Technologies
The stack we build on, and why
Every tool here is one we design with, run in production and watch with AI observability. Pick one to see when it is the right choice, when it is not, and how we use it.
Models
Llama
Meta's family of open-weight large language models
Mistral
European language models, open-weight and hosted
Qwen
Alibaba's open-weight models for text, code and vision
DeepSeek
Open-weight models known for reasoning and code
Gemma
Google's lightweight open-weight models
Hugging Face
The hub for open models, datasets and ML libraries
GPT (OpenAI)
OpenAI's hosted models, reached through an API
Claude
Anthropic's hosted models for reasoning, writing and code
Gemini
Google's hosted multimodal models
LlamaMeta's family of open-weight large language models
MistralEuropean language models, open-weight and hosted
QwenAlibaba's open-weight models for text, code and vision
DeepSeekOpen-weight models known for reasoning and code
GemmaGoogle's lightweight open-weight models
Hugging FaceThe hub for open models, datasets and ML libraries
GPT (OpenAI)OpenAI's hosted models, reached through an API
ClaudeAnthropic's hosted models for reasoning, writing and code
GeminiGoogle's hosted multimodal models
Serving and AI platform
vLLM
High-throughput inference server for open LLMs
Ollama
Run open LLMs locally with one commandTGI (Text Generation Inference)
Hugging Face's inference server for LLMs
NVIDIA GPUs
The standard hardware for training and serving AI models
Ray Serve
Scalable model serving built on the Ray framework
LangChain
Framework for building LLM applications and agents
vLLMHigh-throughput inference server for open LLMs
OllamaRun open LLMs locally with one command
TGI (Text Generation Inference)Hugging Face's inference server for LLMs
NVIDIA GPUsThe standard hardware for training and serving AI models
Ray ServeScalable model serving built on the Ray framework
LangChainFramework for building LLM applications and agents
Observability
Data
pgvector
Vector similarity search inside PostgreSQLPostgreSQL
Reliable open-source relational database
MySQL
Widely used open-source relational database
MongoDB
Document database for flexible JSON-like data
Redis
In-memory data store for caching, queues and sessions
Elasticsearch
Distributed search and analytics engine
pgvectorVector similarity search inside PostgreSQL
PostgreSQLReliable open-source relational database
MySQLWidely used open-source relational database
MongoDBDocument database for flexible JSON-like data
RedisIn-memory data store for caching, queues and sessions
ElasticsearchDistributed search and analytics engine
Tell us what you run and what you want to change. We reply personally, and the first consultation is free.
Let's talk »
