A terminal coding agent where the model writes one program instead of calling tools one at a time. Bough flips the usual tool-calling loop: the agent emits a single script that does the work, which removes a lot of round-trip overhead on multi-step tasks.
Be the first to rate Bough. Your feedback helps other users decide.
Have the agent generate a single program that performs a multi-file refactor in one pass.
Replace twenty tool calls with one script, cutting latency and tokens.
Run the whole session in a TUI without leaving the shell.
Similar tools in the same category — compare side-by-side
A radically extensible coding agent for the modern Lisp hacker. Kli is built around extensibility fi...
An open-source Elixir runtime for AI agents that live inside your application and act by writing cod...
A public collection of skills for real engineers, published straight from the author's own .agents d...
Guides and comparisons about code tools
Eleven recent open-source and self-hosted projects for building, sandboxing and deploying coding agents you own outright rather than rent.
A practical guide to AI code-security tools for 2026 — Snyk, Wiz AI, Codiga and Amazon Q Developer across code, IaC and cloud posture layers.
Best AI code tools for mobile development in 2026 — AppForge AI, ReactNative AI, and companions like Codiga for review and security.
AI coding assistants compared by job: Copilot, Cursor, Claude Code, CodeRabbit, and Warp, for completion, agentic work, review, and the terminal.
Automate your documentation workflow with AI code tools. Generate clear, comprehensive docs for your projects in minutes in 2026.