palgu

An engineering harness that governs coding agents and any model

Advanced API
Screenshot of palgu, An engineering harness that governs coding agents and any model

What is palgu?

Palgu is an engineering harness for AI coding agents. It routes tasks to models by risk, enforces team standards, validates and independently reviews changes, and records an audit trail, via a terminal CLI or the Palgu Studio desktop app.

Palgu positions itself as an engineering harness rather than another coding agent. Instead of writing code itself, it sits around agents such as Claude Code, Codex, Cursor, aider or its own agent, and manages how a task moves from a vague request to a tested, reviewed and recorded change. Its pitch is that agent orchestrators only run more agents, while Palgu applies one set of routing, budgets, policy, review and audit across all of them. In practice a developer signs in once and works from the terminal with the palgu command, or from Palgu Studio, a desktop app for macOS and Windows that groups tasks, a Validation Center, a Council Chamber, knowledge and routing. A single request triggers a sequence the site walks through with a refund-feature example: mapping the blast radius of a change, pulling architecture decision records, grading risk, requiring tests before implementation, choosing a model by task size and risk, validating functionally and visually, convening an independent multi-seat review by models that did not write the code, and logging the outcome in an audit ledger. The palgu -p flag runs a single task and exits, which suits CI and scripts, and palgu review exits with an error when the review council requests changes. The audience is engineering teams and platform teams that want agent-written code to follow their own standards. Deployment options include SaaS or a self-hosted gateway, bring-your-own keys, local or sovereign models, SSO through OIDC and SAML, audit export and data residency. The vendor says its servers never run customer code and that the audit log stores prompt hashes rather than prompt text. Among alternatives, Palgu competes less with single coding assistants than with orchestration and governance layers around them. It is aimed at teams who value policy control, model switching and proof of validation over a lightweight individual setup. The vendor also publishes benchmarks in which six models passed the same acceptance tests inside the harness, though those figures are self-reported.

How do you use palgu?

  1. 1Install the palgu CLI
    Run the one-line installer for macOS and Linux or the PowerShell version for Windows. Node.js 20 or newer is required, and the installer adds it if missing.
  2. 2Sign in
    Create a free account and run palgu login in the terminal. Every request then goes through the Palgu API.
  3. 3Run a first task
    Start a session with palgu, or run palgu -p with a short instruction such as fixing a failing test to execute one task and exit.
  4. 4Connect existing agents
    Use palgu enable to route Claude Code or Codex through Palgu, or point Cursor and aider at the endpoint. The docs cover setup.
  5. 5Set policy and review results
    Define standards such as tests before code, model choice by risk and budgets. Then check validation results and the audit record for each change.

Pros and cons

Pros

  • Works across agents (Claude Code, Codex, Cursor, aider) and models, so a team can switch models without rewriting its engineering policyAI
  • Independent review by models that did not write the code, plus functional and visual validation before a PR opensAI
  • Governance features include budgets, allowlists, SSO, audit export and an audit ledger storing prompt hashesAI
  • Flexible deployment: SaaS or self-hosted gateway, bring-your-own keys, and local or sovereign modelsAI
  • CLI mode (palgu -p, palgu review) fits CI pipelines and scripts, alongside a desktop appAI

Cons

  • Aimed at teams with defined standards and policies; a solo developer may find the layered workflow heavyAI
  • Palgu Studio is offered only for macOS and Windows, with Linux limited to the terminal CLIAI
  • Benchmark claims of consistent results across models are self-published and cover a single test appAI
  • Adds another service layer: requests go through the Palgu API or a gateway you must host and manageAI
  • Pricing beyond the first free month is only partly stated on the homepage, and managed model credits cost extraAI

How much does palgu cost?

Free trial

Every plan is free for your first month, and a free account is available. Cancel anytime.

Learn more

Pricing

Free account, and every plan is free for the first month, then from $9 per seat. Cancel anytime. Credits can be bought for managed models, or users can bring their own keys.

Learn more

Support

Documentation is available on the site, along with a platform-team checklist for deployment. The homepage does not describe other support channels.

Learn more

Integrations

Routes Claude Code and Codex via palgu enable; Cursor and aider connect to its endpoint. Supports frontier, open and local models (Ollama), BYOK, SSO (OIDC, SAML), CI runners, and SaaS or self-hosted gateway.

Learn more

Features

Live code graph and architecture context, risk grading, tests-first policy, model routing by task and risk, functional and visual validation, multi-seat independent review council, audit ledger, budgets, allowlists, and CLI plus Studio desktop app.

Frequently asked questions about palgu

  • How much does palgu cost?
    Free account, and every plan is free for the first month, then from $9 per seat. Cancel anytime. Credits can be bought for managed models, or users can bring their own keys.
  • Does palgu offer a free trial?
    Every plan is free for your first month, and a free account is available. Cancel anytime.
  • Does palgu have an API?
    Yes, palgu offers an API.
  • How do you use palgu?
    The walkthrough on this page covers 5 steps: 1. Install the palgu CLI 2. Sign in 3. Run a first task 4. Connect existing agents 5. Set policy and review results.
  • What platforms does palgu support?
    palgu is available on MacOS, Windows and Linux.
  • What does palgu integrate with?
    Routes Claude Code and Codex via palgu enable; Cursor and aider connect to its endpoint. Supports frontier, open and local models (Ollama), BYOK, SSO (OIDC, SAML), CI runners, and SaaS or self-hosted gateway.

Status

StatusActive
Views0
Outbound clicks0
Added11/18/2026

Platforms

MacOSWindowsLinux

Pricing

Free TrialSubscription