Agent SDK

You write the agent. LMbox provides the runtime.

The official SDK to package and deploy a business AI agent on your customer's LMbox appliance. YAML manifest, system prompt, golden eval suite, HMAC signature. Count 2 to 3 days of development, from manifest to a production agent.

lmbox-cli on GitHub See existing agents Partner program

The dev flow

Three commands, from skeleton to signed deployment.

The SDK encodes the whole agent workflow — scaffolding, validation, build, pack, deploy. No manual step, no CI pipeline to write.

Scaffold

Start from a template (legal-document, _base) or a blank agent. The CLI generates the manifest, system prompt, test suite, README.

lmbox agent new nda-reviewer --vendor magellan

Iterate

Edit the manifest and prompt. The CLI validates the manifest against the official schema (JSON Schema draft 2020-12) and runs the golden suite against a local or remote model.

lmbox agent test ./nda-reviewer

Deploy

The agent is packaged as a HMAC-signed .lmbox + JSON sidecar. The deploy command pushes it to the customer's LMbox. The heartbeat picks it up on the next cycle.

lmbox agent deploy ./nda-reviewer --box BOX-XXX

Anatomy of an LMbox agent

Everything fits in a 4-file folder.

No framework, no proprietary DSL. YAML, Markdown, JSON Lines. Readable by a lawyer or a Compliance Officer, executable by an AI agent.

manifest.yaml

The agent's contract: model, prompts, tools, required connectors, eval thresholds, deployment parameters (audit, PII redaction). Validated against `lmbox.eu/v1`.
prompts/system.md

The system prompt encoding the business logic. This is what you, the partner, bring: your sector expertise translated into clear instructions.
evals/golden.jsonl

Golden test suite — one JSON-Lines case per situation, with assertions on expected output. Blocking in CI: an agent doesn't ship below its threshold.
tools/

Optional Python code for function-calling tools (RAG, actions, external API calls). Empty for pure-analyst agents.

manifest.yaml

apiVersion: lmbox.eu/v1
kind: Agent

metadata:
  slug: nda-reviewer
  version: 0.1.0
  vendor: lmbox
  vertical: legal
  display_name: NDA Reviewer
  description: >-
    Lit chaque NDA, identifie les clauses non-standard,
    rédige un mémo d'amendements.

spec:
  model:
    primary: mistral-large-2
    fallback: qwen2.5-32b
    temperature: 0.1
    max_tokens: 1024
  prompts:
    system: prompts/system.md
  tools:
    - name: search_clause_library
      type: rag
      source: connectors.sharepoint.legal-templates
  evals:
    pass_threshold: 0.8
    golden: evals/golden.jsonl
  deployment:
    audit: true
    rgpd_redact: [nir, iban, phone]

Why a SDK

Turn 15 days of prompt engineering into 2-3 days of packaging.

2-3 d

Iteration cycle

From client brief to agent in production. The SDK covers 100% of the cycle: scaffold, validate, test, package, sign, deploy.

€45k

Project revenue per agent

Discovery + prompt engineering + RAG + connectors + UAT + MEP. A clean deliverable you bill man-day to your end client.

100%

Partner IP

The agent you write is yours. You keep the right to repackage it as a vertical offer and resell it on the Partner Marketplace.

Let's talk about your first agent.

If you're a service integrator, consulting firm, or vertical software vendor, we have a structured partner program: early-phase SDK access, 2-day Certified Agent Engineer training, hands-on support for your first deployment.

Join the program See the code (MIT)