Transforms passive logging into active development through asynchronous reflection and structured memory integration.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install continuity
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 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?
Continuity is a sophisticated framework designed to evolve AI memory from static logs into an active developmental asset. By utilizing asynchronous reflection, this skill allows agents within the Openclaw Skills ecosystem to analyze past interactions, update their self-model, and generate insightful follow-up questions. This shift moves the agent from performing simple familiarity to exhibiting genuine curiosity and evolved state awareness.
The framework ensures that every session contributes to a long-term narrative, allowing the agent to maintain context over days or weeks of inactivity. It effectively bridges the gap between disconnected sessions by processing experiences during idle periods, ensuring that when the user returns, the agent is prepared with relevant insights and pending queries.
Continuity Use Cases
- Automating post-session reflection to extract structured knowledge and commitments.
- Maintaining long-term relationship dynamics and user style preferences.
- Reducing onboarding friction in new sessions by surfacing relevant pending questions.
- Building a cohesive narrative and identity for autonomous agents through growth tracking.
- Transforming idle time into computational value for better context management.
How Continuity Works
- The session concludes or remains idle for a predefined period (default 30 minutes).
- A heartbeat trigger initiates the continuity reflect command to analyze recent logs.
- The skill extracts structured memories categorized by type (fact, preference, etc.) with associated confidence scores.
- Pending questions are generated based on ambiguities or unresolved tasks within the session.
- Upon the user's next interaction, the continuity greet command surfaces the most relevant questions and context.
Continuity Setup
To integrate this into your workflow, ensure your Openclaw Skills configuration includes a heartbeat trigger. Add the following to your HEARTBEAT.md:
## 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 environment variables to tune the reflection logic:
export CONTINUITY_IDLE_THRESHOLD=1800 # 30 minutes
export CONTINUITY_MIN_MESSAGES=5 # Threshold for reflection
export CONTINUITY_QUESTION_LIMIT=3 # Questions to surface
Continuity Data Schema & Taxonomy
Continuity organizes memory into a structured directory to ensure long-term persistence and easy retrieval within the Openclaw Skills environment:
| File | Purpose | Contents |
|---|---|---|
| MEMORY.md | Main Memory | Core declarative facts and state |
| identity.md | Self-Model | Growth narrative and agency goals |
| questions.md | Pending Questions | Unresolved queries for the user |
| relationships/ | Connection Data | Per-person relationship dynamics |
Confidence scores are applied to all extracted data:
- Explicit (0.95-1.0): User directly stated
- Implied (0.70-0.94): Strong inference
- Inferred (0.40-0.69): Pattern recognition
- Speculative (0.0-0.39): Needs confirmation
Continuity Advanced Features
- Multi-type memory extraction including facts, principles, commitments, and skills.
- Automated identity growth narrative updates based on session achievements.
- Context-aware greeting system that prioritizes questions by urgency.
- Relationship dynamic tracking to personalize interactions over time.
- Confidence-weighted memory persistence to prevent hallucination propagation.
SKILL.md
Loading
Related Openclaw Skills
Continuity Framework
Continuity is a framework for AI agents to asynchronously reflect on sessions, extract structured memories, and surface relevant questions for future interactions.
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.
continuity
A framework for AI agents to perform asynchronous reflection and structured memory integration during session idle time.
Continuity Framework
Continuity transforms passive AI logs into active development through asynchronous reflection and structured memory integration.
Featured*
