On this page

Every list of AI agent frameworks I read quotes a star count, and almost none say when it was taken. A number from last spring sits next to one from last week, and a repo that stopped shipping in April still looks like a contender.

So I built the version I wanted to cite. A script reads 43 open-source agent frameworks from the GitHub, npm and PyPI APIs every day and rebuilds the table below. Every figure carries its date, the scoring is written out in full, and the data is free to copy.

This page is the dataset. If you want my opinion on which framework to pick for a project, that lives in the best open-source AI agent frameworks, which compares the six I would shortlist and explains why.

Headline numbers
  1. Dify ranks first of 43 open-source agent frameworks on the composite score (95.5 of 100) as of 17 November 2026, ahead of n8n (93.0) and AutoGPT (81.5). Among code-first frameworks, LangChain leads at 80.8, then Mastra at 80.8.
  2. n8n gained the most GitHub stars: 2,845 in the last 30 days, followed by AgentScope (2,642) and Dify (2,555). Relative to size, AgentScope grew fastest among repos above 5,000 stars, at 7.9% in 30 days.
  3. Mastra was the most active repo, with 2,075 commits to its default branch in 30 days; n8n (1,622) and Pipecat (1,504) follow.
  4. 32 of the 43 frameworks shipped a release in the 30 days to 17 November 2026, while 6 are archived or had no commit in 90 days (MetaGPT, Flowise, Coze Studio, SuperAGI, Upsonic, Inngest AgentKit).
  5. The 43 tracked repos hold 1,782,192 GitHub stars between them; the visual builders (Dify, n8n, AutoGPT, Langflow, Activepieces, Flowise, Coze Studio) account for 46% of them.

Updated . Refreshed daily from the GitHub, npm and PyPI APIs.

Cite this page: "Open-source AI agent framework leaderboard", Gravity, updated , https://gravity.fast/data/ai-agent-framework-leaderboard/. Data licensed CC BY 4.0: reuse it anywhere, commercially too, with credit and a link. Download the full table as data.csv.

The leaderboard

Ranked by the composite score described in the methodology. The Type column separates code-first libraries from visual builders and voice-agent frameworks, so sort by eye within a type if that is the comparison you need. Repo names link to GitHub.

#FrameworkTypeStarsStars gained, 30 daysCommits, 30 daysActive contributors, 90 daysLatest releaseOpen issuesWeekly downloadsScore
1DifyVisual builder, Python161,329+2,5551,0342754 November 20263%No package95.5
2n8nVisual builder, TypeScript210,703+2,8451,62219316 November 20263%103.2k npm93.0
3AutoGPTVisual builder, Python188,072+4398394915 November 20267%No package81.5
4LangChainCode framework, Python149,750+1,7252264215 November 20266%36.6M PyPI80.8
5MastraCode framework, TypeScript29,557+6722,07510013 November 20266%3.4M npm80.8
6Vercel AI SDKCode framework, TypeScript28,025+64260212513 November 202610%45.8M npm78.8
7CrewAICode framework, Python61,014+1,1872279012 November 202617%617.0k PyPI78.4
8AgentScopeCode framework, Python36,132+2,64222815916 November 202625%170.8k PyPI78.1
9PipecatVoice agents, Python17,301+7291,50413612 November 20269%391.0k PyPI73.1
10LangGraphCode framework, Python45,056+1,6141292514 November 202620%14.7M PyPI72.7
11Pydantic AICode framework, Python21,253+5611,38512017 November 202626%1.5M PyPI72.7
12LangflowVisual builder, Python156,722+9271644710 November 20266%13.4k PyPI72.2
13AgnoCode framework, Python43,216+43117712912 November 202628%592.2k PyPI70.9
14Google ADKCode framework, Python22,247+34543526412 November 20267%2.7M PyPI69.9
15OpenAI Agents SDK (Python)Code framework, Python30,729+614886316 November 20261%4.7M PyPI68.3
16ActivepiecesVisual builder, TypeScript25,579+482552308 November 202615%No package66.5
17LiveKit AgentsVoice agents, Python15,258+46626820813 November 202611%1.3M PyPI66.3
18Microsoft Agent FrameworkCode framework, Python14,719+52436417413 November 202617%43.1k PyPI65.1
19HaystackCode framework, Python27,024+26127917210 November 20262%176.8k PyPI64.7
20DSPyCode framework, Python39,103+423924810 November 202620%1.5M PyPI64.2
21Strands AgentsCode framework, TypeScript9,233+37535912513 November 202635%8.9M PyPI62.1
22LlamaIndexCode framework, Python52,925+37993413 November 20266%414.6k PyPI58.2
23Semantic KernelCode framework, C#28,784+11191567 November 20262%83.9k PyPI53.7
24smolagentsCode framework, Python30,400+4909429 May 202644%202.2k PyPI44.0
25AutoGenCode framework, Python61,881+4202130 September 202519%107.2k PyPI43.0
26SwarmsCode framework, Python7,384+1093052116 November 2026 (PyPI)19%4,370 PyPI42.3
27LangGraph.jsCode framework, TypeScript3,418+581672717 November 202617%5.0M npm41.2
28AG2Code framework, Python5,073+721404615 November 20263%56.0k PyPI40.7
29VoltAgentCode framework, TypeScript10,988+16411124 November 202620%42.0k npm38.4
30OpenAI Agents SDK (JS)Code framework, TypeScript4,025+99511716 November 20265%2.4M npm37.1
31MetaGPTCode framework, Python71,318+414009 March 20251%1,090 PyPI34.8
32BeeAI FrameworkCode framework, Python3,462+25113672 November 20262%7,048 PyPI34.3
33CAMELCode framework, Python18,041+1235133 September 202619%15.1k PyPI33.8
34LettaCode framework, n/a25,467+2882212 October 2026 (PyPI)0%2,834 PyPI33.4
35Atomic AgentsCode framework, Python6,337+47612414 November 20262%5,359 PyPI32.7
36LangroidCode framework, Python4,152+34322214 November 202615%9,251 PyPI29.0
37Flowise archivedVisual builder, TypeScript55,574+620029 July 202626%3,536 npm28.2
38Agency SwarmCode framework, Python4,638+349730 October 20261%1,273 PyPI24.2
39Coze StudioVisual builder, TypeScript21,815+93005 February 202647%No package21.0
40SuperAGICode framework, Python17,748+400016 January 202441%No package16.3
41Agent SquadCode framework, Python7,806+150223 September 202621%1,670 PyPI15.7
42UpsonicCode framework, Python7,971+140019 May 202610%1,796 PyPI9.1
43Inngest AgentKitCode framework, TypeScript963+150013 November 202552%27.5k npm6.3

Data as of 17 November 2026. Stars, commits and active contributors (distinct commit authors on the default branch in 90 days, bots excluded) and releases from the GitHub API; weekly downloads are the last 7 days on npm (api.npmjs.org) or PyPI (ClickPy's copy of the PyPI download logs, with pypistats.org as fallback) for the package named in each project's install docs. "Open issues" is open issues as a share of all issues ever filed, pull requests excluded. * Stars gained is scaled to 30 days from a Wayback Machine capture of the repo page between 20 and 75 days old; it switches to this tracker's own daily snapshots once they are 30 days deep. Score: see methodology.

Who is gaining stars

Total stars reward age. A framework launched in 2023 has had three years to collect them, so the more useful question for anyone choosing today is who is gaining attention now. The chart ranks the repos by stars gained in the last 30 days.

GitHub stars gained in the last 30 days, top 12 open-source agent frameworks n8n 2,845; AgentScope 2,642; Dify 2,555; LangChain 1,725; LangGraph 1,614; CrewAI 1,187; Langflow 927; Pipecat 729; Mastra 672; Vercel AI SDK 642; OpenAI Agents SDK (Python) 614; Pydantic AI 561. Data as of 17 November 2026. STARS GAINED IN 30 DAYS, AS OF 17 NOVEMBER 2026 n8n 2,845 AgentScope 2,642 Dify 2,555 LangChain 1,725 LangGraph 1,614 CrewAI 1,187 Langflow 927 Pipecat 729 Mastra 672 Vercel AI SDK 642 OpenAI Agents SDK (Python) 614 Pydantic AI 561
Stars gained in the 30 days to 17 November 2026, from the GitHub API. Values marked ~ are scaled from a Wayback Machine capture of the repo page, as the table note explains.

Absolute gains favour big repos, so the headline numbers also name the fastest grower relative to its size among repos above 5,000 stars. Both are in the CSV if you want to run your own cut.

How to read the ranking

Stars are attention, not usage. A star costs one click and is never taken back by most people. It tells you how many developers noticed a project, which is why the visual builders, with their broad non-developer audiences, hold most of the stars in this table.

