Sign in Submit site

opensource

github.com/Helicone/helicone AI Infrastructure & MLOps Open-source projectOpen source

Helicone provides open-source observability for LLM applications, with tools to monitor, evaluate, and experiment.

Visit opensource 24 alternatives
github.com/Helicone/helicone
opensource homepage screenshot

About opensource

Helicone is an open-source LLM observability platform and AI gateway for AI engineers. Its one-line integration logs requests from providers such as OpenAI, Anthropic, LangChain, Gemini, and the Vercel AI SDK. It can inspect traces and sessions for agents, chatbots, and document processing pipelines, and it tracks metrics such as cost, latency, and quality.

The homepage also describes a playground for testing prompts, prompt versioning, and a gateway that routes requests to 100+ models through one API key with automatic fallbacks. Self-hosting is supported with Docker, and a Helm chart is described for enterprise workloads. The homepage states a free tier of 10,000 requests per month with no credit card required, but this is not confirmed as current, and pricing is listed as unknown. Using the hosted gateway routes requests through Helicone's infrastructure. The homepage describes SOC 2 and GDPR compliance, which this entry has not verified.

Key features

  • One-line integration to log requests from OpenAI, Anthropic, LangChain, Gemini, and Vercel AI SDK
  • AI gateway routing 100+ models through one API key, with automatic fallbacks
  • Inspection of traces and sessions for agents, chatbots, and document pipelines
  • Tracking of cost, latency, and quality metrics, with export to PostHog
  • Playground for testing and iterating on prompts, sessions, and traces
  • Prompt versioning using production data, deployable through the gateway
Best for: AI engineers building LLM applications who want open-source observability and can either self-host or use the hosted AI gateway.
Good for
  • Source code is publicly available in a GitHub repository under an open-source license.
  • Integration is described as a single line of code added to existing OpenAI-style client setups.
  • Self-hosting is supported through a Docker Compose setup.
Watch out for
  • The repository states that manual deployment is not recommended; Docker or Helm is preferred.
  • The Helm chart for enterprise workloads requires contacting the company by email.
  • Fine-tuning is listed only with two named partners, OpenPipe and Autonomi, with more described as coming soon.

opensource at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026
open sourceai infrastructurelanguage modelsprompt engineering

opensource alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Infrastructure & MLOps

Well-known listings from the same topic.

All 341
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioKili Technologykili-technology.comAPI docsdocs.x.aiEyePop.aieyepop.ai
Related topicsAI Business ToolsAI Image GeneratorsAI Agents & AutomationAI Data & AnalyticsAI Chatbots & AssistantsAI Voice & AudioAI Writing ToolsAI Video Generators

opensource FAQ

How do I start using the hosted AI gateway?
Sign up to get an API key, add credits at helicone.ai/credits, set the baseURL in your code to https://ai-gateway.helicone.ai, and use your API key. The homepage says logs can then be viewed in Helicone.
How can I self-host Helicone?
Clone the GitHub repository, copy the .env.example file to .env in the docker directory, and start the services with the helicone-compose.sh script. The homepage describes Docker as the simplest option.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing

Listing maintained by Chris McClure and the WebIndexly editors · Updated Oct 12, 2026 · How we rank