Parall vs Skillπ vs ReadGZH vs Hermes Agent
Pricing, plans and key features compared side by side. Updated November 2026.
Pricing model
Contact for pricing
Free
Freemium
Freemium
Free plan
—
✓ Yes
✓ Yes
✓ Yes
Paid plans from
Not published
Completely free
¥9/month
$20/month
Who it's for
Parall enables seamless collaboration between humans and AI teams through a shared data model, eliminating the need for translation layers, glue scripts, or API begging. By integrating AI colleagues directly into existing workflows via channels, tasks, wikis, and inboxes, organizations can adopt AI without migrating their entire systems. This approach allows teams to start with real workflows immediately while maintaining compatibility with their current tools.
Agent skills are scattered across GitHub repositories, so discovery is the real problem, and Skillπ indexes them with the licence and pinned commit attached. Each entry separates what has actually been checked from what has not, including two Notion skills left visibly incomplete. It is a browsing resource rather than a generator, so treat it as reference material next to the tools themselves.
ReadGZH solves a real blocker: mainstream AI tools like ChatGPT, Claude, and Perplexity cannot read WeChat public articles because of anti-scraping protections. It gives researchers, developers, and knowledge workers a reliable, token-efficient way to feed WeChat content into any AI workflow. The permanent cache also builds an open, reusable knowledge base of cleaned articles.
Hermes stands out because it is genuinely self-improving -- the soul.md and context file system means the agent builds up knowledge about your specific workflows over time rather than starting fresh every session. The combination of self-hosting (so your data stays yours), open-source extensibility, and a growing skills ecosystem makes it the most customizable general-purpose agent available. If you are comfortable running software on your own machine, it is the easiest way to get a persistent AI agent that actually knows you.
Key features
- Channel Team communication hub
- Task Work management and tracking
- Wiki Knowledge base and documentation
- Inbox Centralized notifications and messages
- Agent AI team members integration
- Unified Data Model Single data model for humans and AI
- No Translation Layer Direct interaction without middleware
- No Glue Scripts Eliminates need for custom integration code
- Searchable directory browse agent skills by task across Claude Code and Codex
- Skill detail pages original repository, pinned commit and licence for each entry
- Setup requirements the tools, accounts and access a skill needs before installation
- Editor's picks curated by job rather than by download count
- Recorded sample runs 10 isolated samples with visible output and a stated scope
- Honest gaps two Notion skills are left marked unfinished rather than filled with simulated output
- Agent-facing prompt paste one prompt so your agent recommends a skill for the current project
- Free to browse no pricing page or paid plan is published
- WeChat article reader paste a link and get a clean, AI-accessible page in seconds
- API access api.readgzh.site/rd?url= returns full article content for any AI tool
- WebMCP protocol MCP integration for AI agents and automation workflows
- Deep extraction seven-layer parser strips WeChat nested tags, cutting token use 50-87%
- Permanent cache cleaned articles stored globally; re-reads by anyone are free
- AI summary mode Pro feature returns a structured summary without the full text
- Image-message support handles illustrated posts and extracts text and images
- Long-article paging splits very long posts into ~40KB chunks via ?part=N
- Multi-Platform Connectivity -- Connect Hermes to Telegram, Discord, Slack, WhatsApp, Signal, Email, and CLI so the agent meets you wherever you work
- Persistent Memory -- Hermes learns from your projects via soul.md, agents.md, and context files; preferences and solutions carry forward across every session
- Cron Scheduler -- Schedule recurring tasks in plain language -- reports, backups, monitoring jobs -- without writing cron syntax or managing separate automation tools
- Delegated Subagents -- Spawn isolated sub-agents with their own conversation history, execution environment, and tool access for parallel or sensitive workloads
- 300+ Models via Nous Portal -- Access OpenAI, Anthropic, Google, Mistral, and Nous own models through one subscription with bundled web search, browser automation, image gen, and TTS
- Five Execution Backends -- Run tasks locally, inside Docker, over SSH, in Singularity containers, or on Modal cloud; swap backends per task without changing your agent setup
- Skills System -- Package repeatable workflows as named skills (e.g. /review-pr, /deploy-staging) that you or your team can invoke with a single command
- Hermes Desktop -- Native cross-platform app (Mac, Windows, Linux) with a streaming chat interface, file browser, preview rail, config UI, and multi-agent orchestration panel
All plans
Not published
Free
$0
Directory browsing; no paid plan is published
Free
¥0
30 credits/day; full parsing and WebMCP support.
Lite
¥9/month
300 credits/month; usage dashboard; add-on packs.
Pro
¥39/month
2,000 credits/month; AI summary and priority queue.
Free (Self-Hosted)
$0
Full Hermes Agent with your own API keys; MIT-licensed, no usage limits imposed by Nous, unlimited installs
Plus
$20/month
$22 in Nous Portal credits per month; access to 300+ models, web search, browser automation, image generation, and TTS bundled
Super
$100/month
$110 in Nous Portal credits per month; same bundle as Plus at higher volume; suited for daily heavy use
Ultra
$200/month
$220 in Nous Portal credits per month; highest volume tier for power users and teams running continuous agent workloads
Profile views
322
on OnePlaceForAI
60
on OnePlaceForAI
393
on OnePlaceForAI
263
on OnePlaceForAI
Other popular comparisons
New AI tools, every Monday
Free weekly digest — tool picks, prompts, and AI news.