Downloads are installs, inflated by machines. Weekly npm and PyPI counts include CI pipelines, container builds and other libraries that depend on a package. LangChain and the Vercel AI SDK post tens of millions a week partly because so much other software pulls them in. Compare downloads within a registry, and treat them as a measure of how embedded a package is.

Commits and active contributors are the pulse. A repo with 60,000 stars and no commits in 90 days is a monument. The table shows that directly: as of 4 October 2026, AutoGen's default branch had no commits in the previous 90 days while Microsoft Agent Framework had hundreds, and Flowise's maintainers had archived the repo on GitHub. If you run Flowise today, these are the alternatives I compared.

The score is one opinion made explicit. I weighted momentum (growth, commits, contributors) at 55% and accumulated popularity (stars, downloads) at 35%, because a framework you adopt today needs to be maintained next year. If you weight things differently, the CSV has every input.

A note on where I sit. I run Gravity, which is on the other side of this choice: people describe a task and an agent runs it, so nobody using it picks a framework. That gives me no favourite in this table, and it is why the comparisons I write, like Gravity vs LangGraph and Gravity vs CrewAI, are about build-it-yourself versus hand-it-off rather than one framework versus another.

Change log

Each line is generated from the daily data: releases published in the last week, rank moves of three places or more, star milestones, and repos archived by their maintainers.

  1. : Pydantic AI published release v2.69.0.
  2. : LangGraph.js published release @langchain/angular@0.4.10.
  3. : Langflow moved from rank 9 to 12.
  4. : smolagents moved from rank 28 to 24.
  5. : n8n published release n8n@1.123.97.
  6. : AgentScope published release v2.0.12.
  7. : AutoGPT published release autogpt-platform-beta-v0.11.3.
  8. : LangChain published release langchain-mistralai==1.2.0.
  9. : AG2 published release v1.3.2.
  10. : LangGraph published release 1.2.22.
  11. : Atomic Agents published release v2.16.0.
  12. : Langroid published release 0.69.23.
  13. : Mastra published release @mastra/core@1.83.0.
  14. : Vercel AI SDK published release @ai-sdk/vue@3.0.332.
  15. : LiveKit Agents published release livekit-agents@1.8.12.
  16. : Microsoft Agent Framework published release python-1.26.0.
  17. : Strands Agents published release python/v1.65.0.
  18. : LlamaIndex published release v0.14.26.
  19. : Letta moved from rank 29 to 32.
  20. : CrewAI published release 1.15.41.
  21. : Pipecat published release v1.16.0.
  22. : Agno published release v3.2.0.
  23. : Google ADK published release v2.14.1.
  24. : OpenAI Agents SDK (JS) published release @openai/agents-extensions@0.22.0.
  25. : AutoGPT moved from rank 8 to 5.

Methodology

What gets included

A project is in the table when it is open source on GitHub, its main purpose is building LLM agents (tool calling, multi-step plans, multi-agent coordination, or a visual canvas for the same), and it has meaningful public use. I confirmed every repo through the GitHub API on 4 October 2026 and recorded renames, such as Strands Agents moving to strands-agents/harness-sdk and Atomic Agents to Eigenwise/atomic-agents.

Left out on purpose: coding agents that are products rather than frameworks (OpenHands, Goose), memory and retrieval layers used inside agents, model SDKs with no agent loop, and ports that were archived and folded into another repo. Where a project ships separate Python and JavaScript repos with their own communities, as LangGraph and the OpenAI Agents SDK do, each repo gets its own row.

The seven measures

  • Stars: the repo's stargazer count from the GitHub GraphQL API, read daily.
  • Stars gained, 30 days: today's count minus the count 30 days earlier from this tracker's own snapshots. Until those exist, the baseline is the nearest Wayback Machine capture of the repo page taken 20 to 75 days earlier, scaled to 30 days and marked with an asterisk. Repos with no usable capture show n/a. GitHub no longer serves the list of who starred a repo and when, so star history cannot be rebuilt from the API.
  • Commits, 30 days: commits reachable from the default branch with a commit date in the last 30 days. Squash-merge projects show fewer commits for the same amount of work, so read this alongside contributors.
  • Active contributors, 90 days: distinct commit authors on the default branch in the last 90 days, counted by GitHub login or commit email, with bots such as Dependabot and Renovate removed. I use this rather than GitHub's all-time contributor list because that list stops linking accounts after about 500 authors and cannot rank large repos.
  • Latest release: the newest GitHub release that is not a draft or pre-release, or the newest upload of the project's PyPI package when that is more recent (marked PyPI).
  • Open issues: open issues as a share of all issues ever filed, pull requests excluded. A low share means issues get closed; very young repos and repos that use another tracker read oddly here.
  • Weekly downloads: the last complete 7 days for the package named in the project's install docs, from the npm downloads API or from ClickPy, ClickHouse's public copy of the PyPI download logs, with pypistats.org as the fallback.

