: