By tstockham96
Persistent memory for AI agents. Give Claude real memory that survives across sessions -- semantic recall, automatic consolidation, knowledge graphs, and bi-temporal tracking. 92% on DMR benchmark, 80% on LOCOMO.
Get a session briefing with relevant context, top entities, and any alerts. Use at the start of sessions to load context.
Run memory consolidation to distill episodic memories into semantic knowledge. Use at the end of long sessions or when memory quality needs maintenance.
Recall relevant memories before answering questions about past work, decisions, preferences, people, or project context. Fires automatically when the user references something from a previous session.
Store important information in persistent memory. Fires when the user shares decisions, preferences, project updates, or says "remember this."
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Persistent memory for AI agents. Give Claude real memory that survives across sessions.
Engram gives Claude persistent, intelligent memory:
claude plugin install engram
Install from claude.com/plugins.
Engram needs a one-time setup:
npx engram-sdk@latest init
This creates a local vault at ~/.engram/default.db and sets up your Gemini API key for embeddings.
Optional: Connect to the hosted API for team sharing and cloud sync:
npx engram-sdk@latest connect https://api.engram.fyi --api-key YOUR_KEY
These activate automatically when relevant:
| Skill | Triggers on |
|---|---|
| memory-recall | Questions about past work, decisions, people, preferences |
| memory-remember | Important decisions, preferences, project updates |
| memory-consolidate | End of long sessions, memory maintenance |
| memory-brief | Session start, "catch me up", context switching |
| Command | Usage |
|---|---|
/engram:recall <topic> | Search memory for a topic |
/engram:remember <text> | Store something in memory |
/engram:brief [context] | Get a session briefing |
/engram:stats | View vault statistics |
Engram runs as an MCP server alongside Claude. When installed:
All data is stored locally in SQLite by default. No data leaves your machine unless you explicitly connect to the hosted API.
Proprietary EULA. Free to install and use.
npx claudepluginhub tstockham96/engram-pluginThe bridge between Claude's working memory and Basic Memory's durable knowledge graph — session briefings, pre-compaction checkpoints, and capture reflexes
Long-term memory for Claude Code — slash commands, skills, opt-in session hooks, codebase indexing, and a deep-retrieval subagent over the @memsy-io/mcp server.
Captures user prompts and agent responses to Memory Engine for persistent context across sessions
Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations.
Cross-host durable memory — same ling-mem daemon and store in Claude Code, Codex, OpenClaw, and Linggen. Three-tier model (core + long-term + episodic staging) of who the user is, not a log of what was done.
Local-first persistent memory system with automatic context injection and durable memory tools.