The composite score

For each measure, every framework gets its percentile rank within the tracked set, from 0 for the lowest to 1 for the highest. The score is the weighted average of those ranks, times 100:

MeasureWeightWhy
Stars25%Accumulated attention; the number most people quote
Stars gained, 30 days20%Attention now rather than in 2023
Commits, 30 days20%Is anyone shipping
Active contributors, 90 days15%How many people the project depends on
Weekly downloads10%How embedded the package is
Release recency10%Full weight for a release in 30 days, half for one in 90 days, none after

Missing measures (no package to download, no star baseline yet) are dropped and the remaining weights rescaled, so a project is never penalised for data that does not exist. Ties break on stars.

Known gaps

  • Stars and downloads can be gamed, and neither is filtered for that here.
  • Download counts mix registries: an npm download and a PyPI download are not the same unit, which is why downloads carry only 10% of the score.
  • Projects that develop in a private repo and mirror to GitHub show fewer commits and contributors than they have.
  • The 30-day growth baseline comes from archived pages until early November 2026, when this tracker's own snapshots take over.

The refresh runs daily. The code that builds this page reads only public APIs, and corrections are welcome at support@gravity.fast. For what these frameworks and platforms cost once you run them in production, see the AI agent pricing index and the cheapest AI agent platforms. The same collector also powers the MCP and A2A adoption census.

FAQ

What is the most popular open-source AI agent framework?

It depends on the measure. By GitHub stars on 17 November 2026, n8n (210,703) and AutoGPT (188,072) lead, followed by Dify, Langflow and LangChain, all above 145,000. By weekly package downloads, LangChain leads on PyPI (about 36.6 million in the week to 16 November 2026) and Vercel AI SDK on npm (about 45.8 million in the week to 15 November 2026). By the composite score on this page, which also weighs recent growth, commits, active contributors and releases, the order changes daily, so check the table for today's ranking.

Which AI agent framework is growing fastest?

The headline numbers at the top of the page name the repo that gained the most GitHub stars in the last 30 days, and the chart shows the top 12. Growth comes from this tracker's own daily snapshots, 30 days apart.

LangGraph vs CrewAI: which is more popular?

CrewAI has more GitHub stars (61,014 against 45,056 on 17 November 2026), while LangGraph has far more package downloads: about 14.7 million a week on PyPI against about 0.6 million for CrewAI in the week to 16 November 2026. Stars measure attention; downloads measure how often the code is installed, including by other libraries and CI systems.

How is the composite score calculated?

Each framework gets a percentile rank among the tracked set on five measures: stars (25%), stars gained in 30 days (20%), commits in 30 days (20%), active contributors in 90 days (15%) and weekly downloads (10%). A release in the last 30 days adds the full 10% release weight, one in the last 90 days half of it. When a measure is missing, such as downloads for a project with no package, the remaining weights are rescaled. The result is shown out of 100.

Why are n8n, Dify and Langflow on an agent framework leaderboard?

Because many teams build agents with them instead of with a code library, and searchers comparing open-source agent options meet them in the same results. They are labelled Visual builder in the Type column so you can compare like with like.

How often is the leaderboard updated, and can I reuse the data?

A script refreshes every number daily from the GitHub, npm and PyPI APIs. The data is published under CC BY 4.0: copy the table or download the CSV, and credit Gravity with a link to this page.

Why is my favourite framework missing?

The list covers open-source projects on GitHub that developers use to build LLM agents, with a public repo and meaningful usage. Coding agents such as OpenHands and Goose are products rather than frameworks and are left out. To suggest a framework, email support@gravity.fast with the repo URL; additions show up in the change log.

Sources

  1. GitHub GraphQL API: stars, issues, releases, commit history and authors for each repo, read daily from 4 October 2026.
  2. npm download counts API: last-week downloads for npm packages, read daily.
  3. ClickPy: ClickHouse's public dataset of PyPI downloads, built from the PyPI BigQuery logs, read daily.
  4. pypistats.org API: fallback for PyPI weekly downloads.
  5. PyPI JSON API: latest package version and upload date.
  6. Wayback Machine CDX API: archived GitHub repo pages from August and September 2026, used once for 30-day star baselines.