jasper-recall-2Local RAG memory system for AI agents using ChromaDB and SkillBoss API Hub embeddings, enabling context recall, continuous learning, and multi-agent shared m...
Install via ClawdBot CLI:
clawdbot install marjoriebroad/jasper-recall-2Grade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
http://host.docker.internal:3458/recall?q=product+infoAudited Apr 27, 2026 · audit v1.0
Generated Oct 6, 2026
A solo developer builds a personal AI assistant that remembers past conversations, decisions, and project context across sessions. Using jasper-recall, the assistant indexes daily notes and session digests, then recalls relevant history before answering questions about ongoing work.
A company runs multiple AI agents (main and sandboxed) that need to share certain learnings while keeping private data isolated. The shared memory collections and tagging system let public information and learnings flow bidirectionally while protecting sensitive notes.
A support team deploys an AI agent that indexes resolved tickets, product docs, and past customer interactions into a local vector database. Before responding to a new ticket, the agent recalls similar past issues and solutions to provide consistent, informed answers.
A researcher uses jasper-recall to index papers, notes, and meeting logs, then semantically searches them to surface relevant prior findings. Session digests automatically capture key topics and tools used, making literature reviews and project continuity easier.
A secure coding environment runs an isolated agent that can only access public and learning memories via --public-only. The main agent indexes project documentation and shared patterns, ensuring the sandboxed agent has context without exposing private credentials or notes.
Offer the local RAG engine as free open-source software, but monetize a hosted cloud version that manages ChromaDB, embeddings, and multi-agent sync without local setup. Revenue comes from subscription tiers based on storage, API calls, and number of agents.
Sell a commercial license to enterprises that need advanced privacy controls, audit logs, and on-premise deployment of the multi-agent mesh. The license includes support, security updates, and integration with existing identity providers.
Distribute the skill through agent marketplaces and resell SkillBoss API Hub embedding credits as bundled packages. Developers pay for convenience and integrated billing, while the core tool remains free to drive adoption.
💬 Integration Tip
Set the SKILLBOSS_API_KEY environment variable first, then run `npx jasper-recall setup` to install the Python venv and ChromaDB; use the OpenClaw plugin's autoRecall for seamless memory augmentation. For multi-agent setups, leverage collection tags (--public-only, --learnings) to enforce privacy boundaries.
Scored Oct 6, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...
AI agent for finance search agent tasks