Whisper: One Model for Every Voice - Inside openai/whisper
Speech recognition used to mean a stack of specialist components — a voice activity detector, an acoustic model, a pronunciation lexicon, a language model, each with its own failure modes — and Whisper’s central idea is that a single sequence-to-sequence...
Streamlit: The Script That Became an App - Inside streamlit/streamlit
Most web frameworks ask you to learn HTTP. Streamlit asks you to write a Python script. x = st.slider("Select a value") followed by st.write(x, "squared is", x * x) is a complete interactive web app — run streamlit run streamlit_app.py...
Skyvern: LLM Agents That Drive the Browser - Inside skyvern-ai/skyvern
Every Selenium script eventually dies the same death: the website redesigns one button, the XPath goes stale, and the automation that ran for months starts failing on a Tuesday. Skyvern attacks that fragility at the root — instead of hand-written...
Pydantic AI: Typed Agents for Every Model - Inside pydantic/pydantic-ai
Type safety is the oldest promise in the pydantic ecosystem, and Pydantic AI — subtitled simply “How Python does AI” — is that promise carried into the agent era. The README’s pitch is that an agent is a normal Python...
Milvus: Vector Search at Billion Scale - Inside milvus-io/milvus
Every RAG application eventually hits the same wall: the embeddings outgrow Postgres, and the search that was instant at a hundred thousand vectors becomes a pile of scan queries at a hundred million. Milvus is the database built for that...
llama.cpp: LLM Inference on Anything - Inside ggml-org/llama.cpp
There is a particular kind of satisfaction in watching a multi-billion-parameter model generate fluent text on a laptop with no discrete GPU, fully offline, at usable speed. That experience is exactly what ggml-org/llama.cpp ships: LLM and vision-language inference written in...
LanceDB: The Embedded Multimodal Lakehouse - Inside lancedb/lancedb
There is a niche between “my vectors fit in a NumPy array” and “I need a Kubernetes cluster” where most AI applications actually live, and LanceDB is built exactly for it: a serverless vector database that runs embedded in your...
Faster Whisper: The Same Model, Four Times the Speed - Inside SYSTRAN/faster-...
The fastest way to make a model four times faster is often to leave it alone. faster-whisper is SYSTRAN’s reimplementation of OpenAI’s Whisper on CTranslate2, a quantized Transformer inference engine, and the README’s benchmark table makes the case with numbers:...
Chainlit: Python Chat UIs in Minutes - Inside Chainlit/chainlit
The fastest way to demo an LLM is a print loop; the fastest way to ship one is a chat interface people can actually use — with history, streaming, file uploads, authentication, and a thread they can return to. Chainlit...
CAMEL: Finding the Scaling Laws of Agents - Inside camel-ai/camel
There is a question that sounds almost childish until you try to answer it: what happens to agent behavior when you multiply agents the way you multiply model parameters? CAMEL is an open-source community dedicated to finding the scaling laws...
vLLM: PagedAttention and Continuous Batching at Web Scale - Inside vllm-proje...
Most inference libraries treat GPU memory as one more thing for you to manage. vLLM, Apache-2.0-licensed and originally developed in the Sky Computing Lab at UC Berkeley, is the serving engine that made memory management the product: its PagedAttention scheme,...
SGLang: RadixAttention and Cache-Aware Serving - Inside sgl-project/sglang
Serving systems usually rediscover the same insight over and over: most tokens you generate have been generated before. SGLang, Apache-2.0-licensed and hosted by the LMSYS non-profit, turned that insight into its founding idea. The project grew out of the RadixAttention...
Qdrant: A Vector Database Written in Rust - Inside qdrant/qdrant
Embeddings are only half of a semantic search system; the other half is a database that can store billions of them, filter them by arbitrary metadata, and return nearest neighbors in milliseconds under concurrent writes. Qdrant, an Apache-2.0 vector database...
Open WebUI: A Self-Hosted Home for AI - Inside open-webui/open-webui
Run one container and you get a ChatGPT-shaped interface pointed at models you control: that is the promise that made Open WebUI one of the most starred projects on GitHub. The README calls it a home for AI — a...
Mem0: The Memory Layer That Gives Agents Recall - Inside mem0ai/mem0
Every LLM application rediscovers the same problem: the model knows everything about the world and nothing about your user. Context windows help for a turn or two, then the conversation moves on and yesterday’s preferences vanish. Mem0, an Apache-2.0 project...
LiteLLM: One Gateway for a Hundred LLM Providers - Inside BerriAI/litellm
Every team that adopts LLMs hits the same wall within months: a dozen provider SDKs, a dozen auth styles, a dozen error taxonomies, and no idea what any of it costs. LiteLLM, at version 1.106.0 and backed by Y Combinator,...
Letta Code: Agents That Rewrite Their Own Memory - Inside letta-ai/letta-code
Most coding agents wake up with amnesia every session: context is assembled, work is done, and everything learned evaporates when the process exits. Letta Code, from the team behind the MemGPT research paper, attacks that premise directly. Its README describes...
LangGraph: Pregel for Agents - Inside langchain-ai/langgraph
Agent frameworks usually promise simplicity and deliver fragility: the moment a workflow needs retries, approval gates, or state that survives a crash, the happy-path abstraction collapses. LangGraph, MIT-licensed and built by LangChain, starts from the opposite end. The README calls...
Haystack 3: Orchestration for Production RAG and Agents - Inside deepset-ai/h...
Frameworks for LLM applications tend to fail in one of two directions: too much magic, so nothing can be debugged, or too little structure, so every project reinvents plumbing. Haystack, the Apache-2.0 orchestration framework from deepset, has spent years threading...
Chroma: The Embedded Vector Database for AI Apps - Inside chroma-core/chroma
Some databases earn adoption by being effortless, and Chroma is the clearest example in the vector search world. Its README reduces the entire workflow to four functions — create a collection, add documents with metadata, query by text, and get...
VectorCraft: Exact Curve Booleans and 27 ms Renders - Inside storytold/vector...
Vector editors are where precision goes to die. Ask any tool to subtract one blob from another and half the time you get the infamous “cannot perform operation” dialog, a snapped anchor you never moved, or a file that renders...
Semantic Kernel: The Kernel That Ran Enterprise AI Agents - Inside microsoft/...
Before “agent framework” was a product category, Microsoft shipped an SDK with a stranger and better idea: treat the LLM like an operating system kernel. Prompts became functions, your Python methods became plugins, and a single orchestrator scheduled them all....
PhotoCraft: Photoshop Reborn in Pure Rust - Inside storytold/photocraft
Photoshop is the most-cloned application in creative software, and almost every clone has failed the same way: they rebuild the toolbar but not the object model, so layers stop behaving the moment you push past trivial edits. PhotoCraft, from the...
PdfCraft: An Acrobat Rebuilt From ISO 32000 - Inside storytold/pdfcraft
Acrobat is the app everyone uses and almost nobody trusts, because PDF tooling has a history of subscription walls, telemetry, and destructive saves. PdfCraft, part of the ArtCraft family on getartcraft.com, is the clean-room answer: an open-source reimplementation of Acrobat...