An open ecosystem for search, retrieval, AI infrastructure, language model training, inference, and AI applications.
Portable, disk-first, open-source technologies for building search engines, vector databases, language models, AI runtimes, and AI applications without heavyweight platforms.
We believe AI infrastructure should be as portable as files on disk.
Search indexes shouldn't require clusters.
Vector indexes shouldn't require specialized databases.
Language models shouldn't require loading hundreds of gigabytes into memory.
Model training shouldn't depend on proprietary ecosystems.
Flatseek is building an ecosystem where every stage of the AI lifecycle—from knowledge retrieval to deployed AI applications—shares the same philosophy:
Portable. Disk-first. Open.
Flatseek Ecosystem
┌──────────────────────────────────────────────────────────────────────────────┐
│ KNOWLEDGE │
│ │
│ Flatseek Flatvec │
│ Keyword Search Semantic Search │
└──────────────────────────────────────────────────────────────────────────────┘
│
▼
┌──────────────────────────────────────────────────────────────────────────────┐
│ MODEL TRAINING │
│ │
│ Flatbuild Flattune │
│ LLM Training LLM Fine-Tuning │
└──────────────────────────────────────────────────────────────────────────────┘
│
▼
┌──────────────────────────────────────────────────────────────────────────────┐
│ MODEL INFRASTRUCTURE │
│ │
│ Flatweight Flatrun │
│ Model Storage Streaming Inference │
└──────────────────────────────────────────────────────────────────────────────┘
│
▼
┌──────────────────────────────────────────────────────────────────────────────┐
│ AI APPLICATIONS │
│ │
│ Flatbot Flatask │
│ Chat App & Language Models RAG Runtime │
│ │
│ Flatlens │
│ Dashboard & Analytics │
└──────────────────────────────────────────────────────────────────────────────┘
Developer tools such as Flatbench and Flatperf support the ecosystem but are intentionally kept separate from the core architecture.
Every project can be used independently.
Together, they form a complete open-source platform for building modern AI systems—from knowledge to production-ready AI applications.
| Project | Description |
|---|---|
| Flatseek | Disk-first full-text search engine comparable to Elasticsearch, OpenSearch, and Apache Lucene, designed for portable indexes without always-on clusters. |
| Flatvec | Disk-first vector database comparable to FAISS, Qdrant, Milvus, and Chroma for semantic search, embeddings, hybrid retrieval, and RAG. |
| Flatbuild | Language model training framework comparable to NanoGPT, LitGPT, torchtune, and Hugging Face Transformers, providing reproducible tokenizer training, model training, checkpointing, evaluation, and model export. |
| Flattune | Fine-tuning framework that prepares datasets from Flatseek and Flatvec, then automates supervised fine-tuning, evaluation, and model specialization. |
| Flatweight | Storage-native model format comparable to GGUF and SafeTensors, designed for portable, streamable AI model storage and execution. |
| Flatrun | Streaming LLM inference runtime comparable to llama.cpp, vLLM, MLX, and Ollama, executing models layer-by-layer directly from storage instead of loading entire checkpoints into memory. |
| Flatbot | Chat applications and the official home of the Flatbot language model family, including reference models, deployment examples, and interactive AI experiences built with the Flatseek ecosystem. |
| Flatask | Retrieval-Augmented Generation (RAG) runtime comparable to LangChain, LlamaIndex, and Haystack, connecting search, retrieval, and language models into grounded AI applications. |
| Flatlens | Search, monitoring, and analytics dashboard comparable to Kibana, OpenSearch Dashboards, and Grafana for exploring knowledge and AI data pipelines. |
| Flatbench | Benchmark suite for evaluating search engines, vector databases, storage systems, and AI runtimes. |
| Flatperf | Low-level profiling and performance analysis toolkit comparable to perf, VTune, and Tracy, providing runtime instrumentation and optimization insights. |
Most AI stacks are assembled from disconnected technologies.
Search Engine
+
Vector Database
+
Training Framework
+
Fine-Tuning Framework
+
Model Format
+
Inference Runtime
+
AI Applications
Multiple projects
Multiple formats
Multiple pipelines
Flatseek takes a different approach.
Flatseek End-to-End Pipeline
Knowledge
│
▼
Search & Retrieval
│
▼
Dataset Preparation
│
▼
Language Model Training
│
▼
Fine-Tuning
│
▼
Model Storage
│
▼
Streaming Inference
│
▼
AI Applications
Portable • Disk-first • Open • Composable
Each project can be used independently, but together they form a unified platform for building modern AI—from knowledge and retrieval to deployed AI applications.
- Disk-first by design — Data and models are designed to live on storage instead of permanently occupying memory.
- Portable formats — Move indexes and models across machines without rebuilding infrastructure.
- Composable architecture — Every project works independently while integrating naturally with the rest of the ecosystem.
- Open standards — No vendor lock-in. No proprietary ecosystem.
- End-to-end AI workflows — From search and retrieval to training, inference, and AI applications.
- Research-driven innovation — Exploring new approaches to search, storage, inference, and machine learning infrastructure.
- Build search engines that scale without heavyweight databases.
- Make semantic retrieval simple, portable, and efficient.
- Train compact, open-weight language models from scratch.
- Build storage-native AI infrastructure.
- Enable streaming inference for models larger than available RAM.
- Simplify reproducible model training and fine-tuning.
- Reduce infrastructure complexity through reusable formats.
- Build a unified ecosystem where knowledge, language models, and AI applications share the same architectural foundation.
Every project is released under the Apache License 2.0.
Use a single project—or combine the entire ecosystem to build your own AI platform.
