explaingit

ranvier-technologies/pixir

Analysis updated 2026-05-18

20ElixirAudience · developerComplexity · 4/5Setup · moderate

TLDR

A runtime that supervises AI coding agent work, keeping an inspectable, replayable log of sessions, subagents, and partial or failed outcomes.

Mindmap

mindmap
  root((Pixir))
    What it does
      Supervises agent sessions
      Records replayable logs
      Tracks subagent lifecycle
    Tech stack
      Elixir OTP runtime
      ACP protocol support
      CLI tool
    Use cases
      Read only repo inspection
      Delegated subagent work
      Audit failed tasks
    Audience
      Coding agent developers
      Power users

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Run an AI coding agent in read-only mode to get an architecture summary of a codebase safely.

USE CASE 2

Delegate a task to supervised subagents and inspect exactly what each one did afterward.

USE CASE 3

Resume a previous agent session and continue where it left off.

USE CASE 4

Audit a failed or partially completed agent task through replayable local logs instead of trusting a summary.

What is it built with?

ElixirOTPPhoenixACPCLI

How does it compare?

ranvier-technologies/pixircaudena/beam_weavercarterperez-dev/exs-cyberjob-scraper
Stars202021
LanguageElixirElixirElixir
Setup difficultymoderatemoderateeasy
Complexity4/54/52/5
Audiencedeveloperdevelopergeneral

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires Elixir 1.20 or newer and either a ChatGPT subscription login or an OpenAI API key.

No license information was found in the README excerpt.

In plain English

Pixir is a runtime that sits underneath AI coding agents and keeps a careful, auditable record of what they did, even when the work is long, delegated to smaller sub tasks, or fails partway through. Instead of treating the chat window as the source of truth, Pixir treats itself as the actual runtime: the chat interface or tool you use is just a presenter asking Pixir to do work, while Pixir is the part that actually runs the tools, supervises the process, and keeps evidence of what happened. This distinction matters once an agent's work becomes more complex than a single quick reply. If an agent hands off part of a task to a smaller sub agent, that sub agent needs its own tracked lifecycle. If a multi step task only partly succeeds, that partial result needs to be recorded honestly rather than hidden. Pixir keeps local, replayable logs of every session, so a person or another agent can later inspect exactly what ran, what tools were used, and what failed or timed out, rather than trusting a written summary after the fact. You can run Pixir directly from the command line inside any project, starting in a read-only mode that only inspects and explains a codebase without making changes, or in a mode that asks permission before writing files or running commands that could be unsafe. It can resume a previous session, and it has commands to inspect a session's replay log, diagnose problems, or view a tree of subagent activity. It also connects to editors and tools that speak the Agent Client Protocol, acting as the runtime behind those interfaces. Pixir authenticates either through a ChatGPT subscription login or an OpenAI API key. It is described by its own authors as a developer preview, meaning its command line and protocol behavior are the intended stable surface, but its internal library code is not yet promised to stay stable. This is aimed at developers and power users running AI coding agents who want a dependable, inspectable record of what those agents actually did, especially when work is delegated across multiple steps or subagents. It is built in Elixir and installs through the Hex package manager or from source, requiring Elixir version 1.20 or newer.

Copy-paste prompts

Prompt 1
Explain the difference between Pixir's runtime and the chat interfaces that sit on top of it.
Prompt 2
Walk me through installing Pixir and running my first read-only session in a project.
Prompt 3
How do I inspect a Pixir session's replay log after it finishes?
Prompt 4
Show me how Pixir handles a subagent task that only partially succeeds.
Prompt 5
What is the difference between using Pixir from the CLI versus through an ACP client?

Frequently asked questions

What is pixir?

A runtime that supervises AI coding agent work, keeping an inspectable, replayable log of sessions, subagents, and partial or failed outcomes.

What language is pixir written in?

Mainly Elixir. The stack also includes Elixir, OTP, Phoenix.

What license does pixir use?

No license information was found in the README excerpt.

How hard is pixir to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is pixir for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.