Overview

hipmmcode is a provider-agnostic AI coding agent that lives in your terminal. It combines a fullscreen terminal UI, a 40+ tool runtime, and a multi-agent orchestration layer, and it can talk to a large catalog of model channels — Anthropic, OpenAI, Gemini, DeepSeek, Kimi, Qwen, xAI Grok (API key or device-code OAuth), Codex subscription, and any custom proxy — through four native wire protocols plus the Claude Code process bridge.

hipmmcode                       # fullscreen interactive REPL
hipmmcode "fix the failing test"  # one-shot headless run
hipmmcode serve                 # HTTP/WS server + async task queue
hipmmcode acp --listen :9910    # drive it from an editor over the network

What makes it different

Provider-agnostic to the core	Top + Extended channel catalog; each speaks its native streaming protocol (OpenAI-compatible, Anthropic, Gemini, Responses). OAuth for Codex / xAI / Qwen. A custom endpoint is 3 lines of JSON. One agent team can mix models from different vendors.
Fullscreen TUI by default	A managed viewport with mouse support: hover and click to expand tool output, drag-select with auto-copy, a pinned bottom status bar that survives streaming, an in-turn todo tree, and a transcript view on Ctrl+O.
Multi-agent orchestration	The Agent tool spawns teammates — foreground or background, on any provider — that coordinate through shared task lists and file mailboxes. Bundled profiles (team-designer, judge, optimizer, Explore, Plan, …) work with zero setup.
Governed autonomy	A permission rule engine (allow / deny / ask), everyday permission modes including Auto (new-install default), conditional bypass, lifecycle hooks, an optional OS-level bash sandbox, and hard blocks on destructive commands.
Embeddable everywhere	Headless exec with text / json / stream-json output, a direct-connect HTTP/WS server with a fire-and-forget task queue, the Agent Client Protocol (ACP) for editors, and a stream-json SDK control protocol on stdin/stdout.
Self-documenting binary	hipmmcode integration prints the full machine-integration handbook; hipmmcode doctor diagnoses your environment; hipmmcode update self-updates.

The 30-second tour

1. Install — one curl line, Homebrew, npm, or a PowerShell one-liner on Windows. See Installation.
2. Connect a model — hipmmcode model walks you through picking a channel, pasting an API key, and choosing a default model. See Quickstart.
3. Chat — hipmmcode opens the fullscreen REPL. Type naturally; the agent reads files, runs commands, searches the web, and edits code with your approval.
4. Scale up — ask it to spawn named Agents in parallel; they automatically share the session's single implicit team. Then wire in MCP servers, install skills, define hooks, or drive it headlessly from scripts and servers.

Feature map

• Interactive mode — the fullscreen TUI, keyboard, mouse, vim mode, attachments (images & video)
• Slash commands — all 75 in-REPL commands
• Headless mode — exec, output formats, budgets, webhooks
• Sessions & memory — resume, fork, rewind, compaction, persistent memory
• Settings — every config key and environment variable
• Model channels — built-in providers, custom endpoints, model discovery
• Built-in tools — the full 40-tool registry
• Agent teams — teammates, legions, background agents
• Skills & plugins — skills, custom commands, plugin marketplaces
• MCP servers — standard .mcp.json, OAuth, trust gating
• Permissions & sandbox — rules, modes, OS sandbox
• Hooks — lifecycle command hooks
• Server & task queue — hipmmcode serve, POST /tasks
• Editor integration — ACP over stdio and WebSocket, IDE diagnostics
• SDK protocol — stream-json control protocol
• CLI reference — every subcommand and flag

Platforms

macOS (Apple Silicon & Intel), Linux (x64 & arm64), and Windows (x64, native) — distributed as prebuilt binaries. The binary is free to use; see the LICENSE shipped with each release.