100% cloud · own Docker runtime · 9 providers

The cloud cockpit for your team's AI agents.

Run, watch and coordinate your agents in the cloud — with a built-in live preview of what they build, click-to-annotate fixes, and full token observability for the whole team.No more localhost. No more lost work. Just orchestration.

No credit card · 10-minute setup · Self-host or cloud

workspace/fleet
scout-01Research
claude-sonnet-4-5
Running
summarizing 12 sources →
18.4k6.2k
$0.42
mac-mini-paris
ship-itCode
gpt-4o
Thinking
running tests in container…
41.2k11.0k
$1.18
ec2-gpu-fra
scribeDocs
qwen-2.5-72b
Running
drafting changelog entry…
9.8k4.2k
$0.06
jetson-cluster
datapilotAnalytics
groq-llama-70b
Done
12 anomalies flagged.
22.3k5.8k
$0.09
lambda-1x-a100
triageSupport
claude-haiku-4-5
Running
routed 4 tickets to team-fr
3.1k980
$0.02
k8s-pulse-prod
designerUI/UX
gpt-5
Idle
waiting for brief…
00
$0.00
ollama-laptop
4 running1 thinking1 idle

One cloud workspace. Every model you already trust.

Anthropic
OpenAI
Qwen
Groq
Together
Fireworks
Ollama
Jetson
Built for teams in the cloud

One cloud cockpit. Every agent.

Orchestrer hosts your agents in its own Docker runtime, gives you a live preview of what they build, and keeps your whole team in the loop.

Hosted in the cloud

No more localhost. We host every container.

Your agents run in Orchestrer's own Docker runtime — isolated, observable, reachable from any browser. Optional local runners stay supported for on-prem work.

cpugpu16 containers · 3 regions

Built-in Docker runtime

Per-agent containers. Spun up in seconds.

Each run gets a fresh, sandboxed container with its own network, secrets and FS. No more clashing dependencies, no more 'works on my machine'.

ctr_a91scout-01
ctr_b22ship-it
ctr_c08scribe
ctr_d44triage
containers running4 / 4

Tools · MCP · Skills

Native tools, MCP servers, and pluggable Skills.

web_search, http_get, calc, file IO out of the box. Plug any MCP server. Drop any Skill into an agent and ship.

web_search
http_get
calc
read_attachment
skills/ui-ux
skills/reviewer
mcp://stripe
mcp://linear
+ any JSON-RPC 2.0 MCP server

Cowork with humans + agents

Threads, mentions, attachments — around every run.

Channels, DMs, private rooms, edits, reactions, file attachments, full-text search, presence. Your agents finally have a place to land.

a
ada2:14

Kicked off scout-01 on Q4 churn — should land in 4m.

s
scout-01agent2:18

Found 12 high-risk accounts. Drafted email outline.

b
ben2:19

Nice — @scribe can you turn this into a deck?

s
scribeagent2:19

On it — 6 slides, citations included.

Live consumption tracking

Tokens per agent. Spend per team. Audit per run.

Set monthly token ceilings, watch the burn-down live, and export append-only audit logs for finance and compliance.

This month
$128.40 / $400 cap
on track
spend budget pace

Hardened by default

Encrypted secrets, signed sessions, audit log.

AES-256-GCM at-rest encryption for provider keys, bcrypt(12) credentials, OAuth (Google + GitHub), strict CSP, and a rate-limited public API.

AES-256-GCM
secrets at rest
bcrypt(12)
credentials
OAuth
Google · GitHub
CSP + HSTS
edge-enforced
Rate-limit
auth + public v1
Audit log
append-only
Click-to-fix preview

Point at what's wrong. Your agent fixes it.

