Braintrust
Eval-first LLM platform — datasets, eval runs, prompt playground, tracing. Founded by ex-Impira (acquired by Dropbox) team. Used by Notion, Brex, AirOps.
Active · Verified 2026-10-27 · fresh as of 2026-10-27 · 44 cited facts, 0 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Eval + observability for AI vendor fix
- Tier
- T1
- Latest release
- v0.48.1 (2026-10-26) — braintrust Python SDK registry fix
- License
- proprietary; SDKs open source registry fix
- GitHub
- searched not found vendor fix
- Pricing
- Starter $0/mo; Pro $249/mo; Enterprise custom vendor fix
- Funding
- $36M Series A 2024-04 (a16z led; $150M valuation). vendor fix
- Freshness
- 2026-10-27 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial registry fix
- SDK languages
- csharp, go, java, python, ruby, typescript vendor fix
- Protocols
- mcp-server, opentelemetry vendor fix
- Compliance
- gdpr, hipaa, soc2-type2 vendor fix
When to use
Optimised for: searched not found
Anti-fit: searched not found
Pros & cons
Pros
searched not found
Cons
searched not found
Claims & capabilities
$36M Series A 2024 (a16z led).
Technical surface
- API surface
- Python SDK, TypeScript SDK, bt CLI
- Backend storage
- not applicable — not a memory product
- Deployment
- Both (self-hosted + managed cloud) — hosted SaaS; on-prem deployment on Enterprise
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- searched not found
- MCP
- yes — Braintrust MCP server (Connect with MCP quickstart)
- A2A
- searched not found
- OpenTelemetry
- searched not found
Compare Braintrust with…
Similar systems
Other evaluation & observability platforms in the catalog, ranked by inbound references.
- Arize Phoenix T1
Arize AI's open-source LLM observability tool — OpenTelemetry-native LLM tracing, evals, datasets. Arize commercial offers Phoenix + Surveyor.
- Arize AI T1
Production ML monitoring + LLM observability (Arize AX) — drift, eval, root-cause. Pre-LLM observability leader; now LLM-pivoted.
- Confident AI / DeepEval T2
Open-source DeepEval framework + Confident AI cloud — pytest-style eval runs, hallucination/relevance/bias metrics, datasets.
- OpenLLMetry (Traceloop) T2
Traceloop's open-source OpenTelemetry auto-instrumentation for LLM workflows — works with any OTel-compatible backend (Datadog, New Relic, Grafana, etc.).
- Helicone T2
Open-source LLM observability and AI gateway — one-line proxy integration captures every LLM call; sessions, custom properties, evals. Acquired by Mintlify in Mar 2026 and placed in maintenance mode; helicone.ai now states it is no longer part of Mintlify.
- Ragas T2
Open-source eval framework for RAG pipelines — faithfulness, answer-relevance, context-precision, context-recall. Widely used as a baseline RAG eval kit.
Sources (43 cited facts, 0 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Eval + observability for AI vendor
- What it does & what's distinct Eval-first LLM platform — datasets, eval runs, prompt playground, tracing. Founded by ex… vendor
- Claims / benefits $36M Series A 2024 (a16z led). vendor
- Created 2023 vendor
- Latest release v0.48.1 (2026-10-26) — braintrust Python SDK registry
- License proprietary; SDKs open source registry
- Funding $36M Series A 2024-04 (a16z led; $150M valuation). vendor
- Customers / scale Notion, Vercel, Stripe, Airtable, Zapier, Brex; LLM eval / prompt engineering platform. vendor
- Pricing Starter $0/mo; Pro $249/mo; Enterprise custom vendor
- Deployment Both (self-hosted + managed cloud) — hosted SaaS; on-prem deployment on Enterprise vendor
- HQ US (SF) vendor
- Founders / pedigree Ankur Goyal (CEO; ex-Impira CEO, MemSQL); founded 2023. vendor
- API surface Python SDK, TypeScript SDK, bt CLI vendor
- MCP support yes — Braintrust MCP server (Connect with MCP quickstart) vendor
- obs-langsmith no vendor
- obs-opentelemetry yes vendor
- obs-datadog no vendor
- obs-helicone no vendor
- obs-weave no vendor
- obs-langfuse no vendor
- obs-arize no vendor
