Bring your AI agent logs and traces into Bronto with OpenTelemetry, and query your logs through Bronto’s MCP server with LangGraph. Follow model calls, tool use and errors in one place, with 12 months of always-hot retention. Explore how you can easily connect these tools with Bronto.
We built a real agent with Vercel's new eve framework to track tech events and Call for Papers deadlines, posting digests to Slack and filing CfPs in Jira. Because eve is OpenTelemetry native, sending its traces and logs to Bronto took minutes, giving full visibility into every model call and tool run.
Build with eve
Define the agent, tools, schedules and Slack channel by convention.
Deploy to Vercel
Run on Vercel with Cron, Blob storage and AI Gateway models.
Enable OpenTelemetry
Export the traces and logs eve already emits for every run.
Send to Bronto
Search every LLM call and tool invocation, kept hot for 12 months.
Anthropic's new OpenTelemetry export for the Claude Platform is vendor neutral, so Bronto supports it from day one. Messages API requests, tool use and Managed Agents sessions arrive as standard GenAI spans, so you can see which tools the model called, which call failed and where the time went.
Add a Custom destination
In the Claude Console, open Settings, OpenTelemetry, Add destination.
Point it at Bronto
Use your regional Bronto ingestion URL and an API key with the Ingestion role.
Choose content mode
Send metadata only, or full content with prompts, responses and tool arguments.
Trace every agent step
See model runs, tool calls, token usage and timing next to the rest of your telemetry.
OpenClaw is an open-source AI assistant that runs on your own hardware. Send its logs, actions and traces to Bronto with OpenTelemetry, then search across agent history and investigate what happened without grepping. Model calls arrive with token, model and provider context, while BrontoClaw brings sessions, errors and tool usage into one dashboard.
Create a Bronto dataset
Set up a free Bronto account and create a dataset to receive your OpenClaw telemetry.
Generate an ingestion API key
Create your key during onboarding or in Settings → API Keys.
Connect OpenTelemetry
Add a diagnostics block to your OpenClaw config to export logs and traces to Bronto's OTLP endpoint.
Investigate your agent's activity
Search agent history and explore sessions, token usage, latency, errors and tool calls with BrontoClaw.
%20--%3e%3csvg%20version='1.1'%20id='Layer_1'%20xmlns='http://www.w3.org/2000/svg'%20xmlns:xlink='http://www.w3.org/1999/xlink'%20x='0px'%20y='0px'%20viewBox='0%200%20304%20182'%20style='enable-background:new%200%200%20304%20182;'%20xml:space='preserve'%3e%3cstyle%20type='text/css'%3e%20.st0{fill:%23252F3E;}%20.st1{fill-rule:evenodd;clip-rule:evenodd;fill:%23FF9900;}%20%3c/style%3e%3cg%3e%3cpath%20class='st0'%20d='M86.4,66.4c0,3.7,0.4,6.7,1.1,8.9c0.8,2.2,1.8,4.6,3.2,7.2c0.5,0.8,0.7,1.6,0.7,2.3c0,1-0.6,2-1.9,3l-6.3,4.2%20c-0.9,0.6-1.8,0.9-2.6,0.9c-1,0-2-0.5-3-1.4C76.2,90,75,88.4,74,86.8c-1-1.7-2-3.6-3.1-5.9c-7.8,9.2-17.6,13.8-29.4,13.8%20c-8.