TUI-use: Let AI agents control interactive terminal programs
Details
- External ID
- 47692661
- Source
- HN
- Company
- —
- Product
- TUI-use: Let AI agents control interactive terminal programs
- Website domain
- github.com
- Launched
- April 8, 2026
- Cohort
- —
- Upvotes
- 52
- Upvotes percentile
- 0.8367609254498715
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Enrichment
- Theme
- ai agent infrastructure and tooling
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- ai agents control terminal programs
- Manually corrected
- False
Could you build this?
Partial Bridging an LLM to an arbitrary interactive pseudo-terminal (PTY) requires managing ANSI escape codes, terminal emulation states, and screen buffer parsing.
What it would actually take: The architecture requires creating virtual pseudo-terminals (pty/termios) in Python or Go, embedding a terminal emulator engine (like pyte or xterm-headless) to parse ANSI escape sequences and render an internal screen state matrix, and feeding text snapshots or coordinate diffs to an LLM. Handling edge cases around interactive curses apps, alternate screens, raw mode, and async input timing requires specialized low-level terminal I/O knowledge.
Discussion
20 comments analyzed.
Competitors mentioned: tmux with agent glue/shims, mcp-repl, agent-tui, Jupyter kernel over MCP, nREPL/CIDER
Concerns raised: Prompt injection vulnerability from TUI output being read as agent context, Token usage impact not clearly documented compared to tmux alternatives, Polling-based interaction model bloats context window, Edge cases with debuggers, multi-line inputs, large outputs, interrupts
Feature requests: Token usage comparison/optimization documentation vs tmux, Support for interactive debuggers (GDB, PDB, delve), Handle large outputs without filling context window, Better support for long-running commands and restarts
Competitors
Other products that read as similar to this one — 1786 launches clear the similarity bar, closest 8 shown.
Attention rank: #266 of 1787 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 161 days after the earliest competitor.
- Cook · hn · 2026-03-05 · 6 upvotes · similarity 0.74
- TermHub · hn · 2026-04-05 · 5 upvotes · similarity 0.73
- Wmux · hn · 2026-06-13 · 5 upvotes · similarity 0.69
- Aurict · hn · 2026-09-04 · 5 upvotes · similarity 0.67
- jolo · github · 2026-09-10 · 30 upvotes · similarity 0.66
- Agent Armor, a Rust runtime for enforcing policies on AI agent actions · hn · 2026-04-17 · 7 upvotes · similarity 0.65
- A2acast · hn · 2026-08-28 · 5 upvotes · similarity 0.65
- Fleet · hn · 2026-06-29 · 8 upvotes · similarity 0.64
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.