simranjeet97/Synapse
Synapse: Enterprise-grade Agentic RAG system powered by Google Gemini 3. Features self-healing retrieval (CRAG), adaptive routing, hybrid search, and multi-layer security guards for high-accuracy, production-ready AI.
Synapse: Enterprise-grade Agentic RAG system powered by Google Gemini 3. Features self-healing retrieval (CRAG), adaptive routing, hybrid search, and multi-layer security guards for high-accuracy, production-ready AI.
npx skills add simranjeet97/SynapseSynapse: Enterprise-grade Agentic RAG system powered by Google Gemini 3. Features self-healing retrieval (CRAG), adaptive routing, hybrid search, and multi-layer security guards for high-accuracy, production-ready AI.
Store and search AI agent conversations to recover lost context and improve memory persistence in multi-agent workflows.
Agent skill repository discovered by 10x-chat research.
A self-hostable, open-source, semantically-searchable Agent Skills registry delivered over MCP, with a three-tier progressive disclosure architecture.
AI memory brain for Claude Code, Cursor, Copilot & Windsurf — 51 MCP tools. Persistent sessions, lessons learned, semantic search, Team Brain, managed Valkey/Redis. Free tier.
English LaTeX paper assistant for existing .tex conference and journal manuscripts (IEEE, ACM, Springer, NeurIPS, ICML). Use for compile diagnosis, venue formatting, BibTeX or Biber checks, grammar, logic, abstract, title, figure, table, pseudocode (algorithm2e, algorithmicx, algpseudocodex), experiment-section review, related-work synthesis, research-gap derivation, journal adaptation, de-AI polish, translation, or submission readiness. Trigger for prompts like "proofread my LaTeX paper", "fix my .tex build", "rewrite related work", "derive research gap", "check booktabs table", "review algorithm2e pseudocode", "改投会议", or "换投期刊". Use latex-thesis-zh for Chinese degree theses, typst-paper for .typ projects, and paper-audit for reviewer-style critique.
Implement a research paper as an interactive marimo notebook together with the user. Start by understanding what the user wants to explore, fetch the paper via alphaxiv, then build a focused notebook.