Misha Brukman's repositories
AnimateLCM
AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning
bluesky-social-app
The Bluesky Social application for Web, iOS, and Android
continue
⏩ Continue is an open-source autopilot for VS Code and JetBrains—the easiest way to code with any LLM
danielmiessler-fabric
fabric is an open-source framework for augmenting humans using AI.
DeepSeek-Coder
DeepSeek Coder: Let the Code Write Itself
figma_clone
Figma Clone using Next.js, Fabric.js and Liveblocks in TypeScript
GCP-localllm
Run LLMs on Google Cloud Workstations.
gitbutler
The GitButler version control client, backed by Git, powered by Tauri/Rust/Svelte
hurl
Hurl: run and test HTTP requests with plain text.
immich
Self-hosted photo and video backup solution directly from your mobile phone.
indexify
A scalable realtime and continuous indexing engine for Unstructured Data to build Generative AI Applications
InstantID
InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥
LLM-Finetuning
LLM Finetuning with peft
llrt
LLRT (Low Latency Runtime) is an experimental, lightweight JavaScript runtime designed to address the growing demand for fast and efficient Serverless applications.
Lumos
A RAG LLM co-pilot for browsing the web, powered by local LLMs
mame
MAME
mui-x
MUI X: Build complex and data-rich applications using a growing list of advanced React components, like the Data Grid, Date and Time Pickers, Charts, and more!
OLMo
Modeling, training, eval, and inference code for OLMo
oohtml
Object-Oriented HTML. project
phidata
Build AI Assistants using function calling
pkl
A configuration as code language with rich validation and tooling.
renovate
Universal dependency automation tool.
ROCm
AMD ROCm™ Software
skiff-apps
Privacy-first, end-to-end encrypted Mail, Pages, Drive, and Calendar.
toolong
A terminal application to view, tail, merge, and search log files (plus JSONL).
uclaml-SPIN
The official implementation of Self-Play Fine-Tuning (SPIN)
vale
:pencil: A markup-aware linter for prose built with speed and extensibility in mind.
ZLUDA
CUDA on AMD GPUs