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.

ctx

985

yilecoding/fastapi-react-admin

Skill Claude Code

A project-context tool for recording important lessons about bugs and failure-prone code in nearby AGENTS.md documents. These documents give coding agents repository-specific guidance.

not rated 12 4d ago A SkillSpector: pass 67 tokens original MIT

memory-tool

986

pbrns/Lethe

Skill Claude CodeCodex

Persistent memory for stateless chat sessions. Saves and retrieves facts, preferences, and context across separate sessions using local device storage. Use when the user asks to remember, save, recall, forget, or search stored information. Always call getcontext automatically at the start of every new session before…

not rated 12 +1 4mo ago A 67 tokens

awiki-save

987

TacoTakumi/agent-wiki

Skill Claude CodeCodex

Save content from the current conversation to the Agent Wiki. Use when research, decisions, or valuable findings should be preserved.

not rated 12 +1 yesterday A 28 tokens

memory

989

pioneerdotai/pioneer

Skill Claude Code

Use this skill when Pioneer should proactively use durable memory or recalled context: decide whether memory can improve a turn, answer from remembered user/project facts, request memory tools, search/list/get stored memories, save durable preferences or project decisions, forget memories, audit or clean up memory, or…

not rated 12 +1 changed 4d ago A SkillSpector: warn 64 tokens original MIT

murmur-mcp

990

murmur-io/murmur

Skill Claude CodeCodex

Query Murmur's local read-only MCP server for gated, indexed knowledge — semantic + full-text search over meetings and notes, entity dossiers, structured transcripts, open-commitment rollups, and typed note-folder database queries. Prefer this over grepping raw vault files. Use when you need to find, retrieve, or…

not rated 12 +3 changed 8d ago A 93 tokens AGPL-3.0

memoryweb

991

corbym/memoryweb

Skill Claude Code

Activate at the start of any session where memoryweb MCP tools are available. Covers filing, connecting, and retrieving knowledge through the memoryweb graph — any coding, architecture, backlog, or general work an agent is tracking for this user.

not rated 12 changed 4d ago A 50 tokens original MIT

engram

992

get-engram/engram

Plugin Claude Code

Bundles 1 skill · 51 tokens together

Persistent, searchable memory for Claude. Stores conversations verbatim and retrieves them by meaning.

not rated 12 +1 changed 3d ago A tokens not measured

chat-history

993

ay-bh/chat-history

Skill Claude CodeCodex

Search, inspect, and export Claude Code, Cursor, and Codex conversation history. Use when the user asks about past conversations, wants to find a previous session, needs to search chat history, wants a summary of what they worked on, or asks to resume a session. Also use when the user says "what did I work on", "find…

not rated 11 changed today A 93 tokens original MIT

claude-find

994

Cavinooo/claude-find

MCP server Claude CodeCodexCursor +2

Pull Deep Memory from across your Claude Code Sessions — when you need it. Runs locally from the claude-find npm package.

not rated 11 3mo ago A tokens not measured original MIT

wormhole

995

fatmali/wormhole

Plugin Claude Code

Bundles 1 MCP server

Collaborative AI memory layer - sync work between Claude Code, GitHub Copilot, and Cursor.

not rated 11 7mo ago A tokens not measured

memory-mcp

996

chenxiaofie/memory-mcp

MCP server Claude CodeCodexCursor +2

A local memory service that stores and retrieves information about situations and entities for an AI assistant. It runs from a Python package and needs one environment variable.

not rated 11 1mo ago A tokens not measured original MIT

termem

997

leox255/termem

Plugin Claude Code

Bundles 1 skill · 178 tokens together

Cross-agent terminal memory: recall, search, and resume Claude Code, Codex, Gemini, opencode, and shell sessions by directory. No model calls, no network.

not rated 11 1mo ago A tokens not measured

squish

998

michielhdoteth/squish-memory

Skill Claude CodeCodex

ALWAYS use this skill when working with agents, memory, context, persistence, or AI agent state. Use when the user mentions: 'the agent forgot', 'save this', 'remember that', 'context is lost', 'memory', 'MCP server', 'agent memory', 'persistent memory', 'session context', 'project context', 'recall', 'remember'…

not rated 11 12d ago A SkillSpector: warn 157 tokens original MIT

llm-wiki-kb

999

chengjialu8888/LLM-Wiki-KB

Skill Claude CodeCodex

Build and maintain personal knowledge bases as LLM-compiled markdown wikis, inspired by Andrej Karpathy's LLM Wiki pattern. The LLM incrementally ingests raw sources (articles, papers, repos, images) into a structured, interlinked wiki of .md files — with summaries, entity pages, concept pages, cross-references, and a…

not rated 11 5mo ago A 219 tokens original MIT

coalwash

1000

TheColliery/CoalWash

Plugin Claude Code

Bundles 2 commands, 4 hooks, 1 plugin · 61 tokens together

CoalWash — memory-defragment/cleanup engine for agent memory, two lanes: class-B (memory + governance files) gets the semantic wash — a free mechanical Quick pass plus a code-enforced fidelity gate blocking any STRUCTURED-token drop by diff (links, dates, versions, frontmatter; prose fidelity is the paid semantic…

not rated 11 changed yesterday A tokens not measured original Apache-2.0

remembrances-mcp

1002

madeindigio/remembrances-mcp

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "remembrances-mcp" as configured in madeindigio/remembrances-mcp. Launched with remembrances-mcp-beta --config /www/MCP/remembrances-mcp/.ai/remembrances.config.

not rated 11 4mo ago A tokens not measured original MIT

grape

1003

gael55x/Grape

Skill Claude CodeCodex

Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.

not rated 11 2mo ago A 48 tokens original MIT

anneal-memory

1004

phillipclapham/anneal-memory

Skill Claude CodeCodex

Persistent four-layer agent memory (episodic + continuity + Hebbian + affective) plus a prospective spore layer and an on-demand crystallized-pattern tier, via anneal-memory. Use in any project wired for anneal-memory — an ANNEALMEMORYDB env var, an anneal://continuity MCP resource, or memory instructions referencing…

not rated 11 changed 7d ago A 170 tokens original MIT

gbrain-ingest

1005

imphillip/gbrain-openclaw

Skill Claude CodeCodex

Ingest meetings, articles, docs, and conversations into the brain. Updates existing pages with new info, creates pages for new entities, maintains cross-references.

not rated 11 5mo ago A 37 tokens original MIT

wiki

1006

flup-repo/skills

Skill Claude Code

Compile personal data (journals, notes, messages, whatever) into a personal knowledge wiki. Ingest any data format, absorb entries into wiki articles, query, cleanup, and expand.

not rated 11 1mo ago A 40 tokens

seeklink

1007

simonsysun/seeklink

MCP server Claude CodeCodexCursor +2

Local semantic search CLI and optional MCP stdio server for Markdown vaults. BM25 + vector + wikilink graph + metadata via RRF. Native CJK. Runs locally from the seeklink Python package.

not rated 11 3mo ago A tokens not measured original MIT

toon-memory

1008

LuiggiVal08/toon-memory

MCP server Claude CodeCodexCursor +2

Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM. Runs locally from the toon-memory npm package. Needs 6 environment variables to run.

not rated 11 1mo ago A tokens not measured 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: