HN Explorer

ij23

↗ HN profile [ 118 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. Show HN: LiteHarness – One SDK for Claude Agent, OpenAI Agent, Pi AI (github.com)

    We built this library because agent harnesses were too fragmented and we needed a simple abstraction to call multiple coding-agent SDKs. lite-harness has one function - query() import { query } from "@lite-harness/sdk";…

    2 points 3
  3. LiteLLM Agent Platform: Run Claude Code/Codex On-Prem Sandboxes and Vaults (github.com)
    3 points 2
  4. LiteLLM (YC W23): Founding Reliability Engineer – $200K-$270K and 0.5-1.0% equity (ycombinator.com)
    1 points 0 job
  5. Open-Swarm – use 100 LLMs on OpenAI swarm framework (github.com)
    2 points 1
  6. FastRepl – open-source evals for RAG, Agents (github.com)
    3 points 0
  7. React Library to Build Dashboards (tremor.so)
    1 points 0
  8. Open Interpreter: Code Interpreter in your terminal, running locally(100 LLMs) (github.com)
    4 points 0
  9. EvaDB – SQL Queries Using Hugging Face, Open AI, Ultralytics, PyTorch (github.com)
    6 points 1
  10. 1 points 0
  11. Show HN: LiteLLM - Open source library A/B test LLMs in Production (litellm.vercel.app)

    Hello Hacker News, Stop relying on benchmarks and easily test LLMs in production. Try it here: https://admin.litellm.ai/ LiteLLM allows you to simplify calling any LLM as a drop in replacement for gpt-3.5-turbo We're…

    2 points 0
  12. 1 points 0
  13. 1 points 0
  14. 1 points 0
  15. Llama2 on Replicate faster than ChatGPT? (github.com)
    1 points 2
  16. Show HN: liteLLM Proxy Server: 50+ LLM Models, Error Handling, Caching (github.com)

    Hello hacker news, I’m the maintainer of liteLLM() - package to simplify input/output to OpenAI, Azure, Cohere, Anthropic, Hugging face API Endpoints: https://github.com/BerriAI/litellm/ We’re open sourcing our…

    140 points 35
  17. Show HN: LiteLLM -Open-Source Library for Anthropic,Azure,OpenAI, etc. API Calls (litellm.ai)

    Needed a simple way to call multiple LLM providers. LiteLLM provides 2 functions - `completion` and `embedding`; and guarantees consistent input/output formats across all providers. That's it!

    5 points 1
  18. Show HN: Litellm – Simple library to standardize OpenAI, Cohere, Azure LLM I/O (github.com)

    I built this library because langchain was too bloated and I needed a simple abstraction to call multiple LLM APIs. litellm has two functions - completion(), embedding()

    62 points 18
  19. Show HN: ReliableKeys – Set Spend Limits on OpenAI Keys (reliablegpt.dev)
    3 points 0
  20. 1 points 0
  21. 1 points 0
  22. 1 points 0
  23. Show HN: ReliableGPT run 200 GPT-4 requests in parallel (colab.research.google.com)

    reliableGPT handles GPT-4 429 rate limit errors it optimally allocate jobs for incoming requests to maximize usage of Requests/min and Token/min limits

    14 points 3
  24. Show HN: ReliableGPT – error handling library for 100% GPT uptime (github.com)
    2 points 0
  25. Show HN: BerriAI – Monitor Hallucinations in LLMs (Sentry for LLM Apps) (logs.berri.ai)

    Hi HN - Ishaan and Krrish here from BerriAI. We’ve built a hallucination monitoring tool for LLM Apps in production, that can instantly identify language mistranslations (responding to a user in the incorrect language)…

    4 points 0