Documents repo of ForkSilly. ForkSilly：兼容sillytavern（酒馆）角色卡、世界书、正则、预设、聊天记录的安卓移动端应用；同时也可作为stable diffusion客户端使用。

Robot Memory - Persistent memory system for AI robots. MCP Server + hybrid search + spatial retrieval.

⚠️ 本工具仅用于授权的安全测试。未经授权使用本工具进行网络攻击是违法的。一个智能化的自动化渗透测试机器人，具备AI驱动的安全测试能力。

Find relevant information in your documents using natural language queries - no more keyword matching or manual browsing through hundreds of files. Built for speed and efficiency, this lightweight system searches through 500+ documents in under 300ms while using only 100MB of memory.

Your AI forgets everything between sessions. SAME fixes that. Local-first, no API keys, single binary.

A high-performance AI agent built with Go

Advanced RAG System with Go featuring intelligent adaptive chunking, hierarchical document processing, semantic search, and flexible LLM integration

Git-native, semantically-searchable memory storage for Claude Code. Captures decisions, learnings, and context as git notes with vector search.

Local Codex CLI prompt refinery: ingest JSON/JSONL histories, dedupe, embed (OpenAI), cluster (sqlite-vec), synthesize atomic/workflow prompts via Responses API (Structured Outputs). FTS5+vector search; Streamlit UI; Typer CLI.

triage tool for repos drowning in PRs. finds duplicates, ranks quality, checks vision alignment.

A searchable image database using SigLIP 2 (CLIP) embeddings and SQLite-vec for efficient similarity search.

NeuralRP: local RP engine with SQLite backend. Built to solve the problem of context rot, with best-in-class image generation features.

🔒 100% Local RAG pipeline for .md documents — Ollama + SQLite-vec + MarkItDown MCP. Built on Microsoft.Extensions.DataIngestion (.NET 10)

Node-RED as an LLM-chain framework with IoT

CLI RAG tool - index 30+ document formats, hybrid search, ask questions and get sourced answers.

A lightweight Python client around sqlite-vec for CRUD and similarity search.

Local-first persistent memory for AI agents via MCP. Sanskrit for memory (स्मृति). Zero cloud. Zero cost.

A local semantic emoji search engine that uses transformer embeddings and sqlite vector search to find the perfect emoji from natural language queries. Fast, offline, and powered by Streamlit.

VEKTOR replaces flat vector storage with a structured, multi-layered memory architecture. The only AI memory system that dreams. 4-layer associative graph memory (MAGMA) with autonomous REM cycle

🛠️ Refine and organize your OpenAI Codex CLI prompts effortlessly, using SQLite for fast search and a user-friendly interface for better productivity.