Permission-aware RAG knowledge base for agents — ingest docs, hybrid search, cited answers (hosted API).

MCP server for LandBenchmark — satellite land due-diligence. Exposes an analyze_parcel tool so AI agents can pull a green/caution/walk-away verdict with cited signals for any parcel.

CLI prose linter + AI-slop detector: weasel words, passive voice, hedging, filler adverbs, and research-cited AI tells in text and Markdown

Governed second brain — a Claude Code + Cowork plugin + installer. ONE plugin, two modes: local (default) turns your files into cited memory with deterministic governance and a tamper-evident audit trail after one-time native dependency provisioning; team

Multi-angle visual & technical QA for websites, local dev servers, and built output — real screenshots, axe-core accessibility, mobile/console/network checks, optional AI review lenses. Honest, evidence-cited reports.

MCP server for Kodiak — verifiable fact-checking. Verify a factual claim and get a verdict, calibrated confidence, cited sources, and a tamper-evident certificate anyone can verify.

n8n community node for knowledgelib.io — query pre-verified, cited knowledge units for AI agents

Nankai Trough (南海トラフ地震) earthquake hazard and building-safety for AI assistants. Official Japanese government figures, cited and dated, never a safety verdict.

Pi extension for collecting file/line evidence seen or cited during a session.

AITaxAdvise CLI — AI-powered tax research for coding agents. Ask tax questions, get cited legislation.

Agent skill for researcher.now: article & video analysis (formatted content + structured claims/facts/quotes) and deep multi-source research returning cited Research Reports. Includes SKILL.md for Hermes/Claude-style skill loaders.

abm.dev — the account-based marketing API for AI agents. Search, Enrich, and Create across B2B people and companies; every field cited with a source and confidence score. Thin local stdio bridge to the hosted MCP server (mcp.abm.dev, OAuth 2.1 PKCE).

Evidence-backed research workspace for source review, claim validation, cited memo drafting, and export.

A local-first governed second brain for Claude Code — turn your own files into cited (qmd://) memory, with every write run through deterministic governance and recorded in a tamper-evident, SHA-256 ha

Turn user session recordings into cited pull requests and issues on Tangled

MCP server for the complete 49 CFR 172.101 Hazardous Materials Table: hazmat lookup, special-provision decoding, parsing, and basic compliance checks — every field cited to a pinned eCFR revision.

Neutral freight reference + validation layer for AI agents — ADR dangerous goods, HS codes, airlines, airports, UN/LOCODE, Incoterms, identifier validation and freight math. Every tool declares a typed output schema and returns a source-cited response env

A deterministic linter for Sui Move. Rules cited via the Move Book, with a SKILL.md for coding agents.

Evidence-cited analyzer for AGENTS.md / CLAUDE.md agent instruction files: score, findings, and what to cut - every rule backed by a research citation. Native Rust binary.

Token-saving web research for the pi coding agent — a sub-agent pipeline distills search results and pages into cited briefings instead of dumping them into context. Kagi + Wyna backends, SSRF-guarded, privacy-focused.