1,042 tagged Memory and context, measured the same way as everything else here.
Browse within: claude-code-plugin 109agent-memory 51ai-coding 50ai-coding-assistant 30ai-memory 29agent-orchestration 28ai-assistant 28context-engineering 26knowledge-management 24agentic-workflow 23local-first 23agent-skill 21knowledge-base 21knowledge-graph 21
Agent Claude Code
Archive management agent for Athena. Handles athena-index.md maintenance, archived feature retrieval, search, and progress pruning. Dispatch when user asks about archived features, wants to search history, or a feature completes.
jimmc414/claude-code-system-3-thinking
Agent
Cluster similar episodes and extract generalized semantic rules.
jimmc414/claude-code-system-3-thinking
Agent
Analyze past experiences and extract reusable heuristics.
zapprosite/claude-code-minimax
Agent Claude Code
Analisa uso de contexto e sugere compactação — identifica sessões pesadas, props mortos, imports não usados.
Agent Claude Code
GSD-Lite Protocol — Pair programming with AI agents while maintaining ownership of reasoning and decisions.
Agent Claude Code
A research assistant that searches an author’s own notes, saved articles, book excerpts, and personal records for material related to a topic. It treats this private collection as a source alongside public research.
Agent Claude Code
Use whenever the main agent needs to recall past work — episodes, prior sessions, decisions, or past artifacts — from inside .xo/. Keeps heavy reads off the main thread and returns only distilled, relevant context. Invoke when the user references prior work ("continue", "the bug from yesterday", "what we discussed")…
Agent Claude Code
Use when the main agent is about to perform a recurring workflow (deploy, release, migration, code review, debugging recipe) and may have a procedural skill stored in .xo/memory/procedural/ or .xo/skills/. Returns the matching skill verbatim or a clear "no skill found".
Agent
Per-tool agent memory is a private scratchpad of point-in-time .md snapshots; the public shared KB is the durable form.
katmin2001/kenzy_agent_ai_template
Agent
Update project memory so future Codex sessions can continue with minimal context.
Nemex81/solitario-classico-accessibile
Agent
Agente di setup e manutenzione del profilo progetto. Raccoglie le informazioni fondamentali sul progetto, genera .github/project-profile.md come source of truth centralizzata, adatta i componenti language-specific del framework in base allo stack dichiarato. Non partecipa al ciclo E2E. Invocabile solo manualmente o…
Agent Claude Code
Use this agent automatically at the end of meaningful tasks, after git pulls that changed key project areas, after architecture decisions, after major file moves, or when local session state may be stale. It may update local session state, proposes shared knowledge updates, and never treats local memory as source of…
Agent
Convert raw captured information into structured, modular, and traceable vault knowledge.
Agent Claude Code
Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency.
nkipler/claude-code-workspace-architect
Agent
You are a session closing agent. Your job is to analyze the current work session and update all workspace context files to preserve knowledge across sessions.
ivanhoinacki/team-exp-claude-config
Agent
Daily copilot. Accumulated memory across all conversations, full vertical context. Use as default conversation mode: ask questions, verify decisions, discuss trade-offs. Lightweight startup: context loaded on demand, not automatically. Triggers: "copilot", "chat", "update me", "what do we have", "context".
Agent
Claude Code skill that scaffolds a single-source context/ knowledge hub — engineering rules, security law, component architecture, docs, plans, ADRs, and a tech-debt registry — then wires CLAUDE.md, AGENTS.md, and .cursor rules as thin pointers into it, so Claude Code, Codex, and Cursor all read one canonical set of…
Agent
Agent "CLAUDE" from VexloCa/ctxinit, covering binding rules (canonical copies — read before working), orientation and single-source law.
Avos-Lab/git-aware-coding-agent
Agent Claude Code
Research repository context before code changes using avos memory.
Agent
Spawn after a work phase settles or when knowledge needs maintenance: pass work refs, changed files, and target repos. Mines decisions, maintains existing docs (delete stale, reorganize misplaced), writes updates into the right knowledge layers, commits each touched repo without pushing, and reports contradictions and…
IvanLutsenko/awac-ai-agent-plugins
Agent Claude Code
Obsidian vault connection specialist. Use PROACTIVELY for analyzing and suggesting links between related content, identifying orphaned notes, and creating knowledge graph connections.
Agent
The nb MCP server provides LLM-friendly access to the nb note-taking system with proper escaping and project-specific notebook context.
Agent
Agent "stig" from team-monet/monet, covering memory, work, boundaries and voice.
Agent Claude Code
An agent for operating a retrieval-augmented generation system, or RAG system, which lets an AI search stored information before answering. It manages indexing, collections, memory, and system health.
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: