Key takeaways
- Cloud-first orchestration from Warp — agents run on their infrastructure or yours, with unified visibility across desktop, web, and mobile
- First-party Slack and Linear integrations let you trigger agents directly from where work happens
- Enterprise self-hosting keeps code execution within your network while Oz handles orchestration and observability
FAQ
What is Warp Oz?
Oz is Warp's cloud agent orchestration platform for running coding agents with triggers, environments, and team visibility.
Which models does Warp Oz support?
Claude (Opus 4.6, 4.5, Sonnet, Haiku), GPT-5.x/Codex, and Gemini — plus Auto modes that select the best model per task.
Can I self-host Warp Oz?
Yes, Enterprise plans support self-hosted workers that keep execution in your network while using Oz orchestration.
Does Warp Oz compete with Tembo?
Significant overlap — both orchestrate cloud agents with Slack/Linear integrations. Oz is Warp-native; Tembo is agent-agnostic with Jira and signed commits.
Product Overview
Warp Oz is the cloud agent orchestration platform from Warp, the company behind the popular AI-native terminal.[1] While most coding agent tools run locally, Oz is cloud-first — agents execute on Warp's infrastructure (or yours) with unified visibility across desktop, web, and mobile.
| Aspect | Details |
|---|---|
| Company | Warp (AI terminal, $90M+ raised) |
| Model | Cloud-first orchestration |
| Models | Claude, GPT-5/Codex, Gemini |
| Integrations | Slack, Linear, GitHub |
| Hosting | Warp-hosted or self-hosted |
| Platforms | Desktop app, web, mobile, CLI |
Oz positions itself as "the orchestration platform for cloud agents" — turning agents into automations that run without your machine being active.[1]
What It Does
Core capabilities:[2]
- Schedule agents like cron jobs (automations)
- Trigger agents from Slack mentions, Linear comments, or webhooks
- Multi-repo changes in a single task
- Unified control plane across desktop, web, mobile, CLI
- Session sharing — teammates can join running agent sessions
- Full API/SDK for programmatic orchestration
Key primitives:[2]
- Triggers — Events that start work (schedules, integrations, API calls)
- Tasks — Units of tracked work with inputs, state, and outputs
- Environments — Docker image + repos + setup commands for consistent execution
- Hosts — Where execution happens (Warp cloud or your infrastructure)
Integrations
Oz has first-party integrations with Slack and Linear:[3]
| Platform | How It Works |
|---|---|
| Slack | Tag @Oz in a message or DM the bot |
| Linear | Tag the Oz agent on an issue |
When triggered, Oz:
- Reads the conversation/issue context
- Spins up your configured environment
- Runs the workflow in the cloud
- Posts progress and PRs back to the same conversation
This is a key differentiator — most local-first tools (Emdash, Conductor) don't have Slack/Linear integration.
Multi-Model Support
Oz supports a broad range of models:[4]
OpenAI:
- GPT-5.2 (low/medium/high/extra-high reasoning)
- GPT-5.2 Codex, GPT-5.1 Codex Max, GPT-5.1, GPT-5
Anthropic:
- Claude Opus 4.6 (default and max)
- Claude Opus 4.5 and Sonnet 4.5 with thinking mode
- Claude Opus 4.1, Haiku 4.5, Sonnet 4
Google:
- Gemini 3 Pro, Gemini 2.5 Pro
Auto modes:
- Auto (Cost-efficient) — Optimizes for lower credit consumption
- Auto (Responsive) — Prioritizes speed with best available model
- Auto (Genius) — Selects most capable model for complex tasks
Environments
Environments ensure consistent execution across triggers:[2]
# Create an environment with guided flow
/create-environment ./frontend ./backend
# Or specify repos
/create-environment https://github.com/your-org/api.git
An environment includes:
- Docker image — The toolchain and runtime
- Repositories — One or more repos to clone
- Setup commands — Dependency install, builds, bootstrapping
The same environment works across Slack, Linear, CLI, and API triggers — no per-trigger configuration duplication.
