The coding agent
that lives in your
terminal.

interference reads your code, edits files and runs commands through an agentic loop — with explicit permissions and a read-only Plan mode. No editor lock-in. Just the terminal.

interference
interference terminal screenshot
/ 01 — the loop

An agent loop you can watch and trust.

  1. 01

    You ask

    Describe a task in plain language. interference plans before it touches anything.

  2. 02

    It calls tools

    read · ls · glob · grep · webfetch to explore, write · edit · bash · task to act — multi-step, streamed live.

  3. 03

    You stay in control

    Every mutating action is gated by allow / ask / deny. Approve with a diff in front of you.

  4. 04

    Undo anything

    Sessions are persisted and snapshotted. Roll back a change the agent made, instantly.

mode · read-only

Plan

The agent explores and reasons — never writes. Perfect for understanding a codebase or scoping a change before committing to it.

  • Filesystem read & search only
  • Cites file:line evidence
  • Zero side effects
mode · full access

Build

The agent writes files, applies atomic edits and runs commands — each behind your permission rules, with destructive actions denied by default.

  • Atomic edit (unique-match)
  • Sandboxed paths, timed bash
  • Approve-with-preview
/ 02 — what's inside

Small surface. Serious capability.

Native tool-calling

A typed tool registry over the Vercel AI SDK — multi-step, with tool errors fed back for self-correction.

Permissions by design

allow / ask / deny rules enforced in code, not in the prompt. The model can't talk its way past them.

A real TUI

Streaming output, spinners and live tool steps in a flicker-free terminal interface built with Ink.

Sessions & undo

Resume where you left off. Snapshots before every mutation mean undo/redo on the agent's edits.

Cost transparency

See exactly what you’re spending on API calls — live, per-request, in your terminal. No hidden usage, no surprise bills.

Bun-fast

Runtime, test runner, and package manager — one toolchain, zero config. Starts instantly.

38 built-in skills

Domain-specific agent skills (AWS, Rust, SwiftUI, NestJS, Docker, ...) auto-detected by keyword matching or invoked explicitly via /skill-name.

Subagents

Delegate complex multi-step tasks to isolated agents. Explore (read-only) and General (full) types, with permission inheritance.

Slash commands + autocomplete

/help · /clear · /undo · /redo · /init · /model · /plan · /build · /compact · /sessions · /rename. Fuzzy autocomplete on /.

/ 03 — why interference

Not just another agent.

01

European, by choice

Built in Italy. Open-source, MIT licensed, not VC-funded. Your code never leaves your machine unless you explicitly send it to an API. An independent, GDPR-native alternative to Silicon Valley agents.

02

Radically transparent

Every tool call, every reasoning step, and exactly what you’re spending on API costs — live, in your terminal. No hidden usage. No surprise bills.

/ 04 — quickstart

In your terminal in a minute.

bun install -g interference-agent

Then run interference. Add keys with /provider on first launch.