Sourcegraph | San Francisco | Full-Time | SWE, Design Engineer, Forward Deployed Eng, Head of Design, Solutions Eng, Dev Advocate (all roles write code) | https://sourcegraph.com Sourcegraph is hiring SWEs and FDEs for Amp (https://ampcode.com), the most aggressive and powerful AI coding agent. It's growing 50% WoW, and we build it in a crazy way; see https://ampcode.com/how-we-build. Backed by Sequoia, a16z,... - Source: Hacker News / 12 months ago

This is a product by Sourcegraph https://sourcegraph.com who already have a solution in this space. Is this something wildly different to Cody, your existing solution, or just a "subtle" attempt to gain more customers? - Source: Hacker News / about 1 year ago

Sourcegraph | San Francisco / Remote | Full-Time | SWE, Database Platform Eng, Forward Deployed Eng, Solutions Eng, Dev Advocate (all roles write code) | https://sourcegraph.com Sourcegraph is how enterprises industrialize software development with AI. We accelerate and automate how software is built in the world's most important companies, including 7/10 top software companies by market cap and 4/6 top US banks.... - Source: Hacker News / over 1 year ago

Cody by Sourcegraph can transform how you build UI components, from basic buttons to complex, dynamic systems. It handles the heavy lifting so you can focus on crafting good UI/UX designs. Whether you’re customising components or managing complex UI systems, Cody provides the tools to make the process faster and more efficient. - Source: dev.to / over 1 year ago

URL: https://sourcegraph.com What it does: A universal code search tool for navigating large codebases. Why it's great: Quickly locate what you need in vast repositories — ideal for collaboration! - Source: dev.to / over 1 year ago

Helicone takes the simplest possible approach to LLM monitoring: it's a proxy. Change your OpenAI base URL from api.openai.com to oai.helicone.ai, add your Helicone API key as a header, and every LLM request is logged — latency, tokens, cost, prompts, and completions. No SDK integration, no code changes beyond a URL swap. - Source: dev.to / about 1 month ago

You're monitoring production traffic. You need Langfuse / Phoenix / Helicone / Braintrust for that. Online eval is a different problem class: implicit feedback, drift detection, hallucination rates on your data, not on HellaSwag. - Source: dev.to / about 2 months ago

For many teams, especially those starting out or with simpler needs, commercial solutions like Portkey, Helicone, OpenPipe, or LiteLLM Proxy offer off-the-shelf capabilities that cover many common proxy use cases (caching, logging, cost tracking). NeuroLink itself can be seen as an SDK that complements these, allowing you to integrate with them or build similar features on top. - Source: dev.to / 3 months ago

TL;DR: Go with Langfuse if you want open-source and self-hosted. Pick Helicone if you want the fastest setup (2 minutes, no SDK). Stick with LangSmith if your stack already runs on LangChain. And if your org already pays for Datadog, their LLM module slots right in. - Source: dev.to / 4 months ago

Hey HN, we're Justin and Cole, the founders of Helicone (https://helicone.ai) or self-deploy with our new fully open-source helm chart (https://helicone.ai/selfhost). Yet even with detailed traces, probabilistic systems are notoriously hard to debug at scale. So, we released evaluators (either via LLM-as-judge or custom Python evaluators leveraging the CodeSandbox SDK - https://codesandbox.io/docs/sdk/sandboxes).... - Source: Hacker News / over 1 year ago