engram-memoryPersistent semantic memory for AI agents — local, fast, free. Use when agent needs to recall past decisions, store new facts/preferences, search conversation history, or maintain context across sessions.
Install via ClawdBot CLI:
clawdbot install Dannydvm/engram-memoryLocal semantic memory with biological decay, typed memories, and relationship graphs. No API keys. No cloud.
engram search "<current task or context>" --limit 10Always recall before working. Accessed memories get salience-boosted.
engram add "Client uses React with TypeScript" --type fact --tags react,client
engram add "We decided to pause ads" --type decision --tags ads
echo "Raw conversation text" | engram ingestTypes: fact, decision, preference, event, relationship
engram search "what tech stack"
engram search "pricing decisions" --type decision
engram search "client status" --agent client-agentengram relate <src> <tgt> --type supports
engram auto-relate <id>
engram relations <id>Types: related_to, supports, contradicts, caused_by, supersedes, part_of, references
engram stats
engram recall --limit 10
engram export > backup.json
engram import backup.jsonGenerated Mar 1, 2026
A customer support AI uses Engram to remember previous customer interactions, technical issues resolved, and customer preferences. This allows the agent to provide personalized support without repeating questions, improving resolution time and customer satisfaction.
A personal AI assistant employs Engram to store user preferences, past decisions (like travel choices or meeting schedules), and important facts across sessions. This enables the assistant to maintain context about the user's life without relying on cloud services, ensuring privacy.
A software development team's AI agent uses Engram to record technical decisions, architecture choices, and coding standards agreed upon during meetings. The agent can recall these decisions when answering new team questions, ensuring consistency and reducing rework.
A marketing AI utilizes Engram to store past campaign performance data, audience preferences, and strategic decisions. By searching this memory, the agent can recommend optimized marketing strategies based on historical successes and failures without external databases.
A healthcare AI agent uses Engram to maintain a local, private memory of patient interactions, treatment decisions, and medical preferences. This allows the agent to assist healthcare providers by quickly recalling relevant patient history while complying with privacy regulations.
Offer Engram as a free, open-source tool for basic memory functions, with paid tiers for advanced features like enhanced relationship graphing, team collaboration tools, or priority support. This attracts developers and small teams while monetizing enterprise needs.
Provide customized versions of Engram with additional security, compliance features, and integration support for large companies. Charge based on the number of agents, data volume, or through annual enterprise licenses, targeting industries with strict data privacy requirements.
Generate revenue by offering professional services to help organizations integrate Engram into their existing AI workflows. This includes custom development, training, and ongoing support, leveraging expertise in semantic memory and agent systems.
💬 Integration Tip
Start by integrating Engram's search command at the beginning of agent workflows to recall relevant memories before processing new tasks, ensuring context is maintained efficiently.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection