cicada
claudeCicada's memory tools, its skill, and the hooks that save each Claude Code session and add what Cicada remembers to new ones.
1 skill · 1 MCP server · hooks
Claude Code and Codex plugins their authors filed under "memory". All categories.
Cicada's memory tools, its skill, and the hooks that save each Claude Code session and add what Cicada remembers to new ones.
1 skill · 1 MCP server · hooks
/decide records an Architecture Decision Record in docs/decisions.
Writes a dated journal entry of what was done when the session ends.
Teaches Claude your project's vocabulary and injects definitions when you use the terms.
Human-like memory with decay for Claude Code
2 skills
Project-scoped cross-session memory for Hindsight API >=0.10.2 and <0.11.0. Use when a repository explicitly opts in via .hindsight.json; hooks default off, enrichment is operator-gated, and BankGate is client safety, not server authorization.
10 skills · 1 agent · 1 MCP server · hooks
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · hooks
Vault-native memory for Claude Code. Markdown is ground truth. Hybrid retrieval, temporal knowledge graph, zero LLM cost on Stop, token-aware adaptive context.
2 skills · 3 commands · 1 MCP server · hooks
Team memory for coding agents: sessions capture into a shared agent brain, your team's rules and past lessons surface in the agent as it works and every rule that fires is disclosed on its own line, and the sessions behind a pull request are linked to it once a human confirms them.
17 skills · 1 MCP server
Persistent cross-session memory for AI coding agents. Drop-in replacement for claude-mem with PostgreSQL + pgvector, auto-recovery, and multi-agent support.
8 skills · 1 MCP server · hooks
Persistent memory for Claude Code sessions via mnemograph knowledge graph
3 commands · 2 agents · hooks
Persistent project memory for Claude Code via 8 organizator files + optional hooks.
1 skill
Cross-session memory that resumes your project where you left it. Primary framework: Cognitive Load Theory (Sweller, 1988). MOAT-02.
1 skill
Context-triggered memory injection — memories declare event hooks + trigger patterns and are injected when matched
11 skills · 1 agent · hooks
Make every Claude Code session discoverable by what was done, asked, and questioned. Indexes transcripts into a sidecar SQLite store with heuristic and LLM-powered synthesis. Includes SessionEnd hook for forward capture and UserPromptSubmit hook for search reminders.
1 skill · 6 commands · hooks
Ultra-minimal RAG and cross-project memory. Persistent issues and specs with semantic vector search, auto-retrieve hooks, and auto-persist hooks.
5 skills · 1 MCP server
Persistent cross-session memory with automatic extraction, semantic search, spaced repetition, and contradiction detection. Supports Claude Code, Codex, Gemini, VS Code, Cursor, and 5+ more platforms.
1 skill · 3 commands · 1 MCP server · hooks
Persistent context graph for codebase and web navigation. Symbol-chunks files, stores nodes in a SQLite graph, and returns compact references — enabling recall across sessions without re-reading files.
3 skills · 1 MCP server · hooks
Long-term self-managing memory for LLM agents via MCP. Semantic vector search + key-value store over Redis with automatic TTL and LRU eviction.
1 skill · 1 MCP server
Vectorizes transcripts into qdrant before compaction and retrieves relevant prior context on tool use
hooks
Persistent memory plugin storing architectural decisions and project context across sessions using a vector database
33 skills
Claude Code Memory System - File-based learning and memory management
14 skills · 11 commands · 1 agent · hooks
Memory compression system for Claude Code - persist context across sessions
26 skills
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · hooks
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · hooks
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · hooks
Persistent memory for Claude Code — store decisions, recall them semantically, and answer questions grounded in everything the agent has learned.
2 skills · 12 commands · 1 agent · hooks
Kannaka Holographic Resonance Medium — wave-interference memory with chiral hemispheres, 96-class collective substrate, event-sourced HRM with time-machine snapshots + replay, collective recall across the swarm, NATS sync, an agentic coding loop (kannaka agent), real quantum tools (qBraid), and Anthropic/OpenAI/Ollama LLM-backed chat.
5 skills · 10 commands
Persistent hybrid-recall memory for Claude Code: the Zekra MCP + memory-first commands, a curator agent, and an onboarding connector. Requires the `zekra` CLI (npm i -g zekra-cli).
1 skill · 7 commands · 2 agents · 1 MCP server · hooks
AI Memory plugin with local-first storage, configurable strictness, and quoth-memory subagent for context summarization. Transforms documentation from 'search and read' to 'automatic memory'.
6 skills · 2 MCP servers · hooks