StartupSan Francisco, CA · Est. 2022 · Y Combinator
Helicone
Open-source LLM observability and AI gateway.
Helicone is an open-source LLM observability platform — logging, caching, rate limits and evals behind a one-line proxy — with an AI gateway for routing and cost control. A YC company that became the self-hostable counterweight to LangSmith.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- User reportsWorks as a language-agnostic proxy, which a Go team valued over Python-first observability SDKs.[1]
- MetadataApache-2.0 with the platform in the open repo (about 6.2k stars), so it can be self-hosted.[1]
- User reportsIts public LLM cost table is a popular reference; one user picked it because it updates quickly when models are released.[1][2]
Cons
- DocsMintlify acquired Helicone in March 2026, and it now runs in maintenance mode: security updates, bug fixes and new models only.[1][2]
- User reportsOne user found almost no docs on self-hosting, and their self-hosted instance kept redirecting to Helicone's website to log in.[1]
- User reportsOne comparison found that seeing what made a single run expensive means labelling your calls and writing your own SQL.[1]
- User reportsAnother user felt its price data lagged behind new releases and now combines it with other sources.[1]
- Best for
- Teams already on Helicone that want a stable logging and cost proxy while they plan their next move.
- Watch out for
- New features are no longer planned under Mintlify, so new adopters should treat it as legacy.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Co-founder
Evals & benchmarks
Co-founder & CEO
Evals & benchmarks
Activity
- Latest release
- v2025.08.21-1
· 1y ago - Last 90 days
- 0 releases
- · 1y ago
- · 1y ago
- · 1y ago
v1.0.0v1.0.0 Docker image release
· 1y ago
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
On X
No posts from them in our X feed yet.
Neighbours in the directory
San Francisco, CA · Est. 2022
The de-facto standard toolkit for building LLM applications and agents.
LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.
~$75M raised
New York, NY · Est. 2021
Serverless cloud built for AI and agentic compute.
Modal lets teams run inference, fine-tuning and arbitrary agent workloads as serverless Python without managing infrastructure — a common substrate for harness backends at scale.
Seattle, WA · Est. 2019
Durable execution for long-running agent workflows.
Temporal's durable execution engine is widely adopted to make agent pipelines reliable: state survives crashes, retries are automatic, and workflows run for minutes or months. A key piece of serious harness infrastructure.
$430M total · $300M Series D (Feb 2026) at $5B valuation
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Similar entries · 1
- BerriAI (LiteLLM)Startup