helicone

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

View on GitHub↗Upstream Helicone/helicone↗

Builder

Helicone

Helicone • individual

Stars

5,444

Using upstream star count

Forks

504

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Jan 31, 2023

Project creation date

README Summary

Helicone is an open-source LLM observability platform that provides comprehensive monitoring, evaluation, and experimentation capabilities for large language models. It offers one-line integration to track LLM usage, costs, latency, and performance metrics with support for major providers like OpenAI, Anthropic, and others. The platform includes features like prompt management, A/B testing, custom evaluations, and detailed analytics dashboards.

AI Dev Skills

Unmapped

LLM Operations (LLMOps)AI Model MonitoringLLM Performance AnalyticsAPI Gateway ManagementPrompt Engineering EvaluationAI Cost OptimizationModel Response CachingA/B Testing for AI Models

Tags

LLM Operations (LLMOps)AI Model MonitoringLLM Performance AnalyticsAPI Gateway ManagementPrompt Engineering EvaluationAI Cost OptimizationModel Response CachingA/B Testing for AI ModelsLLM Response CachingMLOps for Large Language ModelsPrompt Optimization and TestingAI SafetyLLMOpsAI ObservabilitySelf-hostedAI Model Performance TrackingMulti-provider LLM ManagementDeveloper ToolsCompound AI SystemsLLM Application MonitoringOn-premiseAI InfrastructureTextCost Analysis for AI OperationsAI Experiment ManagementCloud APITypeScript

Recent Activity

Updated 27 days ago

7 Days

30 Days

90 Days

Quality

production

Quality: high
Maturity: production

PM Skills

Scale & ReliabilityDeveloper Platform

Languages

TypeScript100.0%

Timeline

Project created: Jan 31, 2023
Forked: Mar 13, 2026
Your last push: 27 days ago
Upstream last push: 7 days ago
Tracked since: Mar 17, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…