6,602 tagged Memory and context, measured the same way as everything else here.
Browse within: LLM 230agent 159agent-memory 153cli 135agentic-ai 123agents 119ai-memory 110claude-code-plugin 83ai-coding 76context-engineering 59ai-tools 58skills 58knowledge-base 57open-source 56
Skill Codex
Compress large local files before adding them to LLM context. Use for docs, notes, transcripts, threads, logs, research dumps, and supported source files where only comments/docstrings should be compressed.
Skill Claude CodeCodex
Skill "public" from shawnhack/exocortex, covering exocortex, tools, core, intelligence and knowledge graph.
Skill Claude CodeCodex
Set up loom (persistent identity + memory) for this agent.
Skill Claude CodeCodex
Persistent context and inter-agent messaging across sessions and platforms. Activate when the user asks about resuming previous work, continuing where they left off, sharing context between agents, multi-agent coordination, remembering across sessions, cross-platform context sync, agent communication, or mailbox…
Skill Claude CodeCodex
Make the agent improve with every task — review the run, distill lessons into durable memory, and reinforce what worked. Use at the end of any non-trivial task, or when the user asks the agent to "learn from this".
Skill Claude CodeCodex
A session-level automation skill for Trae Solo CN that coordinates recalling, retaining, and summarising conversation information. A session is one ongoing chat or work period.
Skill Claude CodeCodex
Capture a work-session insight, lesson, decision, or "this could be a blog post" moment into an ai-journal-mcp managed journal via the addentry MCP tool. Use when the user says to journal/log/record something, or at the end of a session worth remembering. Journal-agnostic — works with whatever journals are configured.
Skill Claude CodeCodex
Report into Jason's cross-project agent fleet, collect source-cited durable decisions into Focus, recall repository memory, and explore its Neo4j read projection. Use for agent presence/asks, explicit decision capture/correction/retirement, prior-memory recall, or graph exploration. Works from any Git project through…
Skill Claude CodeCodex
Extract learnings from Claude Code session logs and save them to the brain.
Skill Claude Code
Persistent activity journal for AI agents. Use joa to log decisions, file changes, errors, observations, and conversations — then query them for context in future sessions. Use at session start for catchup, mid-session when prior context would help, and throughout to log meaningful events.
Skill Claude CodeCodex
Analyze and improve a note for slipbox integration using the actual slipbox via MCP tools. Use when the user shares a note and asks to analyze it, improve it, integrate it, check atomicity, find connections, suggest tags, or refine it. Trigger on: analyze this note, check this zettel, is this atomic, what should this…
Skill Claude CodeCodex
Structured 10-domain identity interview that maps operator values, preferences, and boundaries into HomarUS identity files (soul.md, user.md). Onboarding experience for new agents.
chaosisnotrandomitisrhythmic/anamnesis-mcp
Skill Claude CodeCodex
Use when the user asks to search, find, summarize, or cross-reference past Claude Code sessions. Triggers on "find session", "past session", "session about", "what did we do", "session history", "search sessions", "cross-reference sessions".
Skill Claude CodeCodex
When you have multiple AI agent windows open (Claude Code, OpenCode, Codex, etc.), this skill helps you.
Skill Claude CodeCodex
A skill for recording and finding notes in a local Obsidian Vault, which is a folder of linked Markdown notes. It uses YAML properties to keep saved notes consistent.
Skill Claude CodeCodex
Set up and optimize OpenClaw agent workspaces using the clawspace CLI.
Skill Claude CodeCodex
Use when starting any non-trivial task (recall prior context first) or after making a decision, learning a durable fact, or hitting a gotcha (store it). This is the shared cross-agent memory: the mem0 MCP tools memorysearch / memoryadd, exposed under your client's prefix (e.g. mem0memorysearch). It applies in EVERY…
Skill Claude CodeCodex
Use at the start of a session, or the first time the user references their own background, goals, current work, or preferences, to pull the owner's curated personal context from the context-kernel MCP connector. This is the owner's private memory (identity, goals, current work, resume, writing/figure/answer…
Skill Claude CodeCodex
Ingest a source document into the wiki knowledge base.
Skill Claude CodeCodex
Use when saving or recalling persistent memory via trailmem MCP tools (trailmemstore, trailmemquery, trailmemwelcome, ...), when a trailmem tool call fails or is rejected, or when unsure how to fill its parameters (project scoping, agenttype, eventtype, dedup, linking, archiving).
Skill Codex
Retrieve compact, cited, locally stored project context and expose an audit transcript explaining selection, exclusions, token budget, source versions, and explicit-feedback effects. Use for questions about a project whose root contains .genomefy, for long-running work that needs durable memory, when the user asks to…
Skill Codex
Connect Codex or Claude to an existing Wikimemory MCP, or deploy and configure a personal Cloudflare-hosted instance when the user asks to install, deploy, or connect Wikimemory.
no-carve-only-pizza/secondbrain-oss
Skill Claude CodeCodex
Use for every substantive task to retrieve and update the user's shared SecondBrain memory, including current project state, preferences, decisions, conversation history, and ontology relationships.
Skill Claude CodeCodex
Nightly maintenance of the brain: health check, absorb the day's log into project pages, fact-check drift, review the guest proposal queue, leave a digest.
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: