#bubbletea

Terminal cockpit for running a fleet of Claude Code sessions across all your repos — dispatch work, watch what ships, and act on what's blocked, from one screen.

Sleek, fast, token-efficient AI coding agent. Multi-provider (Cortex, OpenAI, Anthropic, Ollama) with a polished terminal UI. Fork of vix.

A small self-learning coding agent for your own model — any OpenAI-compatible server, local (LLMTray, LM Studio, Ollama, vLLM) or cloud. Single static Go binary, plan/auto modes, skills, permissions, Claude-Code-style TUI.

CLI + TUI that turns the GitHub Copilot CLI into a senior teammate: installs a curated catalog of skills, custom agents, a teaching persona, cross-session memory, and a native Spec-Driven Development engine. Pure Go — no LLM inside; capiko directs, Copilot executes.

A sidebar for Claude Code: usage limits, context, model, cost, git and session stats in a pane beside the transcript

Terminal UI that brings the local sessions of all your AI coding agents — Claude Code, Codex, Grok, and GitHub Copilot Chat — into one searchable place to browse, search, resume, and fork.

AI Identity & Account Switcher — isolated identities for coding agents (Claude Code, Codex, Cursor Agent)

A terminal coding agent that shows its work — safe by default, open to every model, built to prove what it builds

Write coding-agent prompts in your own language — DeepL or Google Cloud Translate translates them to English and delivers them into Claude Code, Codex or any herdr agent pane.

The Ultimate Multi-Agent MCP Hub & Go CLI connecting Claude Code, OpenAI Codex, and Google Antigravity

Go TUI app + Claude Code plugin that gives Claude sessions a persistent canvas display panel. Multiple TUI windows stay in sync via a shared Unix socket daemon.

Talunor is a local-first terminal AI agent written in Go, with persistent, auditable SQLite memory, guarded tool use, and a complete step-by-step course explaining how it is built.

A control panel over local and remote tmux servers, built for orchestrating many Claude Code sessions at once

A terminal observability UI for AI coding agents. See what Claude Code is doing, where, and why - without a second editor.

A fast terminal dashboard for coding-agent token usage and estimated costs, with date filters, cached reports, and exports.

Move coding-agent sessions between your machines, and between Claude Code and Codex. CLI, TUI and a desktop app for macOS and Windows.

TUI for Mandatum delegation chains: who sent this agent, where trust breaks, and what it may still do

OpenAI-compatible HTTP proxy for local LLMs (LM Studio, Ollama) with model-aware queueing, retry/failover, SSE streaming, and a Bubble Tea TUI. Single portable binary, no CGO.