session-memory
Persistent session memory system that prevents knowledge loss after context compaction. Converts session transcripts to searchable Markdown, builds an auto-updating glossary index (people, projects, decisions, timeline), and sets up cron jobs for continuous indexing. Use when: (1) the agent forgets details after compaction, (2) you want to recall who was discussed or what was decided in past sessions, (3) setting up long-term memory for a new OpenClaw agent, (4) the user asks about memory loss, session recall, or knowledge persistence across sessions.
Why use this skill?
Prevent AI context loss with Session Memory. Automatically index, search, and manage your long-term agent interactions, decisions, and project data.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/moltbotmolty-del/faya-session-memoryWhat This Skill Does
The session-memory skill is a robust infrastructure layer designed to solve the critical issue of knowledge degradation in long-running AI agents. As agents perform context compaction to manage memory limits, they often discard specific, granular details. This skill provides a persistent, searchable, and structured memory hierarchy. It converts raw JSONL session logs into a queryable Markdown format, aggregates entities into a living glossary (capturing people, project milestones, decisions, and timelines), and automates maintenance through cron-based indexing. By anchoring agent interactions in a permanent, vectorized file structure, the skill ensures that no specific project detail, decision, or stakeholder note is ever truly forgotten.
Installation
To install the skill, execute the following command in your terminal:
clawhub install openclaw/skills/skills/moltbotmolty-del/faya-session-memory
Once installed, you must perform the initial setup:
- Run
python3 scripts/session-to-memory.pyto ingest your existing session history. - Run
python3 scripts/build-glossary.pyto generate the foundationalSESSION-GLOSSAR.md. - Configure your local cron jobs as outlined in the documentation to ensure the memory index stays synchronized with ongoing sessions.
Use Cases
- Project Management: Track evolving requirements and decisions across weeks of conversation.
- Stakeholder Tracking: Maintain a directory of people, their roles, and their contributions to specific sessions.
- Knowledge Retention: Prevent the 'amnesia' that occurs when an agent compacts its context window.
- Audit Trails: Review exactly when and why specific technical or business decisions were made.
Example Prompts
- "Based on our past sessions, who was the primary stakeholder that requested the v6 API migration?"
- "Can you check the SESSION-GLOSSAR.md and summarize all decisions made regarding the website-redesign project?"
- "I feel like we discussed a bug in the authentication module last month; can you search the session logs to find the specific error message?"
Tips & Limitations
- Performance: For agents with thousands of sessions, ensure the
--incrementalflag is used during cron tasks to avoid redundant processing. - Customization: Heavily leverage the
KNOWN_PEOPLEandKNOWN_PROJECTSdictionaries in the script. The more you prime the agent with context, the higher the retrieval accuracy. - Limitations: The skill relies on file system access. Ensure your environment has sufficient disk space for the generated Markdown library if you manage extremely large volumes of chat data. Note that content over 2KB per response is truncated to maintain performance.
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-moltbotmolty-del-faya-session-memory": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution