A local-first Agent OS runtime for reproducible, specification-first AI coding workflows, restructuring AI coding through Socratic interviews, immutable seed specs, and a 3-stage evaluation gate.

Model Context ProtocolAI AgentsRust

VIEW DETAILS →

A KVCache-centric disaggregated architecture platform for LLM serving, providing distributed KVCache pooling, topology-aware high-speed transfer engine, and centralized scheduler, supporting Prefill-Decode separation and MoE elastic inference.

Large Language ModelsRustPyTorch

VIEW DETAILS →

A multi-language backend framework that unifies APIs, background jobs, queues, workflows, streams, and AI agents with a single core primitive (Step), featuring built-in observability and state management. Supports TypeScript, Python, and JavaScript under Apache-2.0 license.

Multi-Agent SystemAI AgentsAgent Framework

VIEW DETAILS →

A minimal, secure Python interpreter written in Rust for AI agents, featuring microsecond startup latency and state snapshotting.

SDKAI AgentsAgent Framework

VIEW DETAILS →

A high-throughput, low-latency inference framework designed for serving generative AI and reasoning models in multi-node distributed environments.

Model & Inference FrameworkRustPython

VIEW DETAILS →

A lightweight coding agent that runs locally in your terminal to assist with development tasks.

Agent & ToolingTypeScriptPython

VIEW DETAILS →

Wren Engine is the semantic engine for MCP clients and AI agents, enabling accurate data access, semantic understanding, and governance for AI systems.

Agent & ToolingPythonRust

VIEW DETAILS →

A curated list of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agents, maintained by the E2B team.

Docs, Tutorials & ResourcesPythonTypeScript

VIEW DETAILS →

A developer tool that adds autocomplete and AI capabilities to your existing terminal on macOS & Linux platforms, built with Rust.

Agent & ToolingRustPython

VIEW DETAILS →

NautilusTrader is a high-performance, production-grade algorithmic trading platform designed for quantitative traders. Powered by a Rust core for speed and safety, it enables event-driven backtesting and live trading within a native Python environment, ensuring seamless deployment from research to production without code changes.

OtherPythonRust

VIEW DETAILS →