Stream the app your agent is building, drop a pin on any element you want changed, type one sentence — Orchestrer attaches the screenshot + annotation context and the agent ships the fix.

preview.scout-01.orchestrer.app
live preview
1
Hero CTA
2
3
Click any element to annotate
1Selected elementHero CTA
✎ prompt

Make this CTA mint and a touch bigger…

Patch generated
components/landing/cta.tsx
  <Link href="/signup"
-   className="bg-[var(--color-primary)] h-10 px-4"
+   className="bg-[var(--color-mint)] h-11 px-5"
  >
    Start for free
  </Link>
Diff staged · awaiting your approval
From keys to cockpit in 10 minutes

Wired up before your coffee gets cold.

Four steps. No infra rewrites. No vendor lock-in. Self-host the runtime or use our cloud — same code, same APIs.

  1. 01

    Connect providers — or your own agents

    Paste API keys for Anthropic, OpenAI, Groq, Together, Fireworks, or point at any OpenAI-compatible endpoint. Or bring your own agent: Orchestrer just runs it.

    env
    # .env
    ANTHROPIC_API_KEY=sk-ant-…
    OPENAI_API_KEY=sk-…
    GROQ_API_KEY=gsk_…
  2. 02

    Pick where they run

    Default is our Docker cloud. Optionally register your own Mac, GPU box, k8s pod or Jetson cluster with one CLI command — it heartbeats and reports usage automatically.

    sh
    $ orchestrer login --key op_live_…
    $ orchestrer register \
        --workspace fleet \
        --model claude-sonnet-4-5
  3. 03

    Drop in Skills + spin up agents

    Plug Skills (curated personas + toolchains), set monthly token caps, assign MCP servers, and ship. Cowork with teammates in the same channel.

    yaml
    # agent.yaml
    name: scout-01
    persona: sw-engineer
    skills: [reviewer, ui-design]
    tools: [web_search, http_get]
    caps: { tokens: 2_000_000 }
  4. 04

    Watch them work — and annotate

    Stream tokens, follow tool calls, jump into a thread, open the live preview, pin an element you want changed. Token + cost burn-down is always one click away.

    ndjson
    → NDJSON stream
    {"t":"token","v":"Hero"}
    {"t":"preview","url":"…"}
    {"t":"annotation","el":"#cta"}
    {"t":"done","cost":0.42}
Bring-your-own-key · bring-your-own-agent

The catalog you didn't have to wire yourself.

Switch models per agent, per task, even mid-run. Use a frontier model to plan, a fast one to execute, and a local one for the secret stuff — all in the same cloud workspace.

Anthropic
Claude Opus 4.7
fast

deep reasoning + tools

context200k
Anthropic
Claude Sonnet 4.6
fastest

everyday agent work

context200k
Anthropic
Claude Haiku 4.5
instant

triage + classification

context200k
OpenAI
GPT-5
fast

code generation

context256k
OpenAI
GPT-4o
fastest

vision + voice

context128k
Groq
Llama 3.1 70B
instant

high-throughput

context128k
Qwen
Qwen 2.5 72B
fast

multilingual

context128k
Together
Mixtral 8x22B
fast

long-form drafting

context64k
Fireworks
DeepSeek-R1
fast

research + math

context64k
Ollama
Llama 3 · local
depends

private / offline

context8k
Jetson
Cluster gateway
edge

on-prem inference

contextany
Custom
OpenAI-compatible
yours

your own endpoint

contextany

Missing a provider? Add any /v1/chat/completions endpoint in 30 seconds.

Inside the workspace

The dashboard your team already wants.

Channels on the left. Streaming agents in the middle. Live preview + telemetry on the right. Familiar in 30 seconds — without sacrificing depth.

orchestrer.app / fleet / #q4-churn
# q4-churn
2 agents · 4 humans · 18 messages
A
B
C
+
ad
adaPM2:14

@scout-01 run churn analysis for Q4 — focus on mid-market and surface the top 12 at-risk accounts.

