Continuity is a framework for AI agents to asynchronously reflect on sessions, extract structured memories, and surface relevant questions for future interactions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install continuity-framework
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install continuity-framework using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Continuity Framework?
Continuity Framework is a sophisticated skill designed for developers using Openclaw Skills who want their AI agents to evolve beyond simple session logging. Instead of just reading past notes, this skill enables agents to perform deep post-session reflection, synthesizing facts, preferences, and commitments into a persistent memory state.
By integrating these insights into a self-model, the agent transitions from a passive assistant to an active, evolving collaborator. It ensures that every interaction contributes to a growing body of knowledge, allowing the agent to maintain a genuine sense of context and curiosity across multiple sessions.
Continuity Framework Use Cases
- Automating post-session reflection to extract key project facts and developer preferences.
- Generating follow-up questions for the next user session to maintain project momentum.
- Updating agent identity and relationship dynamics based on long-term interaction patterns.
- Managing complex commitments and obligations through structured memory integration.
How Continuity Framework Works
- Trigger reflection via a heartbeat event after a conversation remains idle for a set period (default 30 minutes).
- Analyze the most recent conversation history to extract structured memories with associated confidence scores.
- Integrate new findings into the long-term memory state, updating facts, principles, and relationship data.
- Generate context-aware follow-up questions based on gaps in knowledge or pending commitments.
- Surface these questions and relevant context using Openclaw Skills when the user starts a new session.
Continuity Framework Setup
To integrate this into your workflow, add the following to your HEARTBEAT.md file:
## Post-Session Reflection
**Trigger**: Heartbeat after conversation idle > 30 minutes
**Action**: Run continuity reflect
**Output**: Updated memories + questions for next session
You can also configure the behavior via environment variables:
export CONTINUITY_IDLE_THRESHOLD=1800 # Seconds before reflection triggers
export CONTINUITY_MIN_MESSAGES=5 # Minimum messages to warrant reflection
export CONTINUITY_QUESTION_LIMIT=3 # Max questions to surface at once
Continuity Framework Data Schema & Taxonomy
The skill organizes data within the memory/ directory using a clear taxonomy to ensure high-fidelity retrieval. Data is stored across the following files:
| File | Purpose |
|---|---|
MEMORY.md |
The primary record of facts and learned principles. |
identity.md |
Stores the self-model and narrative growth of the agent. |
questions.md |
A queue of pending questions generated during reflection. |
relationships/ |
Per-person directory for tracking interaction dynamics. |
reflections/ |
Optional logs documenting specific reflection cycles. |
Each memory entry includes a confidence score ranging from 0.0 (Speculative) to 1.0 (Explicit).
Continuity Framework Advanced Features
- Confidence-based memory extraction to differentiate between direct statements and subtle pattern recognition.
- Identity growth narrative tracking that allows the agent to evolve its persona and role over time.
- Contextual greeting system via the
greetcommand that automatically surfaces pending questions at the start of a session. - Multi-type memory taxonomy including skills, principles, moments, and relationship dynamics for a human-like memory structure.
SKILL.md
Loading
Related Openclaw Skills
Happy Hues
A design-focused skill that provides curated, role-based color palettes to help AI agents generate beautiful and functional UI color schemes.
Task Tracker
A proactive state management system that ensures AI agents maintain progress context across session resets and complex multi-step workflows.
Salesforce Query (Schema-Adaptive)
A schema-adaptive Salesforce integration for Openclaw Skills that discovers environment-specific data structures to enable resilient GTM workflows.
Immersive AR/VR Marketing for High-Visual Products
A professional framework for designing and deploying AR, VR, and 3D immersive shopping experiences tailored for high-value, visual-centric products.
Continuity
Transforms passive logging into active development through asynchronous reflection and structured memory integration.
continuity
A framework for AI agents to perform asynchronous reflection and structured memory integration during session idle time.
Featured*
