Python SDK · TypeScript SDK · OpenTelemetry · plain REST. Pick whichever fits your stack — they all write the same tamper-evident chain.
import blackbox_sdk as bb
bb.configure(api_url="https://blackbox-gold.vercel.app
")
with bb.run("my_run", model="claude-sonnet-4-6",
system_prompt="You are a helpful assistant.") as r:
r.reasoning("Deciding what to do…")
r.tool_call("web_search", result={"hits": ["..."]})
r.output("Here is the answer.", cost_usd=0.0031, latency_ms=820)
r.seal()pip install blackbox-sdkimport { BlackboxClient } from "@blackbox-ai/sdk";
const bb = new BlackboxClient({ apiUrl: "https://blackbox-gold.vercel.app
" });
const run = bb.run("my_run");
await run.genesis({ system_prompt: "You are helpful.", model_snapshot: "gpt-4o", tools: [] });
await run.reasoning("Deciding what to do…");
await run.toolCall("web_search", { query: "latest news" });
await run.seal();npm install @blackbox-ai/sdk# Zero-config OTel — no SDK needed export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT="https://blackbox-gold.vercel.app /v1/otel/traces" export OTEL_SERVICE_NAME=my-agent # Every LLM call is now recorded automatically.
pip install opentelemetry-instrumentation-anthropiccurl -X POST https://blackbox-gold.vercel.app
/v1/events \
-H "Content-Type: application/json" \
-d '{"run_id":"my_run","type":"reasoning","title":"Step 1"}'POST https://blackbox-gold.vercel.app
/v1/events