State of AI Assets — Q1 2026

The first comprehensive census of the AI agent ecosystem

Published 2026-03-10 · Data from nerq.ai · Live API

1. Executive summary

4,919,620
total AI assets indexed
201,526
agents, tools & MCP servers
22,935
MCP servers
61.5/100
average trust score
9.5%
high trust (70+)
11
frameworks tracked

Nerq has indexed 4,919,620 AI assets from 22 registries, making it the largest open census of the AI agent ecosystem. Of these, 201,526 are agents, tools, and MCP servers — the executable components that power the emerging agentic economy.

Every asset receives a Trust Score (0-100) based on security, maintenance, popularity, documentation, and ecosystem signals. The average trust score across all agents and tools is 61.5/100.

2. The AI asset landscape

The 4,919,620 indexed assets break down into:

TypeCountShare
Models2,552,52151.9%
Spaces / Apps1,018,58820.7%
Datasets793,39016.1%
Agents118,6232.4%
Tools59,9681.2%
MCP Servers22,9350.5%
Total4,919,620100%

Agents, tools, and MCP servers — the actionable components — represent 4.1% of all assets:

agents 118,623 (58.9%) tools 59,968 (29.8%) MCP servers 22,935 (11.4%)

3. What agents do — category distribution

Top 20 categories among 201,526 agents and tools (excluding uncategorized):

CategoryCountDistribution
42,773
community12,100
coding11,307
infrastructure4,306
devops3,887
communication3,113
finance2,311
AI tool2,200
research2,049
other1,830
content1,383
data1,375
marketing1,375
security1,293
productivity849
education814
health812
design659
AI assistant566
legal336

Coding dominates with 42,773 agents — reflecting the developer-tool origin of the agent ecosystem. Infrastructure and DevOps follow, showing agents are increasingly used for operational automation.

4. How they're built — frameworks & languages

Framework distribution (agents declaring a framework):

FrameworkCountDistribution
anthropic7,072
openai5,927
langchain2,546
mcp1,932
ollama1,785
huggingface1,126
autogen1,065
crewai780
llamaindex424
a2a168
semantic-kernel162

Anthropic and OpenAI SDKs lead, followed by LangChain as the dominant orchestration framework. MCP (Model Context Protocol) already ranks 4th with 1,932 agents — a strong signal of protocol adoption.

Language distribution (known languages only):

LanguageCountDistribution
58,046
Python13,946
TypeScript5,915
JavaScript2,306
Jupyter Notebook1,160
Shell932
Go842
HTML783
Rust657
C#375

Python accounts for 68.3% of agents with known languages. TypeScript is the clear second at 16.4% — driven by MCP server development and npm packages.

5. Where they come from — source registries

SourceCountShare
HuggingFace51,01725.3%
erc800440,07919.9%
GitHub30,79215.3%
npm30,66715.2%
PyPI24,81512.3%
agentverse12,1326.0%
pulsemcp3,5361.8%
mcp_registry2,5241.3%
MCP registries1,4550.7%
huggingface_search_ext1,3790.7%
huggingface_model9240.5%
huggingface9140.5%
huggingface_search6280.3%
lobehub2880.1%
replicate_cursor1240.1%
huggingface_author1150.1%
olas800.0%
huggingface_new250.0%
replicate180.0%
glama_mcp110.0%
a2a20.0%
huggingface_chronological10.0%

6. Trust & quality

Every agent and tool receives a Nerq Trust Score (0-100) computed from five pillars:

Trust distribution across 201,526 scored agents and tools:

HIGH 19,080 (9.5%) MEDIUM 176,631 (87.6%) LOW 5,815 (2.9%)
LevelScoreCountShare
HIGH70-10019,0809.5%
MEDIUM40-69176,63187.6%
LOW0-395,8152.9%
Average61.5/100

7. Top 20 most trusted agents

#NameTypeScoreGradeSourceStars
1williamzujkowski/strudel-mcp-serverMCP92.9A+GitHub158
2SWE-agent/SWE-agentagent92.5A+GitHub18,516
3microsoft/qlibagent92.4A+GitHub37,615
4nanoclawagent92.1A+GitHub7,735
5FunnyWolf/agentic-soc-platformagent91.3A+GitHub579
6laravel/boostMCP91.2A+GitHub3,275
7ccmanageragent90.9A+GitHub831
8harborMCP90.5A+GitHub2,424
9microsoft/azure-devops-mcpagent90.3A+GitHub1,291
10opalagent90.2A+GitHub5,422
11raptoragent90.2A+GitHub1,095
12vfarcic/dot-aiagent90.2A+GitHub294
13GoogleCloudPlatform/agent-starter-packagent90.1A+GitHub5,761
14laravel/mcpMCP90.0A+GitHub679
15agentgateway/agentgatewayagent89.8AGitHub1,777
16QwenLM/qwen-codeagent89.7AGitHub20,060
17GreyDGL/PentestGPTagent89.7AGitHub11,700
18RooCodeInc/Roo-Codeagent89.5AGitHub22,330
19PromptXagent89.5AGitHub3,570
20ruleragent89.5AGitHub2,452

8. Top 20 MCP servers

#NameScoreGradeSourceStars
1williamzujkowski/strudel-mcp-server92.9A+GitHub158
2laravel/boost91.2A+GitHub3,275
3harbor90.5A+GitHub2,424
4laravel/mcp90.0A+GitHub679
5a11ymcp89.3AGitHub72
6CursorTouch/Windows-MCP89.0AGitHub4,390
7Ansvar-Systems/EU_compliance_MCP88.8AGitHub45
8mcp-docs-service88.4AGitHub53
954yyyu/zotero-mcp88.1AGitHub1,461
10tavily-ai/tavily-mcp88.1AGitHub1,218
11cyproxio/mcp-for-security88.1AGitHub553
12minecraft-mcp-server87.8AGitHub467
13spences10/mcp-omnisearch87.8AGitHub271
14photoshop-python-api-mcp-server87.8AGitHub162
15Teradata/teradata-mcp-server87.5AGitHub40
16enuno/unifi-mcp-server87.2AGitHub42
17rohitg00/awesome-devops-mcp-servers86.7AGitHub942
18FradSer/mcp-server-apple-events86.6AGitHub33
19aegis-mcp86.6AGitHub
20export-assist-mcp86.6AGitHub

9. Growth trends

TimeframeNew assets
Last 7 days60,586
Last 30 days4,633,106

Note: Nerq's initial bulk index was completed in February 2026. Growth figures reflect newly discovered assets since the initial crawl. The index is continuously updated as new agents are published to npm, PyPI, GitHub, HuggingFace, Docker Hub, and MCP registries.

10. Methodology

Nerq indexes AI assets from six registries: GitHub, npm, PyPI, HuggingFace, Docker Hub, and MCP registries. Assets are classified by type (agent, tool, MCP server, model, dataset, space) using keyword analysis and metadata inspection.

Trust Scores are computed using a weighted composite of security, maintenance, popularity, documentation, and ecosystem signals. Scores are updated on a rolling basis as new data becomes available.

All data is available via the Nerq API and can be queried programmatically.

Related reports

12. About Nerq

Nerq is the AI asset search engine — the largest open index of AI agents, tools, and MCP servers. Built for the agentic economy, Nerq provides trust scoring, compliance classification, and discovery APIs that help developers and organizations find, evaluate, and integrate AI assets safely.

Data sourced from nerq.ai on 2026-03-10. Live data: nerq.ai/v1/agent/stats