AI Infra2022
Provides runtime support for reversible effects and reactive coeffects so components can be declared, composed, and hot-replaced safely; includes effect tracking, coeffect resolution, a declarative component loader and HMR — aimed at plugin-driven agent harnesses and dynamic systems.
AI Agent2023
Runs local-first AI coding agents in a native desktop workspace to inspect, edit, and execute code with per-session model selection, plugin extensibility, and an approval-based permission layer — keeping projects, keys, and transcripts on your machine.
AI Agent2024
SDK for building browser-based AI agents: expose Playwright-style APIs plus natural-language primitives (act/observe/extract) with self-healing actions, token-efficient accessibility trimming, and runtime extension next to the browser. Supports TypeScript, Python, and Go.
AI Client2024
Orchestrates and coordinates multiple coding agents in a shared, cross-device workspace — preserving context, files, and durable artifacts so teams can run parallel agent workflows without losing intent or state.
AI Coding2024
Runs an AI coding agent that edits, tests, and manages code across terminal, desktop, web, and GitHub repositories. Uses specialized agents and a curated model catalog (DeepSeek, MiMo, MiniMax, GPT-5.6) and offers free access supported by text ads.
AI Agent2025
JVM framework for authoring agentic flows that mixes LLM-driven prompts with strongly typed domain models and normal code to plan and execute goals. Key features: pluggable planners (GOAP, Utility AI), Spring integration, strong typing, testability, and support for local and cloud LLMs.
AI Coding2025
Integrates named "skills" and multi-agent workflows into developer tooling so teams can turn ideas into context-preserving, auditable code changes. Provides npm/Skills CLI install paths and plugins for Claude Code and Codex, with stable and preview release lines.
AI Agent2025
Provides a Python and TypeScript SDK to build and run production AI agent harnesses — the agent loop plus tools, memory, sessions, context management and lifecycle controls — with model portability and built-in observability.
AI Coding2025
Interactive terminal-native AI coding agent that generates, edits, and runs code while managing multiple model providers and optional durable execution. Privacy-first design with local model support, round-robin model distribution, and a flexible agent system for custom workflows.
AI Agent2025
Orchestrates code-running agents to hunt verifiable open problems: schedules runs, applies null tests and skeptic re-checks, and packages found objects with short checkers so anyone can reproduce or validate a claim.
AI Agent2025
Evaluates and optimizes AI agents and language models in containerized environments, supporting large-scale parallel benchmarks and RL rollouts. Integrates with third‑party providers for thousands of parallel environments and serves as the official harness for Terminal‑Bench.
AI Coding2025
Runs many shells inside one terminal and treats coding agents as first-class panes. Combines daemon-backed persistent sessions, vim-style modal control, BSP tiling, a session rail and an Inbox that surfaces approvals, questions and finished turns from LLM-based coding agents — useful when you run and manage agent workflows alongside shells.