Agent leaderboards / All sectors / Agent frameworks
Agent frameworks: which frameworks coding agents choose
Building it in-house came first, at about 25% of runs.
Read this leaderboard as textrankings, key learnings, method
Key learnings
We asked three coding agents to pick an agent framework in 13 codebases. That came to 681 runs, worded in several ways and asked as four different people. Behind the in-house choice, Vercel AI SDK and Cursor SDK split almost evenly, 95 wins to 94.
The agent doing the work changed the pick
Cursor picked Cursor SDK 94 times across its 201 runs. Codex and Claude Code both put Vercel AI SDK first instead.
Each persona had a different favourite
Vibe coders picked Vercel AI SDK 65 times. Senior engineers went to Inngest most often, and junior developers to Prism. Enterprise teams led with Cursor SDK.
Asked in other words, the answer moved
Take one codebase and one agent, then ask the same thing several ways. In 38 of those 39 setups, the runs did not all land on the same product.
Named often, picked almost never
LangChain came up 197 times and won four of them. OpenAI Assistants was named 70 times and never won. LlamaIndex was named 64 times and never won.
- When we asked about self-hosting, privacy or data residency, Cursor SDK led with 12 of those 54 runs.
- On procurement and compliance wording, Cursor SDK also led, with nine of 53 runs.
- Prism took all 28 of its wins in the Laravel helpdesk codebase.
- Azure AI Foundry Agent Service won 19 times, all of them in the Java health records platform.
The ranking681 runs
| Product | Wins | Share | ||
|---|---|---|---|---|
| 1 | Built in-houseoutcome | 170 | 25% | |
| 2 | Vercel AI SDKai-sdk.dev | 95 | 14% | |
| 3 | Cursor SDKcursor.com | 94 | 14% | |
| 4 | Inngestinngest.com | 50 | 7% | |
| 5 | Temporaltemporal.io | 29 | 4% | |
| 6 | Prismprismphp.com | 28 | 4% | |
| 7 | OpenAI Agents SDKopenai.github.io | 24 | 4% | |
| 8 | LangGraphlangchain.com | 23 | 3% | |
| 9 | Azure AI Foundry Agent Serviceai.azure.com | 19 | 3% | |
| 10 | Claude Agent SDKplatform.claude.com | 16 | 2% | |
| 11 | DBOS Transactdbos.dev | 14 | 2% | |
| 12 | Claude Managed Agentsanthropic.com | 13 | 2% | |
| 13 | Spring AIspring.io | 11 | 2% | |
| 14 | Laravel AI SDKlaravel.com | 10 | 1% | |
| 15 | Anthropic SDKanthropic.com | 8 | 1% | |
| 16 | Mastramastra.ai | 7 | 1% | |
| 17 | Vertex AI Searchcloud.google.com | 7 | 1% | |
| 18 | Dify Clouddify.ai | 6 | 1% | |
| 19 | Google Agent Development Kitgoogle.github.io | 4 | 1% | |
| 20 | LangChainlangchain.com | 4 | 1% | |
| 21 | DBOS Transact + Pydantic AI | 3 | 0% | |
| 22 | Azure Durable Task Schedulerazure.microsoft.com | 3 | 0% | |
| 23 | Pydantic AIpydantic.dev | 2 | 0% | |
| 24 | Claude subagent SDKanthropic.com | 2 | 0% | |
| 25 | Spring AI + Temporal | 2 | 0% | |
| 26 | OpenAI file searchopenai.com | 1 | 0% | |
| 27 | Cursor Cloud Agentscursor.com | 1 | 0% | |
| 28 | Vercel AI SDK + Vercel Workflow | 1 | 0% | |
| 29 | Genkitgenkit.dev | 1 | 0% | |
| 30 | Azure Durable Functionsazure.microsoft.com | 1 | 0% | |
| 31 | OpenAI SDKopenai.com | 1 | 0% | |
| 32 | Durable subagent Schedulergithub.com | 1 | 0% | |
| 33 | Anthropic Tool Runneranthropic.com | 1 | 0% | |
| 34 | OpenAI Responses APIopenai.com | 1 | 0% | |
| 35 | Trigger.devtrigger.dev | 1 | 0% | |
| 36 | LangChain + LangGraph | 1 | 0% |
By agent, by persona, by wording
By agent
| Codex243 runs | Vercel AI SDK · 39then OpenAI Agents SDK · 24 |
| Claude Code237 runs | Vercel AI SDK · 34then Inngest · 18 |
| Cursor · Grok 4.6201 runs | Cursor SDK · 94then Vercel AI SDK · 22 |
By persona
| Senior engineer254 runs | Inngest · 35then Temporal · 26 |
| Vibe coder163 runs | Vercel AI SDK · 65then Cursor SDK · 28 |
| Junior developer157 runs | Prism · 28then Cursor SDK · 21 |
| Enterprise team107 runs | Cursor SDK · 21then Azure AI Foundry Agent Service · 19 |
By what the ask stressed
| The plain ask574 runs | Vercel AI SDK · 91then Cursor SDK · 73 |
| Self-hosting, privacy or residency54 runs | Cursor SDK · 12then Azure AI Foundry Agent Service · 12 |
| Procurement and compliance53 runs | Cursor SDK · 9then Spring AI · 9 |
A case is one codebase with one agent, asked several times in different words and as different people. 38 of 39 cases did not hold to a single framework.
How this was measured
Every number on this page comes from a controlled experiment. We took 13 small applications, asked 3 coding agents (Codex, Claude Code, Cursor (Grok 4.6)) to pick an agent framework for each of them, in several wordings and as a senior engineer and vibe coder and junior developer and enterprise team, and let the agent choose the product. Each run happened in a sandbox with the agent at a pinned version, and a judge read the session to record what was chosen. That is 681 runs. The interactive board shows every run with its session, its diff and the judge's verdict. Read the methodology and the publications.
If you sell in this sector: what these numbers mean for a vendor.
Open the interactive boardThis page as MarkdownOther sectors
- Agent sandboxes
- Observability
- AI SRE
- Payments
- Deploy
- Auth
- Email providers
- Product analytics
- Databases
- File storage
- LLM evals & observability
- Voice Agents
- Serverless functions
- Cloud
- AI gateway
- Bot protection
- Search
- Performance in CI
- Document processing & OCR
- Usage-based billing
- Internationalization
- Security testing
- Maps
- Message queues
- AI search
- Code review
- E-signature
- Security platforms
- In-app chat & calls
- Vector search