AI Agent Skills Ecosystem shows rapid 10x growth in five months
This page is designed to answer the simple question first: where is the real momentum? The short answer is that developer adoption is accelerating across agent skills, protocols are becoming shared infrastructure, and security has become the deciding constraint for trust and scale.
The market is maturing in public
OpenClaw created the early distribution wave, Hermes proved that learning loops can be more controlled, and Claude Code is showing how enterprise workflows absorb these patterns. Read the top line first, then use the lower sections as evidence.
Daily Skill Submission Velocity
10x GrowthGrowth accelerated before the OpenClaw acquisition and ClawHavoc incident, indicating genuine developer adoption rather than media-driven spikes.
OpenClaw
Gateway-first, TypeScript/Node.js, unbounded memory, marketplace model with 44K+ skills.
Hermes Agent
Learning-first, Python-native, 5-stage loop, bounded memory (~1,300 tokens), auto-generated skills.
Claude Code
Enterprise tier, 4% of GitHub commits, projected 20% by end 2026, compliance-focused.
Framework Comparison
This section compares the main players in plain terms. OpenClaw is strongest in distribution, Hermes is strongest in structured learning, and Claude Code is strongest where enterprise controls matter most.
GitHub Star Trajectory
OpenClaw surpassed React's 10-year milestone in 5 months
Performance & Security
Nous Research benchmarks, April 2026
Detailed Framework Matrix
| Dimension | OpenClaw | Hermes | Claude Code |
|---|---|---|---|
| Center of Gravity | Gateway (communications) | Agent loop (learning) | Editor integration |
| Skill Philosophy | Human-authored, marketplace (44K+) | Auto-generated from experience (118 bundled) | Skills + shell commands |
| Memory Model | Unbounded Markdown files (LanceDB) | Bounded, curated (~1,300 tokens) | Session-based |
| Latency | <1.2s median | ~30% slower routing | Variable |
| Tokens/Turn | ~1,800 | ~8,000+ (with trajectory) | Variable |
| Security (Apr 2026) | 9+ CVEs, 135K+ exposed | Zero agent-specific CVEs | Enterprise-managed |
| Repeat Task Speed | Baseline | 40% faster | N/A |
| Language | TypeScript/Node.js | Python | Proprietary |
Ecosystem Scale & Growth
These numbers show whether the category is becoming real infrastructure or just a burst of attention. The pattern here points to durable adoption: users, instances, downloads, and revenue are all moving together.
Key Growth Metrics Table
| Metric | Value | Period | Context |
|---|---|---|---|
| OpenClaw Stars | 345,000+ | Nov 2025 – Mar 2026 | Passed React's 10-year trajectory |
| ClawHub Skills | 44,000+ | Feb – Apr 2026 | 7.7x increase in ~8 weeks |
| Daily Submissions | 50 → 500+/day | Mid-Jan – Early Feb | 10x acceleration |
| skills.sh (top skill) | 20,000 in 6 hours | Jan 20, 2026 | Launch day velocity |
| MCP Downloads | 97 million/mo | Mar 2026 | 970x in 16 months |
| Hermes Stars | 64,000+ | Feb – Apr 2026 | 30% migration from OpenClaw |
Skills Taxonomy
This chapter explains what people are actually building. The most active skill groups are practical rather than decorative: automation, research, development, and task execution dominate the mix.
ClawHub Skills by Official Category
Community-Curated Functional Groups
Top categories are overwhelmingly action-oriented, not chat-oriented.
Top 15 Skills by Downloads
| # | Skill | Category | Downloads | Function |
|---|---|---|---|---|
| 1 | Capability Evolver | AI/ML | 35,000+ | AI self-evolution engine |
| 2 | GOG (Google Workspace) | Productivity | 33,800+ | Gmail, Calendar, Drive, Docs |
| 3 | Self-Improving Agent | AI/ML | 32,000+ | Cross-session learning |
| 4 | Ontology | AI/ML | 27,600+ | Typed knowledge graph |
| 5 | Summarize | Productivity | 26,100+ | URLs, PDFs, audio, video |
| 6 | GitHub Integration | Development | 24,800+ | Full GitHub workflow |
| 7 | Felo Search | Research | 145,000+ | AI-synthesized search |
| 8 | Notion | Productivity | 13,900+ | Read/write pages & DBs |
| 9 | Nano Banana Pro | Creative | 13,400+ | Image generation (Gemini) |
| 10 | API Gateway | Development | 13,000+ | Managed OAuth to 100+ APIs |
| 11 | Obsidian | Productivity | 12,400+ | Local vault integration |
| 12 | Agent Browser | Web | 11,800+ | Rust headless browser |
| 13 | OpenAI Whisper | Media | 11,500+ | Local speech-to-text |
| 14 | McPorter | Development | 11,100+ | MCP server management |
| 15 | Tavily Search | Web/AI | 9,000+ | AI-optimized web search |
Coding & Development
GitHub (24.8K), DevOps (393 skills), Browser automation, "Night shift" patterns
Content Creation & Media
164 image/video skills, audio/music, presentations (54 design systems)
Business Automation
GOG (#2 downloaded, 33.8K), SEO Research (highest ROI), CRM
AI/ML & Research
MLOps (17 bundled in Hermes), arXiv, Search (250+ skills), Red teaming
Security Landscape: The ClawHavoc Crisis
This is the cost of speed without enough trust controls. The security story matters because it changes how marketplaces, enterprise deployment, and protocol governance need to be designed going forward.