- obs-custom Braintrust IS an evaluation+observability platform; OTLP ingest endpoint exposed vendor
- cost-token-budget no vendor
- cost-prompt-caching no vendor
- cost-semantic-caching no vendor
- cost-batching no vendor
- cost-model-routing no vendor
- cost-streaming-only no vendor
- cost-observability-cost-attribution yes vendor
- eval-langsmith-evals no vendor
- eval-braintrust yes vendor
- eval-weights-and-biases-agent no vendor
- eval-helicone-evals no vendor
- eval-custom-test-harness yes vendor
- eval-human-loop yes vendor
- eval-production-traffic-replay yes vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial registry
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- compliance-certifications gdpr,hipaa,soc2-type2 vendor
- sdk-languages csharp,go,java,python,ruby,typescript vendor
- protocol-support mcp-server,opentelemetry vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-27
- License first recorded as “proprietary; SDKs open source” source
- Latest release first recorded as “v0.48.1 (2026-10-26) — braintrust Python SDK” source
- Pricing first recorded as “Starter $0/mo; Pro $249/mo; Enterprise custom” source
- Deployment first recorded as “Both (self-hosted + managed cloud) — hosted SaaS; on-prem deployment on Enterprise” source
- MCP support first recorded as “yes — Braintrust MCP server (Connect with MCP quickstart)” source
Related systems
References (42)
- Agent2Agent Protocol (A2A) integrates with — Braintrust docs have a Agent2Agent Protocol (A2A) integration page. (verified 2026-10-29)
- Anthropic Claude (foundation models) integrates with — Braintrust docs have a Anthropic Claude (foundation models) integration page. (verified 2026-10-29)
- AutoGen / AG2 integrates with — Braintrust docs have a AutoGen / AG2 integration page. (verified 2026-10-29)
- Baseten integrates with — Braintrust docs have a Baseten integration page. (verified 2026-10-29)
- Claude Agent SDK integrates with — Braintrust docs have a Claude Agent SDK integration page. (verified 2026-10-29)
- Claude Code (Anthropic) integrates with — Braintrust docs have a Claude Code (Anthropic) integration page. (verified 2026-10-29)
- Cohere Command R+ / Command A integrates with — Braintrust docs have a Cohere Command R+ / Command A integration page. (verified 2026-10-29)
- CrewAI integrates with — Braintrust docs have a CrewAI integration page. (verified 2026-10-29)
- Cursor (IDE) integrates with — Braintrust docs have a Cursor (IDE) integration page. (verified 2026-10-29)
- DSPy integrates with — Braintrust docs have a DSPy integration page. (verified 2026-10-29)
- ElevenLabs Conversational AI (now ElevenAgents) integrates with — Braintrust docs have a ElevenLabs Conversational AI integration page. (verified 2026-10-29)
- Fireworks AI integrates with — Braintrust docs have a Fireworks AI integration page. (verified 2026-10-29)
- Genkit integrates with — Braintrust docs have a Genkit integration page. (verified 2026-10-29)
- Google Agent Development Kit (ADK) integrates with — Braintrust docs have a Google Agent Development Kit (ADK) integration page. (verified 2026-10-29)
- Google Gemini 3 family integrates with — Braintrust docs have a Google Gemini 3 family integration page. (verified 2026-10-29)
- LangChain (framework) integrates with — Braintrust docs have a LangChain (framework) integration page. (verified 2026-10-29)
- LangGraph (orchestration) integrates with — Braintrust docs have a LangGraph (orchestration) integration page. (verified 2026-10-29)
- LangSmith integrates with — Braintrust docs have a LangSmith integration page. (verified 2026-10-29)
- LiteLLM integrates with — Braintrust docs have a LiteLLM integration page. (verified 2026-10-29)
- LiveKit Agents integrates with — Braintrust docs have a LiveKit Agents integration page. (verified 2026-10-29)
- LlamaIndex (framework) integrates with — Braintrust docs have a LlamaIndex (framework) integration page. (verified 2026-10-29)
- Mastra integrates with — Braintrust docs have a Mastra integration page. (verified 2026-10-29)
- Microsoft Agent Framework integrates with — Braintrust docs have a Microsoft Agent Framework integration page. (verified 2026-10-29)
- Mistral Large 2 / Mixtral family integrates with — Braintrust docs have a Mistral Large 2 / Mixtral family integration page. (verified 2026-10-29)
- Model Context Protocol (MCP spec) integrates with — Braintrust docs have a Model Context Protocol (MCP spec) integration page. (verified 2026-10-29)
- OpenAI Agents SDK integrates with — Braintrust docs have a OpenAI Agents SDK integration page. (verified 2026-10-29)
- OpenAI Codex CLI integrates with — Braintrust docs have a OpenAI Codex CLI integration page. (verified 2026-10-29)
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integrates with — Braintrust docs have a OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integration page. (verified 2026-10-29)
- Opencode (SST) integrates with — Braintrust docs have a Opencode (SST) integration page. (verified 2026-10-29)
- OpenLLMetry (Traceloop) integrates with — Braintrust docs have a OpenLLMetry (Traceloop) integration page. (verified 2026-10-29)
- OpenRouter integrates with — Braintrust docs have a OpenRouter integration page. (verified 2026-10-29)
- Phidata (now Agno) integrates with — Braintrust docs have a Phidata integration page. (verified 2026-10-29)
- Pipecat (Daily) integrates with — Braintrust docs have a Pipecat (Daily) integration page. (verified 2026-10-29)
- Pydantic-AI integrates with — Braintrust docs have a Pydantic-AI integration page. (verified 2026-10-29)
- Replicate integrates with — Braintrust docs have a Replicate integration page. (verified 2026-10-29)
- Spring AI ChatMemory integrates with — Braintrust docs have a Spring AI ChatMemory integration page. (verified 2026-10-29)
- Strands Agents (AWS) integrates with — Braintrust docs have a Strands Agents (AWS) integration page. (verified 2026-10-29)
- Temporal integrates with — Braintrust docs have a Temporal integration page. (verified 2026-10-29)
- Together AI integrates with — Braintrust docs have a Together AI integration page. (verified 2026-10-29)
- Voyage AI (MongoDB) integrates with — Braintrust docs have a Voyage AI (MongoDB) integration page. (verified 2026-10-29)
- Windsurf (now Devin Desktop) integrates with — Braintrust docs have a Windsurf integration page. (verified 2026-10-29)
- xAI Grok 4 integrates with — Braintrust docs have a xAI Grok 4 integration page. (verified 2026-10-29)
Referenced by (12)
- agentgateway integrates with — agentgateway integrations docs have a Braintrust observability page. (verified 2026-10-29)
- Browserbase integrates with — Browserbase docs have a Braintrust integration page. (verified 2026-10-29)
- Chroma integrates with — Chroma's docs have a Braintrust integration page. (verified 2026-10-29)
- CrewAI integrates with — CrewAI docs have a Braintrust observability integration page. (verified 2026-10-29)
- LiteLLM integrates with — LiteLLM docs have a Braintrust logging/observability integration page. (verified 2026-10-29)
- Mastra integrates with — Mastra repo ships the @mastra/braintrust observability exporter. (verified 2026-10-29)
- OpenAI Agents SDK integrates with — OpenAI Agents SDK tracing docs list Braintrust under external tracing processors. (verified 2026-10-29)
- OpenLLMetry (Traceloop) integrates with — OpenLLMetry docs have a page on exporting traces to Braintrust. (verified 2026-10-29)
- OpenRouter integrates with — OpenRouter Broadcast docs have a page for sending request traces to Braintrust. (verified 2026-10-29)
- Temporal integrates with — Temporal integrations catalog lists Braintrust agent-observability integration (Go, Python, TypeScript). (verified 2026-10-29)
- TrueFoundry AI Gateway integrates with — TrueFoundry AI Gateway ecosystem lists a Braintrust integration page. (verified 2026-10-29)
- Vercel AI SDK integrates with — AI SDK docs have a Braintrust observability integration page. (verified 2026-10-29)