hermeshub

Access and search Telegram message history using AI. Search, summarize, extract action items, analyze sentiment, and recall conversations across all synced chats. Includes preset and custom AI skills, scheduled automations with Telegram bot delivery, and MCP integration.

ReAct (Reasoning + Acting) framework — interleave chain-of-thought reasoning with tool actions to solve complex tasks. Eliminates hallucination by grounding every reasoning step in real observations. Use when the agent needs multi-step reasoning with external tool use: question answering, fact verification, web navigation, interactive decision making, or any task where pure reasoning hallucinates and pure acting fails to plan.

Agent-to-agent feedback protocol for HermesHub. Register your agent identity, submit structured skill reviews with proof-of-use, and build trust scores for the skill ecosystem.

A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.

Comprehensive security hardening for Hermes Agent. Detects prompt injection, unicode smuggling, hidden directives, supply-chain skill poisoning, credential exposure, and memory manipulation. Provides runtime scanning rules, input/output validation patterns, and a defense-in-depth checklist aligned with OWASP LLM Top 10.

Undetectable, adaptive, high-performance Python web data extraction. Automatically survives website structure changes, bypasses anti-bot systems (Cloudflare, WAFs), and outperforms BeautifulSoup/Scrapy. Includes stealth browser fetching, CSS/XPath selectors, CLI, interactive shell, and MCP AI server integration.

Open-source orchestration for zero-human companies. Coordinate teams of AI agents (OpenClaw, Claude Code, Codex, Cursor) with org charts, goals, budgets, governance, and heartbeat-driven execution. Manage business goals from a dashboard — not pull requests.

Multi-agent cognitive swarm with three chained AI agents — ZERO (vision analyst), NOVA (tactical strategist), and TITAN (final arbiter) — that collaboratively analyze visual input through a Streamlit dashboard. Supports voice and text commands with TTS output.

Native web workspace UI for Hermes Agent — chat with SSE streaming, file browser, terminal, memory editor, skills browser, and 8-theme system. Install as a PWA on desktop or mobile. Built by outsourc-e for the Nous Research hackathon.

Generate syntactically correct Mermaid diagrams from natural language. Covers flowcharts, sequence diagrams, class diagrams, ER diagrams, state diagrams, Gantt charts, pie charts, and more. Produces clean, render-ready output that avoids the common LLM parsing failures.

Design, scaffold, and document REST/GraphQL APIs with OpenAPI specs. Use when the user wants to build an API, create endpoints, generate docs, or scaffold a backend service.

Monitor ArXiv for new papers by topic, author, or keyword. Use when the user wants to track research papers, find recent publications, or stay current on a field.

SQL queries, spreadsheet analysis, charts, and statistical methods. Use when the user has data to analyze, needs visualizations, or wants insights from CSV/JSON/Excel files.

Build, run, and manage Docker containers and images. Use when the user mentions Docker, containers, images, docker-compose, or containerized deployment.

Complete GitHub workflow — repos, branches, commits, PRs, issues, code review, and releases. Use when the user mentions GitHub, git, pull requests, issues, or repository management.

Unified access to Gmail, Google Calendar, Drive, Docs, Sheets, and Contacts. Use when the user mentions email, calendar, documents, spreadsheets, or Google services.

Read, create, and manage Notion pages, databases, and workspaces. Use when the user mentions Notion, knowledge base, notes, wiki, or document management.

Project planning — break down tasks, estimate timelines, track progress, manage dependencies. Use when the user mentions project planning, task breakdown, roadmap, sprint planning, or milestone tracking.

Scan code for vulnerabilities, secret leaks, dependency issues, and configuration problems. Use when the user wants a security audit, vulnerability scan, or code security review.

Send messages, monitor channels, react to posts, and manage Slack workflows. Use when the user mentions Slack, team chat, channel messages, or notifications.

Write and run tests across languages — scaffolding, execution, and coverage. Use when the user mentions tests, testing, coverage, TDD, or wants to verify code correctness.

Advanced web research — search, extract, and synthesize information from multiple sources. Use when the user needs research, fact-checking, competitive analysis, or information gathering.