Alif Jakir

g2mirror. Utility for mirroring a terminal to Even Realities G2 smart glasses

faceclaw. Custom user interface for the Even Realities G2 smart glasses

ShojiWM. The most customizable Wayland compositor with TypeScript(tsx).

smart_remarkable. Integrate LLM with your remarkable ink screen

ghostwriter. Use the reMarkable2 as an interface to vision-LLMs (ChatGPT, Claude, Gemini). Ghost in the machine!

InfoLens. A toolbox for exploring the informational nature of LLMs and language

cv. agents can read each others minds (session logs)

weco-cli. Production-Grade Autoresearch. Ideal for GPU kernels, ML model development, feature engineering, prompt engineering, and other optimizable code.

or-tools. Google's Operations Research tools:

orca. Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

opensmalltalk-vm. Cross-platform virtual machine for the Smalltalk implementations Squeak and Cuis

EvoAgentX. 🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents

dabsn. A PyTorch framework for DABSN—a recurrent architecture with admitted, permanent, and long-term memory—featuring native CPU/CUDA kernels and distributed training.

gstack. Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

E2B. Open-source, secure environment with real-world tools for enterprise-grade agents.

jj. A Git-compatible VCS that is both simple and powerful

durable-streams. The data primitive for the agent loop.

OpenRigLogic. C++

concrete2. Systems programming language designed for safe and predictable code, with semantics defined by a small core calculus formalized and proven sound in Lean

natural_language_autoencoders. Python

HRAG. H-RAG: Hierarchical Vector Compression & Topic-Guided Retrieval for RAG

pro-models. ProHand Models for Simulation (MJCF)

SAELens. Training Sparse Autoencoders on Language Models

algebrica. Algebrica is free and open a mathematical knowledge base dedicated to clarity, structure, and conceptual coherence.

sentence_hyperdiagrams. Python

LabOS. Official Code of LabOS: the AI-XR Co-Scientist that Sees and Works with Humans

eeg-workstation-agent. Open-source EEG analysis agent workflows and prompts for NeuraDock EEG Workstation.

clairnets. GLaDOS — Geometric Lattice Deduction Over Streams: param-efficient sound-reasoning organs (Clifford geometric product + lattice abstract-interpretation + recurrent deduction)

mermaid-rs-renderer. A fast native Rust Mermaid diagram renderer. No browser required. 500-1000x faster than mermaid-cli.

mujoco. Multi-Joint dynamics with Contact. A general purpose physics simulator.

CAN. Python

slint. Slint is an open-source declarative GUI toolkit to build native user interfaces for Rust, C++, JavaScript, or Python apps.

prime-rl. Agentic RL Training at Scale

PyNN. A Python package for simulator-independent specification of neuronal network models.

emg2speech. Python

RecursiveMAS. Offical Implementation for "Recursive Multi-Agent Systems"

AssemblyCalculus.jl. Assembly calculus in pure Julia

post-urbit. Post-Urbit: A personal server protocol specification for decentralized identity, secure messaging, and application runtime

rhizomatic. deterritorialized data at scale

unsloth. Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek, GLM and other models.

ratatui-hypertile. Hyprland-inspired BSP tiling for Ratatui 🐀

stagehand. The SDK For Browser Agents

mono. 99% of Queries in Zero Milliseconds

everything-evenhub.

ax-prover-base. A Minimal Agent for Automated Theorem Proving

y-sweet. A realtime CRDT-based document store, backed by S3.

MC-MineEvolve. Python

ADAM. We introduce ADAM, An emboDied causal Agent in Minecraft, that can autonomously navigate the open world, perceive multimodal contexts, learn causal world knowledge, and tackle complex tasks through lifelong learning.

sesame-robot. An open and affordable mini quadruped robot based on ESP32.

atproto. Social networking technology created by Bluesky

deepmind-research. This repository contains implementations and illustrative code to accompany DeepMind publications

alphafold3. AlphaFold 3 inference pipeline.

gemini-robotics-sdk. Python

alphaproof-nexus-results. Lean math proofs generated by AlphaProof Nexus and accompanying natural language prose proofs.

Graphite. Community-built comprehensive 2D content creation appplication for graphic design, digital art, and interactive real-time motion graphics powered by a node-based procedural graphics engine

dregg. Distributed object-capability authorization with ZK proofs

aws-terraform-dev-container. A VSCode Dev Container with tools to help you build and manage AWS infrastructure with Terraform

pylabrobot. interactive & hardware agnostic SDK for lab automation

grassmann-flows. Reproduction study of Grassmann Flows for sequence modeling (arXiv 2512.19428). Shows 22.6% gap vs claimed 10-15%, includes CUDA kernels with 2x speedup.

renderers. Programmable chat templates for LLM training and inference.

RayZer. Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"

flue. The sandbox agent framework.

