gavdalf/total-recall

Registry 信息

项目简介

Total Recall 是为 OpenClaw 智能体设计的自主记忆系统，采用五层观测记忆架构。它是唯一具备自我监控能力的记忆系统，月费仅约 0.10 美元。

要点

• 五层观测记忆架构
• 自主自我监控能力
• 专为 OpenClaw 智能体设计
• 月费仅约 0.10 美元

使用场景

• 增强智能体记忆持久性
• 自主任务追踪与回忆
• 长时间运行的智能体工作流
• 高效记忆的 AI 智能体操作

README 摘要

# Total Recall > **Note (April 2026):** This project is currently on hold. I'm focusing on other work for the foreseeable future. The code works, the docs are accurate, and issues/PRs are welcome, but response times will be slower than usual. See [#22](https://github.com/gavdalf/total-recall/issues/22) for details. Autonomous memory for OpenClaw-style agents. Total Recall v2.0 keeps the existing v1.x stack intact: - Observer - Reflector - Session Recovery - Reactive Watcher - Dream Cycle It also adds the Ambient Intelligence Engine (AIE): a configurable sensor and rumination pipeline that can watch external systems, think about what changed, maintain a preconscious buffer, and surface urgent items. Prerequisites: `python3`, `jq`, `curl`, and `PyYAML`. Install PyYAML with: ```bash python3 -m pip install PyYAML # or on Debian/Ubuntu: sudo apt install python3-yaml ``` `setup.sh` will verify all dependencies are present before continuing. ## Architecture ### v1.x memory loop ```text Observer -> observations.md -> Reflector -> Dream Cycle -> session recovery / watcher ``` ### v2.0 Ambient Intelligence Engine ```text sensor-sweep -> enabled connectors emit events to memory/events/bus.jsonl -> rumination-engine reads new events and writes structured insights -> preconscious-select scores recent insights into memory/preconscious-buffer.md -> ambient-actions optionally enriches insights with read-only lookups -> emergency-surface pushes urgent alerts through configured channels -> buffer-inject sends the latest buffer back into the live session ``` The AIE flow is additive. None of the v1.x scripts are removed or replaced. ## Quick Start ### v1.x setup ```bash git clone https://github.com/gavdalf/total-recall.git cd total-recall bash scripts/setup.s

话题

暂无话题