Vector Search

URL to Markdown for AI agents and LLMs: turn any public web page into clean Markdown (HTML to Markdown, SSRF-safe, robots.txt-aware). MCP server (stdio + remote), zero-dependency library and x402 pay-per-call API ($0.002 USDC on Base).

Prompt injection + PII detection for LLM apps and agent pipelines. Deterministic, sub-25ms.

MCP server exposing NaN API tools: image generation/editing (flux-2-klein), TTS (kokoro), STT (whisper), embeddings and rerank

Persistent memory for Claude Code — offline, single-file, hybrid search.

Production-grade multi-agent harness for SDD-BDD-TDD software development. RAG memory (BM25), Obsidian vault, MCP server, agent auto-generation. Compatible with Claude, Codex, OpenCode, Kimi, Qwen, DeepSeek, and any AI tool.

A searchable second brain for AI agents: ranked keyword and semantic search over your Markdown.

Persistent, local-first memory for AI coding agents (Claude Code, Codex CLI, Cursor, Copilot CLI): plain markdown in your repo, schema-enforced, relevance-gated recall via harness hooks or MCP. 100% offline.

Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.

Pay-per-request GPT chat, embeddings, agents and prepaid keys with local x402 USDC signing

📚 Model Context Protocol server for AI-powered storytelling — Mage image generation and content tools.

MCP control plane for local cognitive labor — job-shaped tools with tiered Ollama models (instant/workhorse/deep/embed), server-enforced guardrails, and measured economics so Claude can delegate bulk work without losing control.

Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code

One private, local memory your AI tools share. Cross-model, on-device, never lose a session.

Searchable memory for your Claude Code sessions: local hybrid search with reranking, a CLI, and an MCP server for agents.

Unified web ingestion for AI agents: perceive, discover, search, extract, ingest, watch, convert.

A zero-configuration RAG memory server for MCP clients

High-performance WebAssembly theorem prover with dependent types, hash-consing (150x faster), Ed25519 proof signatures, MCP support for Claude Code, AgentDB vector search, episodic memory, and ReasoningBank learning. Formal verification with cryptographic

Semantic search over WSO2 docs (APIM, IS, MI, Choreo, Ballerina) via RAG and pgvector.

Turn any URL into clean Markdown or text for LLMs, RAG and agents. Strips nav, ads and footers.

AI-agent-friendly web spider: structured output, RAG-ready chunks, graph-traversable links