Breaknorm
Sign inStart free

Product

SignalsPeopleCompaniesLocal businessesMCP and API

Plays

Post engagersTeam build-outChampion movedHiring surgeNewly fundedLookalikesAll plays

Data

Coverage by countryHiring dataJob changesEmail verificationCompanies by toolWho is hiringMarket mapsOutboundCompany profilesCompare
PricingDatasetsDocsSign in
Tools · Category

llm app frameworks, ranked by real usage

As of 4 November 2026, LangChain leads llm app frameworks with 3,507 companies naming it in job postings, ahead of LangGraph at 2,401.

As of 4 November 2026 · refreshed daily · counts move as websites, DNS and career sites are re-read.

Leader
LangChain · 3,507
Runner-up
LangGraph · 2,401
Most hiring, 90 days
LangChain
Highest postings per company
Deep Agents
Catalogue
T-1.0.1-prov
12,235companies across the category
29%of them on LangChain
37,756postings naming a llm app framework in 90 days
29tools with enough evidence to rank
02Ranking

Every llm app framework we can measure

Companies naming the tool, and postings naming it in the last 90 days. Bars are relative to the leader.

#ToolCompaniescompaniesPostings, 90 dayspostingsper company
1
LangChainLangChain
3,507
11,5103.3
2
LangGraphLangChain
2,401
8,0283.3
3
LlamaIndexLlamaIndex
1,376
3,8442.8
4
CrewAICrewAI
993
2,9823.0
5
AutoGenMicrosoft
857
2,4182.8
6
Semantic KernelMicrosoft
622
2,5374.1
7
Google Agent Development KitGoogle
353
1,4334.1
8
RagasRagas
218
4792.2
9
OpenAI Agents SDKOpenAI
187
4812.6
10
PydanticAIPydantic
171
3181.9
11
Claude Agent SDKAnthropic
168
3362.0
12
GraphRAGMicrosoft
157
4983.2
13
DeepEvalConfident AI
156
2981.9
14
Strands AgentsAmazon Web Services
148
3552.4
15
Vercel AI SDKVercel
148
2651.8
16
Microsoft Agent FrameworkMicrosoft
128
4653.6
17
Haystackdeepset
120
4043.4
18
DSPyStanford NLP
94
1731.8
19
MastraMastra
61
851.4
20
Spring AIVMware
54
1192.2
21
AutoGPTSignificant Gravitas
50
591.2
22
DifyLangGenius
47
821.7
23
FastMCPPrefect
43
821.9
24
PipecatDaily
32
621.9
25
Deep AgentsLangChain
31
1484.8
26
LangChain4jLangChain4j
31
632.0
27
Prompt FlowMicrosoft
30
1183.9
28
AgnoAgno
27
602.2
29
Anthropic SDKAnthropic
25
542.2
03Head to head

Compare two tools

Same data, two columns: who chooses which by size, industry and country.

LangChain vs LangGraph3,507 · 2,401LangChain vs LlamaIndex3,507 · 1,376LangChain vs CrewAI3,507 · 993LangChain vs AutoGen3,507 · 857LangChain vs Semantic Kernel3,507 · 622LangGraph vs LlamaIndex2,401 · 1,376LangGraph vs CrewAI2,401 · 993LangGraph vs AutoGen2,401 · 857LangGraph vs Semantic Kernel2,401 · 622LlamaIndex vs CrewAI1,376 · 993LlamaIndex vs AutoGen1,376 · 857LlamaIndex vs Semantic Kernel1,376 · 622CrewAI vs AutoGen993 · 857CrewAI vs Semantic Kernel993 · 622AutoGen vs Semantic Kernel857 · 622
Cite this

Quote the sentence with the date and the link. The numbers change daily; the link always shows the current ones.

LangChain leads llm app frameworks with 3,507 companies naming it in job postings, ahead of LangGraph at 2,401. (Breaknorm, 4 November 2026, https://breaknorm.co/tools/category/llm-app-frameworks)
How we know

Read from the source, not self-reported

Every number on this page can be traced to a page we crawled or a posting we read. Full methodology →

  • CatalogueBreaknorm technology catalogue T-1.0.1-prov: 6,296 tools with vendor and category, editions folded into their parent.
  • CompaniesCompanies whose own postings name the tool as the team's system, any confidence. Candidate wish-lists excluded.
  • 90-day postingsOpen postings first seen or posted in the last 90 days that name the tool.
  • Not countedTools used by teams that do not post jobs, and companies without a career site we can read.
FAQ

llm app frameworks: questions

How is this ranking made?

By the number of companies whose own job postings name the tool as the team's system, from the Breaknorm technology catalogue (version T-1.0.1-prov). No vendor paid for a position and no editor chose the order.

Why is this different from review-site rankings?

Review sites rank by reviews collected. This ranks by companies hiring people to work in the tool, which is closer to seats in use. It under-counts tools used by teams that rarely post jobs.

What about product editions?

Editions and sub-products () are counted under the parent so no company is counted twice.

Can I get the companies behind a number?

Yes: click a tool, see the first 20, and sign up for the full list with verified e-mails. Counting is free.

Companies and people

Get the companies your way

The same data as a search, over MCP and the API, as bulk files, or pushed to you as it changes.

SearchCompany searchFilter on what a company actually does→SearchPeople searchDecision makers, normalized and verified→MCP and APICompanies over MCP and APICount, search and export from your agent→DatasetCompany and People datasetThe whole market in your warehouse→DataCoverage by countryCheck your market before you start→SearchLocal businessesThe same database, by category and city→

Every company on every tool,
ranked by what they say

Connect the MCP server, ask which companies run a tool. Start free, no card.

Start free
  1. 01Sign up, no card
  2. 02Connect Claude, ChatGPT or an API key
  3. 03Ask for your market