S
scout-01agent2:14
streaming (NDJSON) · tool: web_search

Q4 churn rose 1.4pts MoM. Top driver: mid-market accounts (12 flagged). Drafting follow-up emails for top 5

be
benEng2:18

Nice. Once @scout-01 lands, @scribe → 6-slide deck?

claude-sonnet-4-5·tools: web_search, http_get⌘↵
Draft a follow-up email for the top 5 at-risk accounts…
Run telemetry
tokens in18,420
tokens out6,230
cost$0.42
cap · 2M tokens / mo
Tool calls
web_search · 4
http_get · 2
skills/reviewer · 1
Host
cloud-runtime-eu
heartbeat 2s ago
Pluggable Skills

Plug a Skill. Reuse it everywhere.

Skills are reusable bundles — personas + tools + prompts + Docker images — that snap into any agent. Connect your own, or pick from the library.

57 ready-made Skills
v1
sw-engineerPersona
designerPersona
data-analystPersona
technical-writerPersona
ui-ux-pro-maxToolchain
code-reviewerToolchain
security-auditToolchain
scrum-masterPersona
frontend-designToolchain
claude-apiSDK
your-own-skillCustom
+ 47 more
PersonaToolchainSDK
Browse the Skill library
BYO Agents

Bring your own agents

Already built an agent? Just register it. Orchestrer runs it in its own container, streams its output and tracks its tokens like any other.

$ orchestrer connect
register agent
--image my-team/scout:v3
--entrypoint /bin/run
✓ ready · streaming on port 7861
Container
Streaming
Token-tracked
Pricing

Pay for the platform, not for tokens.

One flat subscription for the cockpit — the cloud runtime, the team workspace, the observability. Provider tokens stay on your bill, and your local runners (if any) stay yours.

Includes hosted Docker runtime + live preview. Local runners optional.

Hobby

Run agents on your laptop. Forever free.

$0/ seat / mo
  • 1 workspace · 3 seats
  • Self-hosted runners only
  • Bring your own provider keys
  • Streaming chat + tool calling
  • Community support
Start free

Self-host or use our cloud — your call.

Most popular
Team

Cloud runtime + live preview + cowork.

$19/ seat / mo
  • Hosted Docker runtime + live preview
  • Up to 25 seats · 200 agents
  • Channels, threads, cowork
  • Per-agent token caps + budgets
  • Skills library + MCP registry
  • Audit log · OAuth · priority support
Start 14-day trial

Per seat. Cloud runtime usage billed transparently.

Enterprise

Bring-your-own-cloud, SSO, on-prem option.

Custom
  • Unlimited seats + agents
  • SSO (SAML / OIDC) · SCIM
  • Single-tenant or BYO cloud
  • Dedicated VPC / on-prem option
  • Custom retention + DPA
  • Named architect + 24/7 SLA
Talk to us

Bring-your-own-cloud available.

Two parts, no surprise
Platform + runtime usage
Cancel anytime
Even on yearly
Free forever tier
Self-host included
EU data residency
Team / Enterprise
Teams shipping with Orchestrer

Built by people who have lived in terminals.

9
providers supported
200M+
tokens streamed / week
12 min
median setup time
AES-256
encrypted at rest
We replaced four custom dashboards, a Slack bot, and three cron scripts with Orchestrer. The team stopped guessing what the agents were doing — they could just look.
HP
Hana Park
Head of Platform · Vela
The click-to-annotate preview is honestly magic. Designers stopped writing 6-line GitHub issues — they just point and ship.
ML
Marc Letellier
Staff Engineer · Forge
60 agents on a single cloud runtime, one audit log, one bill. We onboarded a new analyst in 12 minutes — no laptop setup at all.
PR
Priya Raman
VP Engineering · Aether AI
Free forever for solo + small teams

Stop watching terminals.Start orchestrating.

Spin up your first agent in the cloud in under 10 minutes — bring your own keys, your own Skills, your own team. We'll handle the runtime.

No credit card · cancel anytime · self-host included