Features

Every feature carries a status —

shipping is in the binary today,experimental works but rough,planned not yet shipped.

›

Agent loop

shipping

The core ReAct loop — prompt, reason, tool, result, next step. Streamed, interruptible, and fully logged.

✎

File editing

shipping

Targeted patches, multi-file edits, new files. Every change lands in the transcript as a diff summary.

⏵

Command execution

shipping

Run shell commands through your $SHELL. Output is captured, streamed back, and written to the session log.

◆

Models & providers

shipping

Curated catalog. provider/model IDs. adapter: openai for any compatible endpoint. Credentials stay out of project config. Catalog →

⌂

Host runtime

shipping

Commands run in your shell on your machine — fastest path, uses the tools you already have installed.

⊟

Docker sandbox

shipping

Ephemeral containers for risky work. Workspace mounted in, container torn down with the session. Sandbox polish is experimental.

☁

Cloud runtimes

shipping

Offload commands to a remote sandbox. Daytona, Sprites, and Modal are available today via the same RuntimeFactory adapter pattern. Runtimes →

⌘

Sessions

shipping

Append-only JSONL logs under ~/.glue/sessions/. Resumable across runs. Replay UI is planned. How it works →

◐

Web tools

shipping

Fetch, search, extract, PDF OCR, browser automation. The CDP backend is experimental. Web →

⇶

Subagents

shipping

Delegate a sub-task to a separate agent with its own context and tool set. Useful for parallel search or independent investigations.

◇

Skills

shipping

Discoverable, runnable skill definitions the agent can invoke as first-class tools.

⌁

MCP integration

shipping

Talk to any MCP server as a tool source. stdio, HTTP+SSE, and WebSocket transports. Bearer and OAuth 2.1 auth, namespaced tools, live status in the TUI.