Self-Hosting (Enterprise)
For enterprises needing execution within their network, Oz supports self-hosted workers:[5]
# Set API key
export WARP_API_KEY="your_team_api_key"
# Run the worker
docker run -v /var/run/docker.sock:/var/run/docker.sock \
-e WARP_API_KEY="$WARP_API_KEY" \
warpdotdev/oz-agent-worker --worker-id "my-worker"
# Route tasks to your worker
oz agent run-cloud --prompt "Refactor auth" --host "my-worker"
Self-hosting architecture:
- Oz orchestrator still manages task lifecycle and observability
- Execution happens on your infrastructure
- Code never leaves your network
- You get same session sharing and team visibility
The worker is open source: oz-agent-worker
CLI and SDK
Oz has a full programmatic interface:[2]
# Run cloud agent from CLI
oz agent run-cloud --prompt "Fix the auth bug" --environment env-123
# Create integrations
oz integration create slack --environment env-123
oz integration create linear --environment env-123
SDKs:
Use cases: CI pipelines, incident tooling, custom automation, internal dashboards.
Pricing
Warp offers credit-based pricing:[6]
| Plan | Price | Key Features |
|---|---|---|
| Free | $0/mo | Limited AI credits, limited cloud agents |
| Build | $18/mo | 1,500 credits, BYOK, extended cloud agents |
| Max | $180/mo | 12x credits (18,000/mo) |
| Business | $45/user/mo | Team SSO, enforced ZDR, up to 50 seats |
| Enterprise | Custom | Self-hosting, BYOK LLM, custom environments |
BYOK (Bring Your Own Key) is available on Build and above — use your own API keys for model providers.
Zero Data Retention
Warp has ZDR agreements with all model providers:[4]
- LLM providers don't train on customer data
- Inputs/outputs deleted after generating responses
- Available across all plans by default
This is a significant enterprise feature — compliance teams care about model training data policies.
Strengths
- Cloud-first — Agents run without your machine being active
- First-party integrations — Slack and Linear built-in
- Multi-model — Claude, GPT-5/Codex, Gemini with Auto selection
- Self-hosting — Keep execution in your network (Enterprise)
- Session sharing — Team visibility into running agents
- Full SDK — Python/TypeScript for programmatic control
- ZDR by default — Model providers don't train on your data
- Warp backing — Well-funded company ($90M+), active development
- Unified experience — Same agents across desktop, web, mobile, CLI
Weaknesses / Risks
- Warp lock-in — Deeply integrated with Warp terminal; harder to use standalone
- Cloud dependency — Even self-hosted workers need Oz orchestration cloud
- Credit-based pricing — Costs can be unpredictable for heavy usage
- No Jira — Slack and Linear, but no Jira integration
- No signed commits — Missing compliance feature for regulated industries
- Newer product — Oz is newer than Warp terminal; less battle-tested
- macOS primary — Warp terminal is macOS/Linux; no Windows
Competitive Landscape
Codex App (OpenAI) — Similar cloud execution + Skills/Automations, but OpenAI-only. Oz is multi-model.
Emdash — Local-first with issue tracker integration. No cloud execution, no Slack integration. Different architecture.
Conductor — Local worktrees for parallel Claude Code. No cloud, no integrations. Simpler tool.
GitHub Copilot Workspace — Cloud-based but GitHub-native. Less flexible than Oz for custom workflows.
Tembo — Agent-agnostic orchestration with Jira, signed commits, BYOK. Oz has Slack/Linear; Tembo has broader enterprise features.
Ideal User
Warp Oz is built for teams who:
- Already use Warp terminal (natural extension)
- Want cloud execution without managing infrastructure
- Trigger work from Slack or Linear
- Need multi-model flexibility (Claude, GPT-5, Gemini)
- Value session sharing and team visibility
- Have enterprise needs (self-hosting, ZDR)
- Don't need Jira or signed commits
Bottom Line
Warp Oz is the cloud orchestration play from a well-funded terminal company. While most coding agent tools are local-first, Oz is cloud-first — agents run on Warp's infrastructure with Slack/Linear integrations built in.
The enterprise story is compelling: self-hosted workers keep code execution in your network while Oz handles orchestration and observability. The ZDR agreements with model providers address compliance concerns.
The weakness is ecosystem lock-in. Oz is deeply integrated with Warp — not a standalone orchestration layer. If you're already in the Warp ecosystem, Oz is the natural choice. If you want agent-agnostic orchestration with broader enterprise integrations (Jira, signed commits), Tembo fills that gap.
Watch Oz carefully. Warp has significant resources and is shipping fast. As the "parallel agent orchestration" category matures, cloud-first vs. local-first will be a key architectural divide.
Research by Ry Walker Research • methodology
Disclosure: Author is CEO of Tembo, which competes in the agent orchestration space.