shodh-localLocal offline cognitive memory for AI agents providing semantic recall, GTD todos/projects, and a knowledge graph with Hebbian learning and a TUI dashboard.
Install via ClawdBot CLI:
clawdbot install doobidoo/shodh-localGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:3030/api/rememberCalls external URL not in known-safe list
http://localhost:3030/api/rememberAI Analysis
The skill interacts only with a local server (localhost:3030) as documented, with no evidence of data transmission to external or unauthorized servers. The API usage is fully consistent with the skill's stated purpose of providing a local-first cognitive memory system. No credential harvesting, hidden instructions, or obfuscation were found.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
An AI assistant uses Shodh-Local to manage a user's GTD todos, projects, and personal memories. It recalls context from previous interactions to provide continuous support, such as reminding about deadlines or summarizing learned topics, all processed locally for privacy.
Researchers employ Shodh-Local to store and semantically recall notes, observations, and literature findings. The knowledge graph helps connect ideas across projects, enabling efficient retrieval of relevant information for papers or experiments without cloud dependency.
A customer support AI agent uses Shodh-Local to remember past interactions, preferences, and issues for specific users. It proactively recalls context to provide personalized responses and track ongoing tasks, improving resolution times and customer satisfaction.
Writers and content creators leverage Shodh-Local to store ideas, plot points, and character details. The semantic recall helps retrieve inspiration based on themes or tags, while todos manage writing schedules and project milestones offline.
A healthcare AI uses Shodh-Local to log patient observations, treatment plans, and learning from medical data. It recalls relevant history for diagnoses and manages follow-up tasks, ensuring continuity of care with local data storage for compliance.
Offer Shodh-Local as a paid service with enhanced features like advanced analytics, cloud sync options, and premium support. Target indie developers and small teams building AI applications, charging monthly or annual fees per user or API call.
Sell enterprise licenses to large organizations needing tailored deployments of Shodh-Local. Include custom training, dedicated support, and integration with existing systems like CRM or project management tools, with one-time or annual licensing fees.
Provide Shodh-Local as open-source software for basic use, monetizing through premium add-ons such as advanced TUI dashboards, priority updates, and commercial support. Attract a community of users who upgrade for enhanced functionality.
💬 Integration Tip
Ensure the local server is running on localhost:3030 with a valid API key, and use consistent user IDs and tags for effective memory recall and organization.
Scored Apr 19, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Automatically prune and compact agent memory files to prevent unbounded growth. Circular buffer for logs, importance-based retention for state, and configura...
Founder onboarding interview that captures company context across 7 dimensions. Invoke with /cs:setup for initial interview or /cs:update for quarterly refre...
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vib...
Expert skill for memory-lancedb-pro — a production-grade LanceDB-backed long-term memory plugin for OpenClaw agents with hybrid retrieval, cross-encoder rera...