4,0-15.1-2.4-20-7.2c-4.9-4.8-7.4-11.2-7.4-19.2c0-8.5,3-15.4,9.1-20.6c6.1-5.2,14.2-7.8,24.5-7.8c3.4,0,6.9,0.3,10.6,0.8%20c3.7,0.5,7.5,1.3,11.5,2.2v-7.3c0-7.6-1.6-12.9-4.7-16c-3.2-3.1-8.6-4.6-16.3-4.6c-3.5,0-7.1,0.4-10.8,1.3c-3.7,0.9-7.3,2-10.8,3.4%20c-1.6,0.7-2.8,1.1-3.5,1.3c-0.7,0.2-1.2,0.3-1.6,0.3c-1.4,0-2.1-1-2.1-3.1v-4.9c0-1.6,0.2-2.8,0.7-3.5c0.5-0.7,1.4-1.4,2.8-2.1%20c3.5-1.8,7.7-3.3,12.6-4.5c4.9-1.3,10.1-1.9,15.6-1.9c11.9,0,20.6,2.7,26.2,8.1c5.5,5.4,8.3,13.6,8.3,24.6V66.4z%20M45.8,81.6%20c3.3,0,6.7-0.6,10.3-1.8c3.6-1.2,6.8-3.4,9.5-6.4c1.6-1.9,2.8-4,3.4-6.4c0.6-2.4,1-5.3,1-8.7v-4.2c-2.9-0.7-6-1.3-9.2-1.7%20c-3.2-0.4-6.3-0.6-9.4-0.6c-6.7,0-11.6,1.3-14.9,4c-3.3,2.7-4.9,6.5-4.9,11.5c0,4.7,1.2,8.2,3.7,10.6%20C37.7,80.4,41.2,81.6,45.8,81.6z%20M126.1,92.4c-1.8,0-3-0.3-3.8-1c-0.8-0.6-1.5-2-2.1-3.9L96.7,10.2c-0.6-2-0.9-3.3-0.9-4%20c0-1.6,0.8-2.5,2.4-2.5h9.8c1.9,0,3.2,0.3,3.9,1c0.8,0.6,1.4,2,2,3.9l16.8,66.2l15.6-66.2c0.5-2,1.1-3.3,1.9-3.9c0.8-0.6,2.2-1,4-1%20h8c1.9,0,3.2,0.3,4,1c0.8,0.6,1.5,2,1.9,3.9l15.8,67l17.3-67c0.6-2,1.3-3.3,2-3.9c0.8-0.6,2.1-1,3.9-1h9.3c1.6,0,2.5,0.8,2.5,2.5%20c0,0.5-0.1,1-0.2,1.6c-0.1,0.6-0.3,1.4-0.7,2.5l-24.1,77.3c-0.6,2-1.3,3.3-2.1,3.9c-0.8,0.6-2.1,1-3.8,1h-8.6c-1.9,0-3.2-0.3-4-1%20c-0.8-0.7-1.5-2-1.9-4L156,23l-15.4,64.4c-0.5,2-1.1,3.3-1.9,4c-0.8,0.7-2.2,1-4,1H126.1z%20M254.6,95.1c-5.2,0-10.4-0.6-15.4-1.8%20c-5-1.2-8.9-2.5-11.5-4c-1.6-0.9-2.7-1.9-3.1-2.8c-0.4-0.9-0.6-1.9-0.6-2.8v-5.1c0-2.1,0.8-3.1,2.3-3.1c0.6,0,1.2,0.1,1.8,0.3%20c0.6,0.2,1.5,0.6,2.5,1c3.4,1.5,7.1,2.7,11,3.5c4,0.8,7.9,1.2,11.9,1.2c6.3,0,11.2-1.1,14.6-3.3c3.4-2.2,5.2-5.4,5.2-9.5%20c0-2.8-0.9-5.1-2.7-7c-1.8-1.9-5.2-3.6-10.1-5.2L246,52c-7.3-2.3-12.7-5.7-16-10.2c-3.3-4.4-5-9.3-5-14.5c0-4.2,0.9-7.9,2.7-11.1%20c1.8-3.2,4.2-6,7.2-8.2c3-2.3,6.4-4,10.4-5.2c4-1.2,8.2-1.7,12.6-1.7c2.2,0,4.5,0.1,6.7,0.4c2.3,0.3,4.4,0.7,6.5,1.1%20c2,0.5,3.9,1,5.7,1.6c1.8,0.6,3.2,1.2,4.2,1.8c1.4,0.8,2.4,1.6,3,2.5c0.6,0.8,0.9,1.9,0.9,3.3v4.7c0,2.1-0.8,3.2-2.3,3.2%20c-0.8,0-2.1-0.4-3.8-1.2c-5.7-2.6-12.1-3.9-19.2-3.9c-5.7,0-10.2,0.9-13.3,2.8c-3.1,1.9-4.7,4.8-4.7,8.9c0,2.8,1,5.2,3,7.1%20c2,1.9,5.7,3.8,11,5.5l14.2,4.5c7.2,2.3,12.4,5.5,15.5,9.6c3.1,4.1,4.6,8.8,4.6,14c0,4.3-0.9,8.2-2.6,11.6%20c-1.8,3.4-4.2,6.4-7.3,8.8c-3.1,2.5-6.8,4.3-11.1,5.6C264.4,94.4,259.7,95.1,254.6,95.1z'/%3e%3cg%3e%3cpath%20class='st1'%20d='M273.5,143.7c-32.9,24.3-80.7,37.2-121.8,37.2c-57.6,0-109.5-21.3-148.7-56.7c-3.1-2.8-0.3-6.6,3.4-4.4%20c42.4,24.6,94.7,39.5,148.8,39.5c36.5,0,76.6-7.6,113.5-23.2C274.2,133.6,278.9,139.7,273.5,143.7z'/%3e%3cpath%20class='st1'%20d='M287.2,128.1c-4.2-5.4-27.8-2.6-38.5-1.3c-3.2,0.4-3.7-2.4-0.8-4.5c18.8-13.2,49.7-9.4,53.3-5%20c3.6,4.5-1,35.4-18.6,50.2c-2.7,2.3-5.3,1.1-4.1-1.9C282.5,155.7,291.4,133.4,287.2,128.1z'/%3e%3c/g%3e%3c/g%3e%3c/svg%3e)
AgentCore Runtime sends telemetry to CloudWatch by default. Instrument your agent with OpenTelemetry, disable the managed pipeline and export OTLP to Bronto through an ADOT Collector or directly from the runtime. Preserve nested GenAI traces with model calls, token usage, tool calls and instrumented prompt and response content.
