Braintrust
AI observability platform for agents: trace production, run evals and catch regressions before users see them.
Tags
Description
Braintrust's SDKs are open source (e.g. braintrust-sdk-javascript Apache-2.0, braintrust-go Apache-2.0, braintrust-proxy MIT); the license of the hosted platform itself is not stated in these repos.
Agent access
Related
- Braintrust MCP: Remote Braintrust MCP server for Claude Code, Cursor, Codex and other clients to query logs and work with Braintrust data.
Guides & comparisons
- Evaluate an AI agent with open-source eval and observability tools (Guide): A hands-on loop for agent quality: instrument with OpenTelemetry, collect traces, turn real traces into a dataset, write code, LLM-as-judge and human evaluators, run offline experiments, then monitor production and gate pull requests in CI.
- Observability and eval platforms for AI agents (Comparison): Langfuse, LangSmith, Arize Phoenix, Braintrust, Opik and Laminar compared on license, self-hosting, OpenTelemetry ingestion, MCP access to your traces, free tiers, paid entry prices and built-in evaluation.
Sources
- https://www.braintrust.dev
- https://docs.braintrust.dev/llms.txt
- https://github.com/braintrustdata/autoevals
- https://github.com/braintrustdata/braintrust-sdk-javascript
- https://github.com/braintrustdata/braintrust-proxy
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)