mengram-memory
Long-term memory with 3 types (facts, events, workflows). Self-improving procedures that evolve from failures. Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, tracking workflows, or reporting procedure outcomes.
Why use this skill?
Give your OpenClaw AI agent long-term memory for facts, events, and workflows. Mengram enables self-improving procedures and cross-session context.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/alibaizhanov/mengram-openclaw-skillWhat This Skill Does
Mengram Memory serves as the long-term cognitive core for your OpenClaw agent, enabling it to evolve from a stateless chatbot into a highly personalized assistant. By implementing a three-tiered memory architecture, it bridges the gap between disconnected interactions. Semantic memory stores stable facts about the user's life and preferences. Episodic memory tracks the timeline of events, meetings, and project milestones. Most uniquely, Procedural memory captures the steps of successful workflows and, crucially, evolves them. When a process fails, the skill triggers an automatic refinement loop, ensuring that the agent learns from mistakes and improves its efficacy over time. This cross-platform persistence ensures that knowledge gained in one channel remains immediately available in others.
Installation
To integrate Mengram into your environment, use the OpenClaw package manager:
clawhub install openclaw/skills/skills/alibaizhanov/mengram-openclaw-skill
Once installed, ensure the agent has write permissions for the {baseDir}/scripts/ directory, as the skill relies on executing localized Bash scripts to manage its vector databases and logic controllers.
Use Cases
- Contextual Personalization: Remembering dietary restrictions, scheduling preferences, or preferred communication styles to eliminate repetitive inputs.
- Project Management: Tracking the history of multi-step deployments or complex research tasks across weeks of interaction.
- Workflow Optimization: Saving frequently executed technical procedures as reusable scripts that become smarter every time they run.
- Historical Auditing: Answering questions like 'When was the last time I spoke to Sarah about the project?' by querying episodic logs.
Example Prompts
- "Check your memory and tell me what my specific requirements are for the upcoming budget meeting."
- "I've just successfully finished the database migration script. Please save this workflow as a standard procedure so we can run it automatically next time."
- "Summarize what you know about my personal preferences so far."
Tips & Limitations
- Proactive Retrieval: Always trigger
mengram-search.shbefore finalizing responses to sensitive or history-dependent queries. - Granularity: Use descriptive, specific tags when saving data to allow for efficient future retrieval.
- Limitations: While highly robust, the system performs best when input data is structured. Avoid saving ambiguous or conflicting information without providing clarifying context for the agent to resolve.
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-alibaizhanov-mengram-openclaw-skill": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write, code-execution