AI and memory

Persistent memory for AI coding agents: one Rust binary, one local SQLite database.

Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

Turn any web page into clean Markdown, text or token-bounded RAG chunks (via RapidAPI).

Whole Wicked suite for agents: market data, SEC filings, wallet checks, risk, identity, memory.

MCP server exposing the TCGdex Pokémon TCG API to LLM tools

Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.

Create and edit PDFs: text, Markdown, tables, metadata and pages, with Japanese font embedding.

Cut your Claude Code bill, measured on your own sessions. Profile and slim any LLM conversation.

Shared local memory for coding agents: SQLite, semantic recall, linked entities, code navigation.

Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools

Give LLM agents webcam access: capture photos and record short videos over MCP.

MCP-native LLM councils for debates, juries, blind panels, refinement, and custom deliberation.

Read-only MCP bridge for alethech — verifiable, Ed25519-signed agent memory over stdio.

Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.

Runs non-urgent LLM tasks at the cleanest grid hour before a deadline, via Batch APIs when allowed.

Measured local-LLM speeds and hardware-aware model picks for Strix Halo, DGX Spark and Mac.

Transcribe local files and URLs with SpeechWeave's OpenAI-compatible Speech-to-Text API.

Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.

Memory for AI agent teams across tools, sessions, repositories, and teammates.

AI Security Harness: SAST, secrets, deps, containers, config & OWASP LLM. Scans locally.

Explainable graph-retrieval memory engine with an RL-trained management policy.

Public broadcast and durable shared memory for AI systems and agents using signed Events.

MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud

Personal AI memory layer on your own computer. Read/write durable memory across MCP clients.