Results for "fastapi"

Minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling. 2x faster than FastAPI with built-in batching, streaming, and multi-GPU autoscaling. Apache 2.0 licensed.

FastAPI-based API server for ExLlamaV2/V3 backends. OpenAI-compatible API with support for model loading/unloading, embeddings, speculative decoding, multi-LoRA, and streaming.

Local-first Expo and FastAPI Japanese practice app for Korean speakers that uses Whisper-compatible STT, local TTS, and embedding-based dialogue matching without a runtime LLM.

Declarative dataflow framework for building testable, modular, self-documenting data pipelines. Encode lineage and metadata directly in Python functions. Originally from Stitch Fix, now Apache incubating. Apache 2.0 licensed.

Open-source desktop novel-writing engine and AI story scaffold with Tauri, FastAPI, SQLite, and plot-generation workflows. MIT licensed.

Kubernetes-native workflow orchestration platform for AI/ML pipelines. Dynamic, resilient orchestration with strong type safety and reproducibility. Used by Lyft, Spotify, and Gojek. Apache 2.0 licensed.

Open-source personal trading agent and research autopilot platform featuring multi-agent swarms, quantitative backtesting, and broker connectors. MIT licensed.

MIT-licensed tool that turns screenshots, mockups, and Figma designs into frontend code.

Alibaba's production-ready multi-agent framework with 23K+ stars. Features built-in MCP and A2A support, message hub for flexible orchestration, and AgentScope Runtime for production deployment.

Local-first desktop workspace for coordinating AI agent teams across conversations, files, terminal, browser, Git, memory, plugins, and verification.

LLM-powered multi-market stock analysis system providing automated decision dashboard reports and real-time market insights. MIT licensed.

All-in-one AI framework for semantic search, LLM orchestration and language model workflows. Embeddings database with customizable pipelines.

Low-code framework for building custom LLMs and deep neural networks. Declarative YAML configuration for training state-of-the-art models with PEFT/LoRA, 4-bit quantization, distributed training via Hugging Face Accelerate, and native Kubernetes support. Linux Foundation AI project. Apache 2.0 licensed.