CVE Severity Distribution
ClawHavoc Attack Timeline
Snyk ToxicSkills Audit Results
| Metric | Count | Rate | Assessment |
|---|---|---|---|
| Total scanned | 3,984 | — | Largest public corpus |
| Any security flaw | 1,467 | 36.82% | >1 in 3 skills affected |
| Critical issues | 534 | 13.4% | >1 in 8 critically vulnerable |
| Confirmed malicious | 76 | 1.9% | Human-verified payloads |
| Plaintext credentials | 283 | 7.1% | API keys in LLM context/logs |
| Prompt injection + malware | 91% | of malicious | Dual-vector evasion |
OWASP Agentic Skills Top 10 (AST10)
Infrastructure & Protocols
Here we look at the pipes underneath the ecosystem. What we need to have is a shared way for tools, agents, and companies to connect safely (protocol layer), and this is where MCP, A2A, and ACP begin to matter.
Protocol Comparison Matrix
| Feature | MCP | A2A | ACP (IBM) | ACP (Cisco) | ACP (Zed) |
|---|---|---|---|---|---|
| Primary Focus | Agent-to-Tool | Agent-to-Agent | Agent-to-Agent | Agent-to-Agent | Editor-to-Agent |
| Transport | JSON-RPC 2.0, HTTP, SSE | HTTP(S), JSON-RPC 2.0, SSE | HTTP RESTful API | RESTful APIs | JSON-RPC 2.0 over stdio |
| Discovery | Application-integrated | Agent Cards (.well-known) | Embedded metadata | Agent Directory + OASF | Editor plugin registry |
| Governance | Linux Foundation (AAIF) | Linux Foundation | IBM / Open | Cisco AGNTCY | Zed + JetBrains |
| Created | Nov 2024 (Anthropic) | Apr 2025 (Google) | May 2025 (IBM) | 2024 (Cisco) | 2025 (Zed) |
| Key Metric | 97-110M/mo downloads | 150+ partners | BeeAI integration | AGNTCY coalition | v0.11.0, 2.3K stars |
Distribution Channels
Knowledge Management Integrations
Distribution Channel Trust Matrix
| Channel | Mechanism | Trust Model | Security Features | Key Limitation |
|---|---|---|---|---|
| ClawHub | Centralized registry | Community + auto scan | VirusTotal + Gemini Code Insight | No pre-publication review; no signing |
| skills.sh | Decentralized GitHub repos | GitHub identity + telemetry | SHA-256 via well-known endpoint | No security scanning of content |
| GitHub CLI | Git-native distribution | GitHub auth + immutable releases | Content-addressed, version pinning | No cryptographic signing |
| Private/Enterprise | Custom repos + workspace dirs | Organization-controlled | Determined by org policy | No standardized RBAC |
Growth Patterns & Traction
Growth is not uniform. Some segments are expanding because they solve immediate work problems, while others are growing because security and governance suddenly became urgent after public failures.
Top Skill Categories by Count
Framework Growth Trajectory
Security Skills
Post-ClawHavoc boom in scanning, auditing, and vulnerability detection tools. Fastest-growing segment.
AI/LLM Orchestration
280+ skills — model routing, prompt engineering, autonomous agents. Largest category on ClawHub.
DevOps & Cloud
210+ skills reflecting the "operator not chatbot" pattern. Direct embodiment of autonomous ops.
GEO
Generative Engine Optimization — $7.3B market by 2031. Optimizing for AI search citations.
Developer Migration
30% active developer migration from OpenClaw to Hermes seeking "maintenance fatigue" relief.
Night Shift Economy
Claude Code: 4% of GitHub commits, projected 20%. Jules: 140K+ autonomous code improvements.
