Give your Hermes agent the web as real sources, never a made-up answer — multi-provider search and extraction with an optional local, key-free DonSeTch option.

Local-first, source-grounded prompt library & workflow toolkit for Gemini Notebook (NotebookLM). 90 prompts · 30 themes · 3 audiences · 10 workflows.

Deterministic evidence-packet checks for AI-generated claims: references, quotes, numbers, and support gaps. CLI, Python, MCP, and review adapters.

Turn contested questions into interactive, source-grounded evidence maps.

ALR-TW：台灣法律研究與查證框架 | Taiwan Legal Research and Verification Framework

Open-source verifier for document citations, source evidence, RAG, and agents, with built-in document parsing.

Give your agent the web as real sources, never made-up answers — an MCP server with 15 search and 9 extract providers plus an optional local, key-free DonSeTch integration.

AI feedback triage pipeline with traceable outputs, evaluation, source grounding, and human review.

FastAPI service that checks extracted knowledge graphs on two axes: deterministic SHACL conformance (keyless) and LLM source-grounding (BYOK). Azure Container Apps, OIDC CI/CD, OpenTelemetry.

Turn research papers into source-traceable, validated AI podcast scripts and audio.

Worldwide Council — source-grounded multi-agent deliberation with citation verification and fail-closed controls.

Production-oriented template for building AI agent skills as verifiable software components — offline eval harness, source-grounding validators, structured logs/traces/metrics, replay artifacts, and a CI quality gate. Runs fully offline with a deterministic mock model.

Trusted financial AI, agentic workflows, and senior AI product/platform architecture.

Source-backed developer-tool research agent with Firecrawl, OpenAI, LangGraph, explicit unknowns, and verifiable exports.

A minimal laboratory prototype for legal AI safety boundaries: source grounding, jurisdiction limits, service-boundary refusal, QA metrics, and Active/Shadow update discipline.

A full-stack AI-powered platform for verifying whether generated claims are supported by source documents.

High-precision information extraction framework.

Leadership notes on trusted financial AI, platform strategy, and governed agentic systems.

Chinese financial news to structured events, with independently verified source grounding

Repository Intelligence searches local code and returns verbatim source lines for a question instead of generating prose; relevance is not guaranteed.