Tag

Provides a Rust-native, event-driven engine for multi-asset backtesting and live trading with Python as the control plane; offers deterministic research-to-production parity, modular exchange adapters, nanosecond-resolution backtests, and performance suitable for training RL trading agents.

Turns the developer terminal into an agentic development environment that accepts natural-language prompts to write code, run multi-step terminal workflows, and debug. Key features include interactive Agent Mode, session sharing, and a cloud orchestration platform (Oz) for scaling agents.

Enables high-performance deployment and serving of popular open-source LLMs (Llama, Falcon, StarCoder, etc.) with production features like streaming, tensor parallelism, quantization and Prometheus metrics. Now in maintenance mode; recommended for teams needing an integrated HF inference stack.

Runs a self-hosted AI coding assistant offering inline completions, workspace chat, model management, and editor/repo integrations — designed to run local/quantized LLMs for private, on‑prem code generation.

Detects file content types with a compact deep‑learning model that runs in milliseconds on a single CPU. Trained on ~100M samples across 200+ content types; offered as a Rust CLI plus Python, JS, and Go bindings for large‑scale security and file‑routing use.

A fast, native code editor that treats AI as a first-class collaborator — built in Rust, rendered at 120fps, with agentic editing, keystroke-level edit predictions (Zeta), multibuffer editing, native Git, and integrations for any agent or model.

Produces real-time 3D reconstructions from multi-view images using Gaussian splatting, with on-device training and interactive viewing across native desktops, Android, and the browser. Uses WebGPU and the Burn ML framework to ship dependency-free binaries, a CLI, live training visualization, and streaming .ply support.

Continuously captures your screen and spoken conversations, transcribes them in real time, generates summaries and action items, and exposes a memory-backed chat that can retrieve what you've seen and heard. Works across desktop, mobile and wearable devices and supports local SDKs and cloud sync.

Connects multiple machines into a local AI cluster to run frontier models across devices. Features automatic device discovery, topology-aware auto-parallelism, RDMA-over-Thunderbolt support, MLX backend, and API compatibility with OpenAI/Claude/Ollama.

Runs a native, extensible AI agent on desktop, CLI, or API to automate code, workflows, research, and writing. Built in Rust, supports 15+ LLM providers and 70+ extensions via the Model Context Protocol — designed for local-first automation and developer workflows.

Terminal-native agentic CLI to chat with Amazon Q Developer, run and explain shell commands, and operate on local code via natural language. Integrates local repo/shell context, supports agent actions and multiple model backends; repo later marked as maintenance-only and points to the closed-source Kiro CLI.

Provides a shared runtime that composes, extends, and observes services in real time by modeling capabilities as discoverable workers, functions, and triggers. It collapses separate integration surfaces (queues, cron, HTTP, observability) into one live catalog so agents and services can call and trace each other immediately.