.num-cell{font-family:ui-monospace,'SF Mono',monospace;text-align:right}

AI agent frameworks compared — 2026

Data-driven comparison of 11 major AI agent frameworks from the Nerq index of 5M+ assets. Published 2026-09-13.

11
frameworks compared
24,427
total agents using these
Anthropic
most adopted

comparison table

frameworkagentsavg trusttop agentlanguagenew (30d)
Anthropic 7,490 59.9 IBM/mcp-context-forge (86.4) Python 0
OpenAI 6,329 58.2 IBM/mcp-context-forge (86.4) Python 0
LangChain 2,680 57.2 vstorm-co/full-stack-fastapi-n (82.2) Python 0
MCP 2,046 61.0 IBM/mcp-context-forge (86.4) Python 0
Ollama 1,900 58.5 promptfoo/promptfoo (86.0) Python 0
HuggingFace 1,238 58.7 deepset-ai/haystack (82.5) Python 0
AutoGen 1,113 58.1 ComposioHQ/composio (80.9) Python 0
CrewAI 809 56.8 vstorm-co/full-stack-fastapi-n (82.2) Python 0
LlamaIndex 465 56.8 ComposioHQ/composio (80.9) Python 0
A2A 191 59.1 pydantic/pydantic-ai (80.0) Python 0
Semantic Kernel 166 55.7 NVIDIA/NeMo-Agent-Toolkit (77.3) Python 0

adoption — agent count

Number of agents in the Nerq index using each framework

Anthropic
7,490
OpenAI
6,329
LangChain
2,680
MCP
2,046
Ollama
1,900
HuggingFace
1,238
AutoGen
1,113
CrewAI
809
LlamaIndex
465
A2A
191
Semantic Kernel
166

average trust score

Mean trust score of agents using each framework (0-100)

MCP
61
Anthropic
60
A2A
59
HuggingFace
59
Ollama
58
OpenAI
58
AutoGen
58
LangChain
57
CrewAI
57
LlamaIndex
57
Semantic Kernel
56

methodology

Framework association is determined from the frameworks array in the Nerq agent database. An agent is counted under a framework if that framework appears in its declared dependencies, metadata, or detected integrations. Trust scores are the Nerq Trust Score v2 — a composite of security practices, compliance, maintenance activity, community trust, and ecosystem compatibility. Data updates hourly from the live index.

related

State of AI Assets Q1 2026 · Best Coding Agents · Benchmark API · Weekly Signal

Data from the Nerq index. JSON: /v1/agent/stats · API docs · all reports

We use cookies for analytics and caching. Privacy Policy