nowfound

AI · February 6, 2024

Graphlit

API for LLM enabled knowledge ingestion and retrieval

What it does

Graphlit simplifies the development of intelligent AI apps and services. Compared to LangChain or LlamaIndex, which require the DIY combo of vector dbs, parsers and data pipelines, our managed platform lets you focus on building your app - not your AI infra.

Does the same job

all alternatives →
  • OpenLIT 2.02025 · ▲141

    Open source dashboard for AI engineering & LLM data

  • AskCodiNov 2025 · ▲230

    Custom LLMs, without training. Use via openai compatible api

  • Moonlit Platform2025 · ▲106

    Content workflow builder for SEOs and content teams

  • Astra AI2024 · ▲142

    Universal API for adding any app to your LLM

  • liteLLM2023 · ▲120

    One library to standardize all LLM APIs

  • n8n LangChain integration2023 · ▲202

    Build LLM apps and plug AI into your team's operations

More ai this month

the category →
  • I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

    AI · 16d ago · simedw.com

  • Astute585

    Automate your B2B brand going viral, with new media creators

    AI · 18d ago · company-app.joinastute.com

  • Grok Bot547

    AI teammates that you can give real work to

    AI · 25d ago · x.ai

  • Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

    AI · 26d ago · cactuscompute.com

  • Make your software self-driving

    AI · 30d ago · coldtea.ai

  • Soloop472

    Approval-first Agent OS for solo founders

    AI · 30d ago · soloop.io

Launched alongside, February 2024

the whole month →
  • Flipner AI1,629

    Capture your ideas & craft texts with AI's touch

    AI · 2024 · flipner.webflow.io

  • Typeframes1,307

    Video creation for makers

    Work · 2024 · revid.ai

  • Superlist1,254

    Home to all your lists

    Work · 2024 · superlist.com

  • Never run out of marketing ideas ever again

    Growth · 2024 · marketingideas.com

  • Layers1,201

    A home for designers

    Work · 2024 · layers.to

  • Heyday1,178

    AI copilot for your own research, notes & conversations

    AI · 2024 · heyday.xyz