Portal-connected system context
Connect Xirp to Portal so the environment can surface system context tied to services, ownership, dependencies, and architectural decisions during a coding session.
Xirp
Xirp is an agentic development environment from Spotify that connects AI coding sessions to Portal context such as services, ownership, dependencies, and architectural decisions. It is designed for engineering teams that want agents to work with institutional knowledge instead of isolated prompts.
Overview
Xirp is an agentic development environment from Spotify that is designed to give AI coding sessions the same kind of system context a human engineer would rely on. Rather than treating each prompt as an isolated task, it connects to Portal so the session can reference services, ownership, dependencies, and architectural decisions.
The product is aimed at teams that want AI tools to work inside an organization’s real operating context. Xirp describes itself as a retrieval problem solver for institutional knowledge, with Workspace for shared session context and documentation that is generated as part of the development flow.
Core features
System-aware session grounding
Starts each session with the surrounding system, not just the file in view, so agents can understand who owns upstream components and what depends on them.
Shared workspace for people and agents
Workspace keeps work items, sessions, and docs together in one shared context layer for engineers and agents.
Automatic documentation from sessions
Turns the output of coding sessions into living documentation that stays current and can be reused later.
Model flexibility
Supports Claude, Gemini, and Codex, letting teams switch models without losing accumulated context.
Local or remote sessions
Can be run locally or remotely, giving teams an option to choose how sessions are executed.
Common use cases
Onboarding into an unfamiliar service
A new engineer can use Xirp to start a coding session with system context instead of searching across old docs, chat threads, or tribal knowledge.
Coding with system context
An engineer working on a change can see the surrounding service ownership, dependencies, and design decisions before making edits, which helps reduce guesswork during implementation.
Looking up architectural decisions
When someone needs to understand why a system was built a certain way, Xirp can surface architectural decisions in the same environment used for development.
Sharing context across a team
Teams can keep session context and generated documentation in Workspace so the next person or agent working on the system can build on what was already captured.
Using different AI models without losing context
Teams that want to compare model behavior can switch between Claude, Gemini, and Codex while keeping the same organizational context.
Pros and Cons
Pros
- Uses organizational context such as ownership, dependencies, and architectural decisions instead of only the current file.
- Can preserve context across sessions through Workspace and generated documentation.
- Supports multiple model providers, including Claude, Gemini, and Codex.
- Offers local or remote session execution.
- Backed by Spotify and described as battle-tested at Spotify on the site.
Cons
- The pricing page is unavailable in the provided source, so public plan details cannot be confirmed.
- The source does not show setup steps or a full list of supported integrations beyond Portal and the named model providers.
FAQ
What is Xirp used for?
Xirp is an agentic development environment that connects to Portal so coding sessions can use system context such as services, ownership, dependencies, and architectural decisions.
Which AI models does Xirp work with?
The site says Xirp works with Claude, Gemini, and Codex, and that you can run sessions locally or remotely without losing context.
How does Xirp keep context between sessions?
Xirp centers on context retrieval and session memory. It captures knowledge from coding sessions, turns it into documentation, and feeds that context into future sessions through Workspace and Portal.
Is pricing available on the website?
The site promotes a beta and mentions requesting access to a Portal instance. The pricing page itself returns a 404, so public pricing details are not available from the source provided.
Quick Facts
- Category
- Developer Tool
- Platform
- Xirp + Spotify Portal
- Primary users
- Engineering teams using AI coding agents
- Models
- Claude, Gemini, Codex
- Session modes
- Local or remote
- Source domain
- xirp.spotify.com
Alternative a Xirp
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Ghost
Ghost è un assistente AI da terminale per chattare, generare codice ed eseguire task da riga di comando. Include modelli gratuiti, supporta Linux, macOS e Windows, ed è open source.
Vi3ecode
Vi3ecode is a maintained development environment for working with AI coding agents. It keeps project context, terminal, Git, memory, flows, review, and communication connected around the agent you already use.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.