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.
Agentic Legal RAG / MCP Harness for Taiwan Law.
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.
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.
Worldview Council — source-grounded multi-agent deliberation with citation verification and fail-closed controls.
A minimal laboratory prototype for legal AI safety boundaries: source grounding, jurisdiction limits, service-boundary refusal, QA metrics, and Active/Shadow update discipline.
Chinese financial news to structured events, with independently verified source grounding
High-precision information extraction framework.
Source-backed developer-tool research agent with Firecrawl, OpenAI, LangGraph, explicit unknowns, and verifiable exports.
A full-stack AI-powered platform for verifying whether generated claims are supported by source documents.
A standalone MCP suppressor that enforces grounding by validating references, rejecting unsupported claims, and stabilising model outputs.
Full-stack AI financial research assistant with FastAPI, React, local RAG, source citations, portfolio risk summaries, and a deterministic RAG evaluation harness.
Evidence-aware editorial AI workflow that turns topics into source-grounded draft packages using query contracts, source scoring, candidate validation, claim checks, and copy-readiness gates.
Python tool for extracting validated, schema-defined JSON from documents (PDF, HTML, Markdown, plaintext) using LLMs, with source grounding and a built-in eval harness. Works with Anthropic Claude or OpenAI.
Synthetic SMB operations eval for source-grounded, privacy-safe, human-approved business agents.
Eval-first RAG that checks claims against arXiv papers; cites the spans it uses, abstains when the corpus is silent, and measures every component against a frozen, passage-anchored gold set.
To associate your repository with the source-grounding topic, visit your repo's landing page and select "manage topics."