Starred repositories
An example principled agentic workflow implementing a wordle clone in golang
Get [Google, Yandex, Baidu, Bing, DuckDuckGo] search results via API for free 🎉
Faster Whisper transcription with CTranslate2
High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, …
Adala: Autonomous DAta (Labeling) Agent framework
A linter for scientific manuscripts
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no c…
CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
Free, open-source web app for learning about ontologies and Microsoft Fabric IQ. Explore a catalogue of pre-built ontologies, design your own visually, export as RDF/XML, and share interactive diag…
Specification and documentation for Agent Skills
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
Clusterscope is a CLI and python library to extract information from HPC Clusters and Jobs.
This is a comprehensive guide that offers advice for how to build a machine learning cluster for researchers at different scales
Profile-guided GPU kernel optimizer for AMD/RDNA3. Auto-tunes llama.cpp MMVQ kernels per model shape. 2x decode speedup on 7900 XTX.
Spends CPU cycles so you don't spend tokens. The LLM gets a briefing packet instead of a flashlight in a dark room.
Website of the find.software project
A small command line tool to convert audio or video to text.
A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
A modern Go framework for building multi-agent AI systems.
🐈 A collection of LLM inference providers and models
LoRA weights for Cerebras-GPT-2.7b finetuned on Alpaca dataset with shorter prompt