Enterprise Adoption Signals
| Signal | Metric | Confidence |
|---|---|---|
| Gartner: enterprise apps agentic by end 2026 | 40%, up from <5% in 2025 | High |
| OpenClaw running instances | 500K+ across 82 countries | High |
| OpenClaw monthly active users | 3.2 million | High |
| OpenClaw monthly website visitors | 38 million (925% MoM growth) | High |
| MCP monthly SDK downloads | 97 million (970x in 16mo) | High |
| Claude Code: % of GitHub commits | 4% → 20% projected by end 2026 | High |
| Agentic AI project failure risk (Gartner) | 40% abandoned by 2027 without governance | High |
Emerging Sectors & Future Outlook
This is the frontier view. We need to have reliable coordination between software agents, payment rails, local devices, and governance systems (agent networks, machine payments, edge inference, compliance tooling) for the next phase to work.
Emerging Sectors Overview
| Sector | Key Metric (2026) | Maturity | Key Players | Strategic Implication |
|---|---|---|---|---|
| Agent social networks | 1.5M API tokens exposed; $93M market cap crash | Nascent / high risk | Moltbook, Permiso, Wiz | Agent-to-agent communication requires security-first architecture |
| Agent-to-human labor markets | 518K+ workers; 32.7% programmatic origin | Early / scaling | RentAHuman.ai | Physical-world attack surface extends beyond digital boundaries |
| Agent-native payments | 165M+ transactions; 480K+ transacting agents | Growth | x402 Foundation, Coinbase, Stripe | Machine-to-machine payments becoming infrastructure |
| Local/edge deployment | Apple Silicon <200ms; RPi 300–500ms | Emerging | Apple, NVIDIA, Qualcomm | Sovereign deployment now technically viable |
| Agent security tooling | 36.82% flaw rate; 1,184 malicious skills | Rapid growth | OWASP, Snyk, Cisco | Security tooling is the fastest-growing sub-sector |
| Guardian/governance agents | 10–15% projected market share by 2030 | Nascent | Accelirate, Gartner | Compliance automation as a service |
| Protocol consolidation | MCP 97M downloads; A2A 150+ orgs | Standardizing | Anthropic, Google, IBM, Linux Foundation | Interoperability becoming table stakes |
The Agent-to-Agent Economy
Sovereign & Local AI Deployment
Agent inference no longer requires data center GPUs. A $100 Raspberry Pi can run capable agents.
Security-Learning Paradox
The most efficient distribution model (centralized marketplace) is also the most vulnerable. The most secure model (autonomous generation) sacrifices network effects.
Markdown's Unpatchable Attack Surface
Natural language instructions evade both code scanners and AI safety filters. 91% of malicious skills combined prompt injection with traditional malware.
Protocol Stack Consolidation
MCP (vertical) + A2A (horizontal) + ACP (enterprise governance) = the new TCP/IP for agents. Interoperability commoditizes framework differences.
Knowledge Management = Real Moat
Obsidian vaults, Notion control planes, and Google Workspace histories create higher switching costs than the frameworks themselves.
Strategic Playbook
This final section turns the research into action. Instead of treating every framework as a winner, it separates where each one is strongest and what decisions different audiences should make next.
For Developers
- OpenClaw for breadth/connectivity, Hermes for depth/learning, Claude Code for enterprise
- Treat skills as untrusted code — sandbox, scan with mcp-scan, review SKILL.md source
- Target underserved verticals: health, education, manufacturing
For Enterprises
- Governance first: RBAC, audit trails, least privilege before wide deployment
- Hermes' bounded memory for compliance-sensitive environments (finance, healthcare, gov)
- Vendor risk assessments on all AI agent vendors — including open-source
For Investors
- Security infrastructure is the highest-conviction sector post-ClawHavoc
- Protocol layers beat application layers: MCP's 97M downloads vs any single framework
- The "night shift economy": time arbitrage through autonomous agents as a new value category
Paid Service & Tooling Opportunities
Semantic skill scanners that understand instruction intent. The gap is structurally larger than npm's 2015 gap. Estimated 10-15% of total agent infrastructure spending by 2030.
Scheduling, monitoring, and QA for autonomous overnight work. Solopreneurs report 70-90% time savings. Infrastructure rents comparable to cloud computing's capex-to-opex shift.
HIPAA-compliant medical skills, educational assessment generators, manufacturing QC inspectors. Less competition, established procurement budgets.
"Guardian Agents" projected 10-15% market share by 2030. EU AI Act logging, GDPR compliance, audit trail automation. Gartner: 30% higher trust, 25% better compliance.
The real moat. Higher switching costs than frameworks. Build specialized connectors for Obsidian, Notion, Confluence with three-layer RAG architectures.
x402-style micropayment infrastructure. 165M+ transactions prove demand. Build escrow, dispute resolution, and KYT/OFAC compliance layers.