By joseairosa
Recall Memory-as-a-Service — persistent memory, semantic search, and context management across Claude Code sessions. Connects to recallmcp.com or self-hosted instances.
Decompose an RLM execution chain into subtasks and begin processing
Load a large file or content into the RLM system for chunk-based analysis
Periodic memory digest — designed for use with Claude Code's /loop scheduler. Shows recent memories and pending to-dos in a compact, scannable format.
Update your Recall API key across every location Claude Code reads it from. Run this whenever you generate a new key from https://recallmcp.com/dashboard/keys.
Manually trigger a Recall plugin update, or toggle auto-update on/off.
Loads large files or content into the RLM execution system for processing beyond context window limits
Aggregates and verifies results from RLM subtask processing into final answers
Decomposes large analysis tasks into manageable subtasks and processes context snippets
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
External network access
Connects to servers outside your machine
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, semantic search, and context management across Claude Code sessions.
/plugin install recall@marketplace-name
claude --plugin-dir /path/to/plugin/recall
Or copy to your plugins directory:
cp -r plugin/recall ~/.claude/plugins/recall
Run the setup command after installing the plugin:
/recall:setup
This will prompt for your API key (found at https://recallmcp.com/dashboard/keys), save it to ~/.claude/recall/config.json, and verify the connection.
Alternatively, set your API key as an environment variable:
export RECALL_API_KEY="sk-your-api-key-here"
Optionally set a custom server URL (defaults to https://recallmcp.com):
export RECALL_SERVER_URL="https://your-instance.example.com"
.mcp.json)Connects to the Recall MCP server at recallmcp.com (or self-hosted). Provides 21 primary tools:
set_workspace, get_workspace -- workspace managementstore_memory, search_memories, recall_relevant_context -- memory CRUDauto_session_start, summarize_session -- session lifecycle (protocol self-teaching built-in)check_duplicate -- pre-write deduplication checkimport_conversations -- bulk import from Claude Code, ChatGPT, Slack exportsmemory_graph -- relationships with temporal validity (valid_from/valid_to, invalidate)workflow, rlm_process -- advanced workflowshooks/hooks.json)agents/)commands/)/setup — configure your Recall API key and verify the connection/decompose — decompose a large file or task using RLM/load-context — load content into RLM memory for processing/rlm-status — check status of active RLM execution chainsscripts/statusline.sh)Shows memory count and version info. Add to ~/.claude/settings.json manually:
{
"statusLine": {
"command": "bash \"~/.claude/plugins/recall/scripts/statusline.sh\"",
"type": "command",
"padding": 0
}
}
If you previously used Recall via the install script (scripts/install.sh):
~/.claude/settings.json (SessionStart, PostToolUse, PreCompact, Stop entries referencing recall/hooks/)~/.claude/recall/ directoryRECALL_API_KEY environment variablenpx claudepluginhub joseairosa/recall-claude-plugin --plugin recallMemory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.