langfuse and helicone

Both are open-source LLM observability platforms with overlapping core features (monitoring, evaluation, experimentation), making them direct competitors in the same market rather than complementary tools.

langfuse
95
Verified
helicone
81
Verified
Maintenance 25/25
Adoption 25/25
Maturity 25/25
Community 20/25
Maintenance 20/25
Adoption 16/25
Maturity 25/25
Community 20/25
Stars: 23,106
Forks: 2,333
Downloads: 3,912,905
Commits (30d): 240
Language: TypeScript
License:
Stars: 5,237
Forks: 494
Downloads: 292
Commits (30d): 7
Language: TypeScript
License: Apache-2.0
No risk flags
No risk flags

About langfuse

langfuse/langfuse

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Provides distributed tracing via SDKs (Python, JavaScript/TypeScript) that capture full LLM call chains with automatic context propagation, backed by ClickHouse for scalable analytics. Features a unified API surface for programmatic access to traces, evaluations, and datasets, enabling custom workflows and integration into existing MLOps pipelines alongside LangChain, LlamaIndex, and other frameworks.

About helicone

Helicone/helicone

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

Operates as a reverse proxy AI gateway that intercepts requests to 100+ LLM providers through a unified OpenAI-compatible API, enabling intelligent routing and automatic fallbacks. Built on a microservices architecture with a Cloudflare Workers proxy layer for request interception, Express-based collection server (Jawn), ClickHouse for analytics, and Supabase for application data. Integrates with OpenAI, Anthropic, Gemini, LangChain, Vercel AI SDK, and supports self-hosting via Docker or Helm with optional async logging through OpenLLMetry.

Scores updated daily from GitHub, PyPI, and npm data. How scores work