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

DEPLOY AN AI AGENT
IN ONE CONFIG FILE.

NAME
parel — agent runtime control plane.
DESCRIPTION
A serverless agent runtime from one config file. Model providers, sandboxes, memory, and policies stay declarative. The kernel only dispatches.
$ parel deploy →man parel
[▓]agent.yaml
●YAML · 18 lines
$ parel deploy▓ ready
§01Platformfeatures.4

A tiny kernel.
An infinite surface.

▓ 01 · PROVIDER LAYER
provider:anthropic | openai | openai-responses
sandbox:e2b
runtime:memory | budget | security
# current built-ins, extended through plugins

OpenAI and Anthropic today.

Select OpenAI, OpenAI Responses, or Anthropic through agent.yaml; run on E2B sandboxes without changing agent code.

▓ 02 · COMPOSABLE RUNTIME
[ kernel ]
model
tools
memory
budget
policy
sandbox
steering
channel

The kernel only dispatches.

Models are selected through the model provider layer; sandboxes, tools, memory, budget caps, and security policies are runtime plugins.

▓ 03 · SERVERLESS BY DEFAULT
active sessions · illustrativeautoscale ready

Serverless agent runtime.

Run agent sessions without operating agent servers or worker pools. PAREL keeps runtime, policy, and execution controlled from the same agent.yaml.

▓ 04 · ONE CONFIG
agent.yaml · main ← feat/budget+4 −1
model: claude-opus-4-6
− plugins: []
+ plugins:
+ - memory-rolling-summary
+ - budget-cap:
+ max_usd: 25
runtime.maxSteps: 40

Git-native, diffable, gradual.

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

§02Architecturecontrol plane / data plane

Push a config.
Get a running agent.

LIVE TRACE
ARCH(7)control plane → data planeARCH(7)
agent.yamlyour repo
agent: research-agent
provider: anthropic
plugin: sandbox-e2b
▾
▓ parel kernelpolicy hooks
scheduler
router
budget
policy
hooks
trace
▾
agent runtimeCF Workers
w-01running
w-02running
w-03idle
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 validates policy and prepares session state.

3RUN

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

§03Examplesexamples.3

Deploy from one file.
No runtime plumbing.

Define agent.yaml, authenticate once, and deploy. PAREL handles model adapters, sandbox lifecycle, session state, and policy hooks.

▶
DURABLE EXECUTION
Workflow checkpoints let turns resume after platform restarts.
▶
LIFECYCLE HOOKS
Intercept any stage: before/after model calls, tool execution, context building.
▶
PLUGIN SDK
Expose sandbox, memory, tools, channels, and guardrails through one plugin contract.
# Example agent definition.
version: "1"
agent:
name: research-agent
model:
provider: anthropic
model: claude-opus-4-6
plugins:
- system-static:
prompt: "You are a research assistant."
- sandbox-e2b
- memory-rolling-summary
- security-basic
- budget-cap:
max_usd: 25
runtime:
maxSteps: 40
§04Ecosystemproviders.3 / plugins.6

Model providers.
Runtime plugins.

Author a plugin →
▓ MODEL PROVIDERS3
  • anthropic
    Claude family
    provider
  • openai
    Chat Completions
    provider
  • openai-responses
    Responses API
    provider
▓ SANDBOX1
  • sandbox-e2b
    isolated cloud VMs
    plugin
▓ CONTEXT3
  • memory-rolling-summary
    LLM-compressed context
    plugin
  • system-static
    static system prompt
    plugin
  • steering-immediate
    mid-turn steering
    plugin
▓ GUARDS2
  • budget-cap
    cost/turn caps
    plugin
  • security-basic
    command and secret filter
    plugin
§05Get Startedinstall.sh

Ship your first
managed agent.

Create a workspace, connect the CLI, and deploy from a versioned config file. Keep models, sandboxes, tools, and policies behind the same runtime contract.

Start free →View docs
quickstart3 steps
$ npm install -g @parel/cli
$ parel login
$ parel deploy agent.yaml
# API key from Console / Settings# Node.js >= 22