Instrument your agent
Configure OpenTelemetry trace, metric and log providers inside your AgentCore Runtime, including GenAI instrumentation.
Disable the managed pipeline
Configure AgentCore with --disable-otel and set DISABLE_ADOT_OBSERVABILITY=true so your own exporters control the telemetry.
Choose your export path
Use the recommended ADOT Collector to hold the Bronto credential, or export directly with a credential sourced from AWS Secrets Manager.
Send OTLP to Bronto
Point your agent's exporters at the Collector or Bronto. Preserve nested agent traces, model token usage and tool calls rather than forwarding only CloudWatch logs.
Run models locally with Ollama and bring their server and model logs into Bronto. Ollama does not include a native OpenTelemetry integration; the Collector reads local log files and forwards them to Bronto. Follow the walkthrough to experiment with models and prompts, then investigate token usage, evaluation timing, resource constraints and errors with fast log search.
Run Ollama and choose a model
Install Ollama, start the server with ollama serve and download a model such as gemma:2b with ollama pull.
Capture server and model logs
Redirect Ollama output to local log files. Enable OLLAMA_DEBUG=true for a richer view of model loading, resource usage and requests.
Forward logs with OpenTelemetry
Configure the Collector's filelog receivers for your server and model logs, then export them to Bronto using OTLP HTTP and an ingestion API key.
Search and compare model activity
Send prompts through the Ollama API, then search logs in Bronto for tokens, prompts, errors and evaluation timing to investigate model behavior.
Turn a CDN log investigation into a defined LangGraph workflow. Connect your LLM to Bronto’s MCP server with FastMCP, discover tools and their schemas, then query errors and cache behavior across five graph nodes. Follow the walkthrough to generate query parameters with richer context and carry investigation results forward in graph state.
Set up LangGraph and your LLM
Create a Python virtual environment and install LangGraph, the model integrations and FastMCP. Configure your model API key through the environment.
Connect to Bronto’s MCP server
Use FastMCP’s streamable HTTP client with Bronto’s MCP endpoint and an API key. Retrieve the available tools, descriptions and input schemas.
Build the investigation workflow
Define graph state and five nodes to find CDN datasets, prepare query parameters, search errors, identify cache keys and retrieve cache-rate time series.
Run and refine your log analysis
Compile and invoke the graph. Give the LLM explicit tool context, check generated parameters and reuse datasets and cache keys in state to reduce repeated model calls.
Configure the Bronto MCP Server to collect data from all of your LLM and agentic flows
Retain full fidelity data in Bronto for 12 months with always hot search
Query TBs and PBs of logs and traces in seconds, consistently.
Your assistant queries Bronto over MCP and writes the answer for you.
Our three-part series walks through the Agent2Agent protocol, MCP agents, and how to let multiple agents search across all your data stores.
What the Agent2Agent protocol is, and how agents can discover and delegate search to one another.
Read post
Connect an agent to several data stores through MCP servers, including Bronto's hosted MCP.
Read post
Coordinate specialist agents over A2A so one question can be answered across every data store.
Read post
“The combination of long-term retention, lightning-fast search, and AI-powered insights means we catch issues much earlier, often before customers notice them.”
