thinkany-ai/termany

Agent-Native Terminal

What it solves

Termany is a specialized terminal designed for developers who run multiple AI coding agents simultaneously. It eliminates the friction of managing dozens of tabs and windows when using different agents (like Claude or Codex) on the same project, while consolidating essential developer tools—such as Git diffs, file explorers, and token cost tracking—into a single interface.

How it works

Termany organizes the workspace into a three-level hierarchy (workspaces, pages, and tabs) to keep sessions persistent and organized. It integrates directly with various AI agent CLIs, allowing users to launch agents into panes and track their status (working, done, or needs attention) based on screen activity. It also provides a unified view for managing SSH connections, remote hosts, and worktrees, with a built-in activity monitor to resolve port conflicts.

Who it’s for

It is primarily for developers who run five or more agent sessions at once, use multiple different AI agents on a single repository, or manage several worktrees and remote dev boxes to ensure long-running tasks survive laptop sleep cycles.

Highlights

  • Multi-Agent Orchestration: Built-in support for agents like Claude, Codex, Gemini, and Grok, with the ability to create "Bots" for group chats and coordinated work.
  • Integrated Review Tools: Panes can switch between a shell, a file tree with inline editing, Git diffs, and a web browser.
  • Session Persistence: Persistent sessions that maintain scrollback and state across worktrees and branches.
  • Cost Tracking: A dedicated usage dashboard that estimates token costs and tracks input/output for supported agents.
  • Remote Management: Per-pane SSH connections with automatic loopback port forwarding for remote URLs.

Related

  • Project
    scaccogatto/okf-skills

    okf‑skills is a Claude‑Code‑native toolkit that lets AI coding agents create, validate, consume and visualise knowledge bundles written in the Open Knowledge Format (OKF v0.2). It ships as a Claude plugin, as skills.sh‑discoverable agent skills, as a GitHub Action for CI validation, and as a read‑only MCP server for agents without file access. The bundle is just a directory of markdown files with tiny YAML front‑matter; the tool provides deterministic validation, automatic scaffolding, and an interactive HTML graph visualiser. Ideal for teams that want portable, version‑controlled system knowledge that both humans and AI agents can read and update.

  • Project
    owndev/Open-WebUI-Functions

    A collection of Python-based pipelines and filters that extend Open WebUI with integrations for Azure AI, Google Gemini, N8N automation, and performance monitoring tools.

  • Project
    NVIDIA/logits-processor-zoo

    A collection of logits processors for LLMs that allow developers to control output behavior, such as enforcing specific phrases, managing response length, and mitigating hallucinations.

  • Project
    OctagonAI/kalshi-trading-bot-cli

    Kalshi Trading Bot CLI is a Bun‑based command‑line tool that uses Octagon AI probability estimates to find edges on Kalshi prediction markets, size trades with half‑Kelly, enforce a five‑gate risk engine, and support basket building, backtesting, paper‑trading, and a learning loop (calibration, reflection, hypotheses). Install via `bunx kalshi-trading-bot-cli@latest`, run the setup wizard for API keys, then use commands like `search`, `analyze`, `buy`, `basket build`, and `portfolio` to trade or simulate strategies.