Alimenter votre agent
L'URL propre à l'éditeur. Ce n'est pas un endpoint PlugMCP.
Host a copy with our keys and logs.
https://memcell.ai/mcpLe bouton Claude ci-dessus ouvre Claude avec le nom et l'URL préremplis. Il vous reste à confirmer sur place.
claude mcp add --transport http ai.memcell-memcell https://memcell.ai/mcpRun in a terminal.
{ "mcpServers": { "ai.memcell-memcell": { "command": "npx", "args": [ "-y", "mcp-remote", "https://memcell.ai/mcp" ] } }}claude_desktop_config.json
URL distante ou commande sur votre machine ? Ce qui distingue les deux installations
Exécuter sur PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LancerDe l'éditeur
# Install globally
npm install -g memcell
# In any project:
memcell connect
Run it in any project. memcell connect automatically:
Shared, persistent memory for AI agents: recall before acting, report outcomes to earn confidence.
memcell mcp.memcell: Adds a clean, git-safe project descriptor to your repo root.Verify anytime:
memcell status
Every time you start a new session with an AI agent, it starts with complete amnesia. It falls into the same traps, repeats outdated assumptions, and recreates issues you already resolved yesterday.
Static instruction files and monolithic system prompts don't solve this:
MemCell gives your agents closed-loop memory:
MemCell pairs two lightweight layers so agents stay aligned without getting in your way:
memcell mcp): Provides interactive tools (recall, remember, report, ingest) when agents need to search memory or record discoveries mid-turn.Once connected, agents recall and report memory automatically. You can also interact with memory directly from your terminal:
memcell recall "how do we handle multi-tenant database sessions?"
# Record a project convention
memcell remember "Always use pnpm for package operations; never invoke npm directly"
# Bind an invariant to a specific lifecycle trigger
memcell remember "Check database migrations for column locks before altering tables" --at "before db:migrate"
Memories sharpen when told what happened. When an approach succeeds or fails, report the outcome:
memcell report stmt_019a4b2c worked --note "CI suite passed cleanly"
memcell report stmt_019a4b2c failed --note "broke Next.js 15 async cookies"
# Ingest an architecture doc, spec, or post-mortem
memcell ingest docs/architecture/auth.md
# Scan and import existing guideline files (CLAUDE.md, etc.)
memcell import
memcell stats
Displays memories followed, errors avoided, estimated tokens saved from prevented error loops, and 30-day activity sparklines.
Run memcell --help or memcell <command> --help for full flag details.
To remove MemCell hooks from a repository without touching your code:
memcell hook remove
rm .memcell
To remove all stored keys and credentials from your local machine:
memcell reset
Apache License 2.0 · © 2026 OpenOri
Shared, persistent memory for AI agents: recall before acting, report outcomes to earn confidence.
{ "mcpServers": { "ai.memcell-memcell": { "url": "https://memcell.ai/mcp", "headers": {} } }}Outils
Pas encore de liste d'outils. Les serveurs distants en obtiennent une après le premier contrôle d'état.
FAQ
Copiez sur cette page la configuration http pour Cursor, Claude Desktop, Claude Code ou VS Code. Elle utilise l'installation de l'éditeur, pas un proxy PlugMCP.
Aucune variable d'environnement requise n'est indiquée sur cette fiche.
MemCell est accessible via HTTP.
Dernière vérification : 2026-10-19. Shared, persistent memory for AI agents: recall before acting, report outcomes to earn confidence.