Linzumi website screenshot

Linzumi

Linzumi is a Y Combinator (Spring 2026) company in San Francisco building a Slack-shaped team chat that runs a fleet of AI coding agents inside every channel. Engineering teams kick off work, watch agent activity in real time, review output, and ship code without leaving the thread. Unlike sandboxed cloud agent products, Linzumi runs agents on the developer's own machine through a local "Commander" runner installed from the @linzumi/cli npm package, so agents work against real environment variables, dotfiles, and branches inside explicitly trusted folders. The product adds a decision inbox that surfaces only the choices needing a human, continuously compiled team context, git safety snapshots taken before each agent turn, and a bundled local MCP server that lets coding agents read scoped Linzumi message, thread, and channel context. It supports OpenAI Codex today with Claude Code announced as coming soon. The service is in beta via a macOS desktop app and a web workspace; there is no public developer API program, documentation portal, or published OpenAPI at this time.

Linzumi publishes 1 API on the APIs.io network. Tagged areas include Company, Artificial Intelligence, Developer Tools, Coding Agents, and Team Chat.

Linzumi’s developer surface includes support, CLI, authentication, changelog, and 11 more developer resources.

20.0/100 emerging ▬ flat Agent 29/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
1 APIs 1 MCP Servers
CompanyArtificial IntelligenceDeveloper ToolsCoding AgentsTeam ChatCollaborationMCPCommand Line InterfaceY Combinator

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 20.0/100 · emerging
Contract Quality 0.0 / 25
Developer Ergonomics 6.1 / 20
Commercial Clarity 2.6 / 20
Operational Transparency 2.1 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 29/100 · agent aware
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/linzumi: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

Linzumi Runner API

The private product API behind the Linzumi web workspace and the local Commander runner, served from serve.linzumi.com under a /api/v2 URI-versioned path. It is not a published ...

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

linzumi-mcp.yml

MCP SERVER

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Linzumi Authentication

oauth2-device-code/oauth2-authorization-code · 3 schemes

SECURITY

Linzumi Domain Security

TLSv1.3 · DNSSEC · DMARC

SECURITY

Resources

Get Started 1

Portal, sign-up, and the first successful call

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 3

Pagination, idempotency, versioning, errors, and events

Build 2

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 2

Status, limits, changes, and where to get help

Company 1

The organization behind the API

Other 2

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: linzumi
name: Linzumi
description: Linzumi is a Y Combinator (Spring 2026) company in San Francisco building a Slack-shaped team chat that runs
  a fleet of AI coding agents inside every channel. Engineering teams kick off work, watch agent activity in real time, review
  output, and ship code without leaving the thread. Unlike sandboxed cloud agent products, Linzumi runs agents on the developer's
  own machine through a local "Commander" runner installed from the @linzumi/cli npm package, so agents work against real
  environment variables, dotfiles, and branches inside explicitly trusted folders. The product adds a decision inbox that
  surfaces only the choices needing a human, continuously compiled team context, git safety snapshots taken before each agent
  turn, and a bundled local MCP server that lets coding agents read scoped Linzumi message, thread, and channel context. It
  supports OpenAI Codex today with Claude Code announced as coming soon. The service is in beta via a macOS desktop app and
  a web workspace; there is no public developer API program, documentation portal, or published OpenAPI at this time.
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://storage.googleapis.com/ployai/d195dfe3-6a0f-4051-8d67-1a4376685f60/user/3e1aeaf5-og-home-en.jpg
url: https://raw.githubusercontent.com/api-evangelist/linzumi/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
x-tier: profiled
x-tier-reason: enriched-from-public-sources
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- Company
- Artificial Intelligence
- Developer Tools
- Coding Agents
- Team Chat
- Collaboration
- MCP
- Command Line Interface
- Y Combinator
apis:
- aid: linzumi:runner-api
  name: Linzumi Runner API
  description: The private product API behind the Linzumi web workspace and the local Commander runner, served from serve.linzumi.com
    under a /api/v2 URI-versioned path. It is not a published developer API — there is no portal, reference, or OpenAPI —
    but it is partially observable through the publicly published @linzumi/cli client, which documents the device-authorization
    endpoint and speaks WebSocket to wss://serve.linzumi.com for runner traffic. Captured here as an observed surface, not
    a supported public contract.
  humanURL: https://www.npmjs.com/package/@linzumi/cli
  baseURL: https://serve.linzumi.com/api/v2
  tags:
  - Coding Agents
  - Team Chat
  properties:
  - type: Authentication
    url: authentication/linzumi-authentication.yml
  - type: Conventions
    url: conventions/linzumi-conventions.yml
  - type: ErrorCatalog
    url: errors/linzumi-problem-types.yml
common:
- type: Website
  url: https://linzumi.com/
- type: Login
  url: https://serve.linzumi.com/
- type: Support
  url: mailto:hello@linzumi.com
- type: Download
  url: https://downloads.linzumi.com/macos-beta/linzumi_macos_latest.dmg
- type: Profile
  url: https://www.ycombinator.com/companies/linzumi
- type: Packages
  url: packages/linzumi-packages.yml
- type: CLI
  url: cli/linzumi-cli.yml
- type: MCPServer
  url: mcp/linzumi-mcp.yml
- type: Authentication
  url: authentication/linzumi-authentication.yml
- type: Conventions
  url: conventions/linzumi-conventions.yml
- type: ErrorCatalog
  url: errors/linzumi-problem-types.yml
- type: Lifecycle
  url: lifecycle/linzumi-lifecycle.yml
- type: ChangeLog
  url: changelog/linzumi-changelog.yml
- type: DomainSecurity
  url: security/linzumi-domain-security.yml
- type: LLMsTxt
  url: llms/linzumi-llms.txt
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence