AgentFlux

Hyperagent is an AI agent platform presented by Airtable founder Howie Liu that deploys a fleet of agents to research, draft, build, deliver, and maintain outputs such as websites, videos, presentations, documents, and dashboards using an organization's data, tools, and working style. Agents run in dedicated computing environments with access to real browsers, shells, files, and connected software; their execution can be inspected as searches, decisions, and generated artifacts. The platform supports always-on agents with scheduled or heartbeat wake-ups, agent-to-agent orchestration, human approval steps, and learning through generated memories and skills. Agents can be invoked from Slack, email, or Telegram, through webhooks, or on a schedule, and are managed from a central command center.

FrontierAgent is an open-source agent runtime, terminal product, and evaluation suite for long-horizon research and file-based work. Its native terminal TUI provides a ReAct workflow in which one stateful agent researches, reads files, writes deliverables, runs commands, and iterates in a task-scoped sandbox, and an Agent Team workflow in which a coordinator maintains a task board, delegates bounded independent assignments to parallel sub-agents, collects structured reports, and synthesizes the result. Shell and file tools use a shared sandbox with read-only /inputs, working-state /workspace, and persistent /outputs directories. The TUI supports queued instructions during execution, approval-required diffs for mutating operations, local action traces, checkpointed sessions, resumption, and reversion. The same workflow engine powers a subprocess benchmark runner with deterministic artifact collection, concurrency, progress inspection, and reruns of individual failures. The repository also documents connection to the OpenAI-compatible Apodex-1.1 endpoint through the Apodex API.

Embabel is an open-source framework for authoring agentic flows on the JVM. Written in Kotlin with a natural Java usage model and built on Spring, it combines LLM-prompted interactions with manually written code and strongly typed domain models. Flows are expressed through actions, goals, conditions, and domain objects; they can be authored with Spring-style annotations such as @Agent, @Goal, @Condition, and @Action, or with an idiomatic Kotlin DSL. The framework dynamically formulates plans toward goals using a pluggable, non-LLM planning step. Its default approach is Goal Oriented Action Planning (GOAP), while Utility AI is also supported for selecting actions by utility scores rather than strict preconditions and postconditions. Conditions are reassessed after each action, and the system replans based on new information and observed effects, allowing known actions to be combined in novel orders and enabling runtime decisions such as parallelization. The planning model is independent of the actions, goals, and plans themselves, and can extend application capabilities by adding domain objects, actions, goals, and conditions without changing finite-state-machine definitions. Execution is provided through an AgentPlatform with focused, closed, and open modes. Focused mode runs a requested agent from application code; closed mode classifies user intent or an incoming event to select an agent; and open mode searches across available goals and actions to build a custom agent, while allowing developers to restrict goal selection. Open mode can find paths not explicitly envisioned by developers and combine functionality from multiple providers, but individual steps must still be defined by the application. Embabel supports mixing language models, including local models for selected tasks, separates the programming model from platform internals for local or production execution, and integrates with Spring dependency injection, AOP, persistence, transactions, and testing. The framework is designed for unit and end-to-end agent testing.

AgentGrid.io is a shared workspace for humans and AI agents to work on the same live artifacts, including documents, reports, slides, apps, and designs. Users can work with agents such as Claude, ChatGPT, Codex, Hermes, OpenClaw, Cursor, and Grok Bot, then have an agent share an artifact into the workspace for people and other agents to access. The workspace provides shared context, per-agent and per-folder permissions for reading, writing, modifying, and publishing, plus version history and diffs for artifacts. Agents authenticate as agents, permissions can be revoked, approvals have owners, and revisions can be restored. The stated workflow is to work with an agent, ask it to share the resulting artifact on AgentGrid.io, and invite people or additional agents to collaborate on the latest version.