NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #3022 most downloaded on PyPI
DEPRECATED: LangChain integration is now included in the main braintrust package. Install braintrust instead.
Last release 6 months ago
01 Apr 2026
Release timing varies
gaps range from 9 days to 5 months
Most releases are documented
notes for 9 of 14 stable releases
Nothing withdrawn
no release was ever pulled
2 years old
14 releases · first in 2025
Added OpenTelemetry compatibility mode for seamless integration between Braintrust and OTEL tracing
Added OpenTelemetry compatibility mode for seamless integration between Braintrust and OTEL tracing
Added setup_claude_agent_sdk for automatic tracing of Claude Agent SDK applications
Improved Anthropic wrapper to log consistent input/output format
Added strict parameter to Prompt.build for strict schema validation
Added SpanComponentsV4 support
Fix langchain-py integration tracing when users use a @traced method
Fix langchain-py integration tracing when users use a @traced method
Wrap OpenAI responses.parse
Add @traced support for generator functions
Autoevals PY (version 0.0.130)
One column per month.
When running multiple trials per input ( trial_count > 1 ), you can now access the current trial index (0-based) via hooks.trialIndex in your task fun
When running multiple trials per input ( trial_count > 1 ), you can now access the current trial index (0-based) via hooks.trialIndex in your task function
Added BraintrustExporter in addition to BraintrustSpanProcessor
Bound max ancestors in git to 1,000
The SDK’s under-the-hood log queue will not block when full and has a default size of 25000 logs
The SDK’s under-the-hood log queue will not block when full and has a default size of 25000 logs
You can configure the max size by setting BRAINTRUST_LOG_QUEUE_MAX_SIZE in your environment
Improvements to the logging of parallel tool calls
Attachments are now converted to base64 data URLs, making it easier to work with image attachments in prompts
Add project.publish() to directly push prompts to Braintrust (without running braintrust push )
Add project.publish() to directly push prompts to Braintrust (without running braintrust push )
@traced now works correctly with async generator functions
The OpenAI and Anthropic wrappers set provider metadata
Improve retry logic in the control plane connection (used to create new experiments and datasets)
Added support for metadata and tags arguments to invoke
Added support for metadata and tags arguments to invoke
The SDK now gracefully handles OpenAI’s NotGiven parameter
Added span.link() to synchronously generate permalinks
Added BraintrustSpanProcessor to simplify integration with OpenTelemetry
Fix a bug where large experiments would drop spans if they could not flush data fast enough
Fix a bug where large experiments would drop spans if they could not flush data fast enough
Fix bug in attachment uploading in evals executed with npx braintrust eval
Upgrading zod dependency from ^3.22.4 to ^3.25.3
Added support for loading prompts by ID via the loadPrompt function
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Your coding agent can read these notes before it upgrades. Set up the MCP server →