
from total-recall264
Autonomous agent memory that passively observes session transcripts, compresses them into prioritized notes, consolidates redundancies, and recovers missed cont
Total Recall adds a persistent, observation-driven memory layer to an agent. It periodically scans recent session transcripts, compresses them into prioritized observations, consolidates and prunes redundant items, and provides session-recovery hooks to capture missed context. Optional reactive watching makes capture near-real-time on high activity.
Use Total Recall when you want cross-session continuity without managing databases or vector indexes: long-running agents, teams needing concise memory logs, or agents that must preserve important events with minimal maintenance. It's ideal for agents that should "just pay attention" and surface prior decisions, preferences, or follow-ups.
prompts/ for Observer/Reflector.Works with agents that can run shell scripts and call LLM providers (OpenRouter, Ollama, Groq). Particularly suited to OpenClaw-style agents and cron-driven agent runs.
This skill has not been reviewed by our automated audit pipeline yet.