6,602 tagged Memory and context, measured the same way as everything else here.
Browse within: LLM 229agent 159agent-memory 153cli 134agentic-ai 123agents 119ai-memory 111claude-code-plugin 83ai-coding 76context-engineering 59ai-tools 58skills 58knowledge-base 56open-source 55
Skill Claude CodeCodex
Turn a recurring search/knowledge-assembly need expressed in free language into an optimal, validated vault-memory task contract written to the vault's contracts/ directory. A contract is a saved, repeatable research recipe (gather the right notes, compile a brief into the memory sink) — this skill is the interactive…
Skill Claude CodeCodex
Use the Decision State MCP tools to retrieve compact project state before substantial work and record meaningful decisions or outcomes after work.
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…
Substrate-memory/codex-substrate-memory
Skill Claude CodeCodex
Recall, inspect, and preserve durable Substrate memory; connect and diagnose the native plugin.
Skill Claude CodeCodex
Use when a user wants to keep a note, or when an LLM dialogue produces a reusable concept, method, prompt, decision, troubleshooting pattern, reference, boundary, distinction, example, or rule worth turning into a fillable personal knowledge-base note.
Skill Claude CodeCodex
Route Markdown documents, evidence-backed project facts, conversation history, personal memory, and reusable procedures without double-writing. Use when an Agent must search or write AFS documents, propose or retrieve governed facts, inspect evidence and Timeline, or choose the correct durable store.
Skill Claude CodeCodex
A personal memory system that stores text, images, files, and secrets in separate collections. It can find stored items by meaning rather than only by exact words.
Skill Codex
Use Codex Project Memory in repositories with the project-memory MCP server installed.
Skill Claude CodeCodex
Manual trigger only. Use only when the user explicitly invokes /mem0:dream or directly asks to run Dream memory maintenance for the active Mem0 OSS project.
Skill Claude CodeCodex
Universal Long-Term Memory & Cross-Agent Handoff Protocol for AI Coding Agents. Use to recall past architectural decisions, persist bug fix patterns, and create clean handoff snapshots between Antigravity, Cursor, and Claude Code.
Skill Claude CodeCodex
Use when Hermes should remember durable lessons, recall prior work, or create guarded skill proposals through Noggin.
Skill Claude Code
Search local indexed markdown knowledge bases. Use when the user asks to find notes, dig up a concept from personal docs, cross-reference ideas across wikis, or answer from indexed local files. Triggers on "look up in notes", "search my docs", "what did I write about", "find in my vault", "check my index", "retrieve…
Skill Claude CodeCodex
Store a lesson learned from the current conversation. Triggered by /lesson command. Use when Master signals that the recent conversation contains a pitfall, fix, or key insight that should be persisted to long-term memory.
Skill Claude Code
Memory Vault MCP server — Markdown + SQLite knowledge store with bidirectional [[wikilinks]]. Use when the user wants to create, read, edit, search, or manage interconnected knowledge notes. Provides 11 tools: vaultwrite, vaultwritebatch, vaultread, vaultedit, vaultdelete, vaultrename, vaultlist, vaultsearch…
Skill Claude CodeCodex
Persistent reader mode for AI. Give your OpenClaw agent a research library that lasts between sessions. Save web pages, organise them into collections, distil the important parts, and access it all through MCP.
Skill Claude CodeCodex
This skill should be used when the user asks to "remember this", "recall", "what did I say about", "note that", "for future reference", "store memory", "my preferences", "forget", or discusses memory storage and retrieval.
Skill Claude CodeCodex
Capture session knowledge with mcp-pusher using mcp:append and mcp:push. Use before context compaction or at session end on Laravel projects with ashwinmram/mcp-pusher.
Skill Claude CodeCodex
Use open-brain as persistent memory for storing and retrieving information across conversations.
Skill Claude CodeCodex
MCP server exposing OpenClaw tools (smart home, memory, cron, sub-agent orchestration) to Claude Desktop, Cursor, Windsurf, and any MCP client. Includes Gemini, Codex, and local LLM sub-agents plus smart prompt splitting.
Skill Claude CodeCodex
Semantic search and retrieval over the OpenClaw vault via an MCP server + watcher.
Skill Codex
Retrieve and interpret durable, evidence-backed project memory from Context Atlas, including overviews, architecture, chronology, decisions, risks, provenance, health, and task-specific context packs. Use when Codex must onboard to an unfamiliar repository, explain how or why code evolved, prepare context before a…
Skill Claude CodeCodex
Daily memory maintenance — enrich, consolidate, and connect your ShelbyMCP memories.
Skill Claude CodeCodex
Universal autonomous long-term memory for AI agents. Remember everything, send only what matters.
Skill Claude CodeCodex
Analyze recent conversation for novelty and persist high-value content to Cordelia memory.
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: