AI coding tools

GitHub8.8 / 10

Developers and teams hosting code with Git

Vercel AI SDK8.7 / 10

TypeScript developers

Vercel AI8.6 / 10

TypeScript/Next.js developers building AI-powered web apps

Ollama8.5 / 10

Developers running open LLMs locally for dev and prototyping

Openrouter8.5 / 10

Developers wanting one API for many models

Langfuse8.4 / 10

AI teams wanting OSS observability with cloud option

Axolotl8.3 / 10

ML engineers fine-tuning open-weight LLMs (Llama, Mistral, Gemma, etc.)

PEFT8.3 / 10

ML engineers fine-tuning open LLMs or diffusion models on consumer GPUs

Pgvector8.3 / 10

Developers who already run Postgres and want vector search

Pinecone8.3 / 10

RAG pipelines and LLM-powered semantic search at scale

Ragas8.3 / 10

RAG pipeline developers needing automated quality metrics

Together8.3 / 10

Startups running open-source LLMs cheaper than OpenAI

Fireworks8.2 / 10

AI engineers needing fast, scalable inference for open-source LLMs like Llama and Mixtral

Groqcloud8.2 / 10

Real-time AI apps needing sub-100ms first-token latency

Portkey8.2 / 10

Engineering teams shipping production LLM features needing multi-provider fallbacks and cost tracking

Supabase8.2 / 10

Full-stack developers building production SaaS apps

Weaviate8.2 / 10

Semantic search and RAG pipelines in production

Bentoml8.1 / 10

ML engineers packaging and deploying inference services to production

Dspy8.1 / 10

ML engineers building systematic, reproducible LLM pipelines

Litellm8.1 / 10

Platform teams giving many developers governed LLM access

Phoenix Arize8.1 / 10

LLM and RAG application developers who need span-level tracing out of the box

Promptfoo8.1 / 10

Developers benchmarking prompts, models and RAG

Qodo8.1 / 10

Development teams seeking automated code reviews

Chroma8.0 / 10

AI engineers building RAG and LLM-powered search

Cursor8.0 / 10

Professional developers who want agent-level AI in their daily coding workflow

FAL AI8.0 / 10

AI startups building image or video generation products

Guidance8.0 / 10

Developers enforcing JSON/structured output from LLMs

llama.cpp8.0 / 10

Developers running LLMs locally and offline

Milvus Cloud8.0 / 10

Developers building RAG/semantic-search applications

Qdrant8.0 / 10

Developers building RAG and semantic-search applications

Unstructured8.0 / 10

AI engineers building RAG pipelines needing reliable document ingestion

Weaviate Cloud8.0 / 10

AI engineers building RAG pipelines and semantic search systems

Zilliz Cloud8.0 / 10

AI/ML teams building RAG and semantic search applications

Apache Tika7.9 / 10

Developers building search indexing (Solr/Lucene) pipelines

Codeium7.9 / 10

Solo developers wanting zero-cost AI autocomplete across 70+ languages

Continue7.9 / 10

Developers wanting open-source AI coding with full model flexibility

Helicone7.9 / 10

Startups adding LLM logging with minimal code changes

mabl7.9 / 10

QA engineers

Milvus7.9 / 10

Engineering teams building RAG, semantic search or recommendations

Windmill7.9 / 10

Engineering teams building and maintaining internal tools and automations

Zed7.9 / 10

Developers seeking a fast, AI-integrated code editor

Convex7.8 / 10

TypeScript teams building real-time collaborative or multiplayer apps

Modal7.8 / 10

ML engineers running batch inference or model fine-tuning jobs

trigger.dev7.8 / 10

TypeScript teams building AI agents, LLM pipelines, or multi-step automations

Trl7.8 / 10

ML engineers fine-tuning open LLMs with SFT, DPO or RLHF

Ellipsis7.7 / 10

Development teams using GitHub

Kestra7.7 / 10

Data and platform engineers wanting a modern, declarative orchestrator

Langsmith7.7 / 10

AI engineers building and debugging LLM pipelines in production

Llamaparse7.7 / 10

Developers building RAG over PDFs and Office docs

MindsDB7.7 / 10

Data teams that want AI agents querying live databases without custom ETL