▓ PAREL
Console →
PAREL(1)Parel ManualPAREL(1)

DEPLOY AN AI AGENT
IN ONE CONFIG FILE.

NAME
parel — agent runtime control plane.
DESCRIPTION
Any model. Any sandbox. Any tool. Composed as plugins, scheduled by a tiny kernel, run serverless on Cloudflare. The kernel only dispatches. Everything else is a plugin.
$ parel deploy →man parel
[▓]~/projects/support-bot/agent.yaml
●YAML · 18 lines
$ parel deploy▓ ready in 1.2s
§01Platformfeatures.4

A tiny kernel.
An infinite surface.

▓ 01 · PROVIDER NEUTRAL
model:anthropic | openai | google | mistral
sandbox:e2b | local | modal | fly
memory:rolling-summary | redis | postgres
# → swap any cell, no app code changes

Any model. Any sandbox.

Swap Claude for GPT, E2B for local — without touching agent code. Plugins implement a tiny interface; the kernel handles the rest.

▓ 02 · PLUGIN ALL THE WAY
[ kernel ]
model
tools
memory
budget
policy
sandbox
steering
channel

The kernel only dispatches.

Models, sandboxes, tools, memory, budget caps, security policies — every capability is a plugin. Nothing is bundled, everything is composable.

▓ 03 · SERVERLESS BY DEFAULT
concurrent agents · last 60s↑312 peak

Cloudflare edge, globally.

Runs on Durable Objects with automatic checkpointing. Crash recovery by platform. Scale from one user to ten thousand on the same agent.yaml.

▓ 04 · ONE CONFIG
agent.yaml · main ← feat/budget+3 −1
model: claude-sonnet-4-20250514
− budget: $5/day
+ budget: $10/day
+ schedule: always-on
+ memory: rolling-summary
sandbox: e2b

Git-native, diffable, gradual.

Version control, code review, gradual rollouts. agent.yaml is the contract between your team and production.

§02Architecturetrace_id = r_8s2q

Push a config.
Get a running agent.

LIVE TRACE
ARCH(7)control plane → data planeARCH(7)
agent.yamlyour repo
name: support-bot
model: claude
tools: [bash, file]
▸
▓ parel kernelv0.1.0
scheduler
router
budget
policy
hooks
trace
▸
agent runtimeCF Workers
w-01running
w-02running
w-03idle
1. declare2. schedule · route · gate3. execute · observe · retry
1DECLARE

Define your agent in agent.yaml — model, tools, memory, budget. Store it in git.

2DEPLOY

parel deploy ships the config to the control plane. The runtime loads plugins, warms Durable Objects.

3RUN

Messages dispatch through the kernel. Logs, traces, and costs stream back in realtime.

§03Examplesexamples.3

Two commands.
No yak shaving.

Author agent.yaml. Run parel deploy. Your agent is reachable over WebSocket, scheduled by cron, or subscribed to a queue.

▶
DURABLE EXECUTION
Workflows checkpoint between steps. Crash → resume, not crash → restart.
▶
LIFECYCLE HOOKS
Intercept any stage: before/after model calls, tool execution, context building.
▶
PLUGIN SDK
definePlugin() + registerModelAdapter(). Ship a plugin in 50 lines.
# A research agent that watches HN.
name: hn-watcher
runtime: parel/v1
model:
provider: anthropic
name: claude-sonnet-4-20250514
temperature: 0.2
sandbox: e2b
memory: rolling-summary
tools:
- bash
- file_read
- file_write
schedule:
cron: "*/15 * * * *"
guards:
budget: $25/day
maxSteps: 40
§04Ecosystemplugins.7

First-party plugins.
Yours next.

Author a plugin →
▓ MODEL2
  • anthropic
    Claude Sonnet/Opus
    official
  • openai
    GPT-4o, o4
    official
▓ SANDBOX2
  • e2b
    isolated cloud VMs
    official
  • local
    dev only, no isolation
    official
▓ MEMORY1
  • rolling-summary
    LLM-compressed context
    official
▓ GUARDS2
  • budget-cap
    daily/request caps
    official
  • security-basic
    command & secret filter
    official
§05Get Startedinstall.sh

One config away from
your first running agent.

Sign up. Install the CLI. Ship in five minutes. Free tier: 10k agent-seconds/month.

Start free →View docs
$ install
$ curl -fsSL parel.sh/install | sh
# macOS · Linux · Windows (WSL)
PAREL~/projects/parelv0.1.0cloudflarebeta15:49:08 UTC