inner-life-memory
Your agent loses context between sessions and performs familiarity instead of genuine recall. inner-life-memory transforms passive logging into active development — structured memories with confidence scores, curiosity tracking, and questions that carry forward.
Why use this skill?
Transform your OpenClaw agent with inner-life-memory. Implement structured recall, curiosity tracking, and persistent context across sessions to enable genuine agent continuity.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/dkistenev/inner-life-memoryWhat This Skill Does
inner-life-memory is designed to evolve OpenClaw from a stateless assistant into an agent with persistent, structured continuity. By implementing a formal reflective loop, the agent transforms raw session data into a persistent 'inner life' comprising facts, preferences, relationships, and principles. It moves beyond simple context windows by maintaining an active, evolving knowledge graph stored in local JSON and markdown files. The skill forces the agent to move from 'simulating familiarity' to 'practicing genuine recall,' ensuring that commitments, lessons, and curiosities from past sessions are carried forward into future interactions.
Installation
To install this skill, use the ClawHub CLI: clawhub install openclaw/skills/skills/dkistenev/inner-life-memory. Before initialization, ensure inner-life-core is installed via clawhub install inner-life-core. Run the initialization script provided in the core repository to generate inner-state.json and drive.json. Without these dependencies, the memory system cannot function.
Use Cases
This skill is perfect for long-term project management, personalized research, and deep-learning companionship. Developers can use it to track project architectural decisions and coding preferences. Researchers can use it to maintain 'Curiosity Backlogs' that span weeks, ensuring that half-formed ideas aren't lost in session gaps. It is also highly effective for building deeper, more professional rapport with users, as the agent remembers critical context, past constraints, and personal communication styles.
Example Prompts
- "Reflect on our work session today and update the memory graph with the key architectural decisions we made for the backend."
- "Review the current curiosity backlog; are there any open questions we should focus on during this session?"
- "Do we have any unresolved commitments or pending tasks in our records that need attention today?"
Tips & Limitations
- Tip: Always perform the post-session reflection to ensure the memory store remains accurate. Stale data reduces the agent's confidence score.
- Tip: Use the confidence system to your advantage; if the agent is uncertain about a fact, ask it to look up the source file to clarify the context.
- Limitation: The skill requires diligent file management. If the markdown structure of
MEMORY.mdorquestions.mdis compromised by manual edits, the agent may struggle to parse the information correctly. - Warning: Do not store sensitive personal credentials or highly private data in the memory files unless your local storage environment is adequately encrypted.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-dkistenev-inner-life-memory": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read
Related Skills
inner-life-reflect
Your agent repeats the same patterns without learning. inner-life-reflect adds self-reflection with trigger detection and quality gates — your agent observes its own behavior, notices shifts, and evolves its personality over time through SELF.md.
inner-life-evolve
Your agent does the same things the same way forever. inner-life-evolve analyzes patterns, challenges assumptions, and proposes improvements — writing proposals to the task queue for user approval. Never auto-executes. Evolution with a safety net.
inner-life-chronicle
Your agent processes thousands of interactions but never reflects on the day. inner-life-chronicle generates a structured diary — what happened, what was learned, how it felt, what's next. Not a log. A journal.
inner-life-core
Your agent forgets who you are between sessions. It gives the same responses every day. It doesn't grow. inner-life-core fixes that. Gives your OpenClaw agent emotions with half-life decay, a 9-step Brain Loop protocol, and structured state — the foundation for an inner life. Works standalone or with inner-life-* extension skills.
inner-life-dream
Your agent only works on tasks and never thinks creatively. inner-life-dream adds freeform exploration during quiet hours — hypotheticals, future scenarios, unexpected connections. Like dreaming, but captured for review.