Vibe Coding Discoverhelicone
View on GitHub🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
Helicone is an open source LLM observability platform and AI gateway. One line of code logs OpenAI, Anthropic, LangChain and other provider calls for tracing, cost/latency analytics, prompt management and evaluation. Self-hostable via Docker with ClickHouse and Supabase.
Use Cases
Monitor and debug LLM request tracesTrack token cost and latency per providerRoute requests across 100+ models with one API keyAutomatic fallback between providersVersion and deploy prompts without code changesEvaluate and experiment on prompts from production dataExport LLM analytics to PostHog dashboardsTrace agent and chatbot sessionsSelf-host an LLM observability stack via DockerDataset curation and fine-tuning workflows
Built With
- Language
- TypeScript
- Frameworks
- Next.js · LangChain · LlamaIndex · LangGraph · Vercel AI SDK · Cloudflare Workers · Express · Supabase · ClickHouse · Docker · Helm · OpenLLMetry
Tags
llm-observability · ai-gateway · llmops · monitoring · evaluation · tracing · cost-tracking · prompt-management · playground · analytics · logging · routing · fallbacks · self-hosted · clickhouse · openai-compatible