v0.2 — Now with Anthropic & LangChain support

A flight recorder
for your AI agents.

Record every decision, tool call, and failure. Replay them later. Zero dependencies, one decorator.

Get Started Free View on GitHub
$ pip install agentblackbox
0
dependencies (core)
1
line to instrument
3+
SDK integrations
20+
models with cost tracking

72% of AI agent projects never reach production.

Not because the agents are wrong — but because they're invisible. You can't debug what you can't see.

🔍

No visibility

When an agent fails, you have no idea which tool call went wrong or what the LLM was thinking.

💸

Surprise bills

Token costs accumulate silently. You only see the damage at the end of the month.

🔄

Can't reproduce bugs

Flaky failures that only happen in production, with no way to replay the exact sequence of events.

🚫

Framework lock-in

Existing tools (LangSmith, W&B) require you to commit to one framework. AgentBlackBox works with any.

One decorator. Full visibility.

Drop it on any function. Existing code is unchanged.

BEFORE

def run_agent(task: str):
    result = client.messages.create(
        model="claude-sonnet-4-6",
        messages=[{"role": "user",
                   "content": task}]
    )
    return result.content[0].text

AFTER — full recording

from agentblackbox import BlackBox

@BlackBox.record(agent_name="researcher")
def run_agent(task: str):
    result = client.messages.create(
        model="claude-sonnet-4-6",
        messages=[{"role": "user",
                   "content": task}]
    )
    return result.content[0].text

AUTO-INSTRUMENT WITH PATCH (zero code changes)

from agentblackbox import patch_anthropic, BlackBox

patch_anthropic()  # patches ALL anthropic calls globally

with BlackBox.session("my-agent") as bb:
    run_my_existing_agent()  # no changes needed

bb.replay()  # see the full timeline

Everything you need to understand your agents.

Built for developers who ship real AI agents to production.

⏱️

Full timeline replay

Replay any session in your terminal with timestamps, token counts, costs, and full input/output.

💰

Cost tracking

Auto-calculates cost per session, per model, per agent. Supports 20+ models from OpenAI and Anthropic.

🔧

Tool call recording

Every tool invocation is captured: name, arguments, result, duration, and errors.

📊

Web dashboard

Local dashboard with session list, timeline detail view, and cost analytics charts.

☁️

Cloud ingest API

Run a shared cloud dashboard — remote agents POST recordings in real-time via API key auth.

📦

Zero dependencies

Core library has no dependencies. Pure Python 3.10+. SQLite storage. Nothing to configure.

Works with every major SDK.

Auto-instrumentation — no code changes in your agent logic.

Anthropic SDK
OpenAI Agents SDK
LangChain
LlamaIndex (coming soon)
CrewAI (coming soon)
Manual API (any framework)
# Anthropic
from agentblackbox import patch_anthropic
patch_anthropic()

# OpenAI Agents SDK
from agentblackbox.integrations import patch_openai_agents
patch_openai_agents()

# LangChain
from agentblackbox import BlackBoxCallbackHandler
handler = BlackBoxCallbackHandler()
chain.invoke(input, config={"callbacks": [handler]})

Share recordings across your team.

Launch a shared dashboard. Agents in production push recordings in real-time.

ARCHITECTURE
Agent A (prod) ──POST /api/v1/ingest──▶ Cloud Dashboard ◀── browser
Agent B (staging) ──POST /api/v1/ingest──▶ (your server)
Agent C (local) ───────────────────────▶
# 1. Start cloud dashboard (generates API key)
agentblackbox dashboard --cloud --port 8765

# 2. In your agents — use RemoteStorage
from agentblackbox.remote import RemoteStorage
from agentblackbox import BlackBox

store = RemoteStorage(
    api_key="abx_...",
    endpoint="https://your-dashboard.example.com",
)
bb = BlackBox.session("prod-agent")
bb._storage = store
bb.start()

Free forever for individuals.

Open source core. Paid cloud hosting when you need it.

Open Source
$0
Self-hosted, MIT license. Forever free.
  • Unlimited local recordings
  • Local web dashboard
  • All SDK integrations
  • CLI tools
  • Self-hosted cloud mode
Get Started →
Enterprise
Custom
On-premise or dedicated cloud.
  • Everything in Cloud
  • SSO / SAML
  • Unlimited retention
  • SLA guarantee
  • Dedicated support
Contact Us →

Start recording your agents today.

Zero config. Zero dependencies. One pip install.

View on GitHub → Join Cloud Waitlist