ReSU. Code for the manuscript "A self-supervised multi-layer network of Rectified Spectral Units (ReSUs)" submitted to NeurIPS

halupedia. Encyclopedia that hallucinates articles on the fly

TabPFN. ⚡ TabPFN: Foundation Model for Tabular Data ⚡

hermes-agent. The agent that grows with you

charton. Grammar of Graphics in Rust

OpenGeneralist. First-principles design and training of a GeneralistAI Gen-1 style model, with decisions grounded in theory and supported by public evidence. Ongoing work.

concord. A feature-rich TUI client for Discord

lapdev. Seamless dev environments for Kubernetes

floem. A native Rust UI library with fine-grained reactivity

lapce. Lightning-fast and Powerful Code Editor written in Rust

LongVLM. Python

CausalVQA. We introduce CausalVQA, a benchmark dataset for video question answering (VQA) composed of question-answer pairs that probe models’ understanding of causality in the physical world.

cuda-oxide. cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.

agentic-harness-engineering. Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.

nano-world-model. A Minimalist, Batteries-included Repository for Advancing World Model Science.

examples-monorepo. Holds all the more complex examples in a single monorepo

FineGates. [FineGates] Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity, AISTATS 2026

urdf-skill. Skill for URDF generation and validation for robot model outputs

cad-skill. Skill for script-driven CAD generation, inspection, and validation

text-to-cad. A collection of agent skills for CAD, robotics and hardware design

HALO. Hierarchal Agent Loop Optimizer

worldforge. Harness framework to build world model based workflows for physical AI systems.

Awesome-Feed-Forward-3D. An curated list for feed-forward 3D scene modeling, including research directions, datasets, and applications.

mike. OSS Legal AI Platform

AutomataGPT. Python

automated-trading. Backup of pdf 'Max Dama on Automated Trading' from http://isomorphisms.sdf.org/maxdama.pdf (now offline). obviously not my own work

dimos. Dimensional is the agentic operating system for physical space. Command humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seamlessly with physical input (cameras, lidar, actuators).

spw-workbench. workbench for spw

obsidian-skills. Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.

pandas-ta-classic. Technical Analysis Indicators - Pandas TA Classic is an easy to use Python 3 Pandas Extension with 250+ Indicators and Candlestick Patterns

youtu-agent. A simple yet powerful agent framework that delivers with open-source models

GR00T-VisualSim2Real. GR00T-VisualSim2Real: Open-source sim-to-real framework for humanoid visual loco-manipulation. Train in simulation, deploy zero-shot on real robots with RGB + proprioception for tasks like pick-and-place and door opening.

genjax. Probabilistic programming with vectorized programmable inference

macro. Macro is a unified interface for email, messages, tasks, calls, agents, pull requests, docs, crm — linked together with shared AI memory.

ableton-mcp. Python

hope_nano. This is the unofficial implementation of HOPE based model as shown in the google deepmind research paper.

flutter. Flutter makes it easy and fast to build beautiful apps for mobile and beyond

aics. AICS TUI - Search and manage your Claude Code and Codex sessions

habermas_machine. Python

sbox-public. s&box is a modern game engine, built on Valve's Source 2 and the latest .NET technology, it provides a modern intuitive editor for creating games

browser-harness. Browser Harness | Self-healing harness that enables LLMs to complete any task.

cookbook. TypeScript

Bonsai-demo. Bonsai Demo

x-humanoid-training-toolchain. This project provides a training toolchain for adapting TienKung humanoid robots and RoboMIND dataset with the open-source LeRobot framework.

gemma4-browser-extension. On-device AI agent Chrome extension powered by Transformers.js and Gemma 4

restrans. Python

agents. A framework for building realtime voice AI agents 🤖🎙️📹

hmdm-docker. An official Docker image for Headwind MDM

promnesia. Another piece of your extended mind

VisionClaw. Logseq Spring Thing Immersive & Agentic Knowledge Development Engine

logseq. A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://github.com/logseq/logseq/releases. roadmap: https://logseq.io/p/NX4mc_ggEV

og. Logseq og (file version)

agents-are-thinking. Exploring agent "thinking" animation.

ast-bro. A fast, AST-based code navigation toolkit that maps file shapes, public APIs, and call graphs across coding languages. Designed to help coding agents and humans explore codebases, analyze blast radius, and generate token-budgeted context with massive token savings.

snntorch. Deep and online learning with spiking neural networks in Python

-Project-Nord-Spiking-Neural-Network-Language-Model. The first pure SNN language model trained from scratch with a fully original architecture. 618M parameters • 93% sparsity • Runs on phone • Online learning via STDP • $260 total training cost

spikingjelly. SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

SpikeGPT. Implementation of "SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks"

fleet. Open device management

minebench. Minecraft-style voxel benchmark for comparing AI models (Arena + Sandbox)

late-sh. A cozy terminal clubhouse for developers. Lofi beats, casual games, chat, and tech news, all via SSH.

catgrad. a categorical deep learning compiler

ZWM. Paper: "Zero-shot World Models Are Developmentally Efficient Learners"

obsidian-wiki. Framework for AI agents to build and maintain a digital brain through Obsidian wiki

bayes3d. Jupyter Notebook

b3d. Bayes3D

codex. Lightweight coding agent that runs in your terminal

zigzag. Zig

stretchystudio. FOSS 2D animation tool for turning static illustrations into mesh-deformable characters

research-environments. Environments by the Prime Intellect Research Team

mcp_massive. An MCP server for Massive.com Financial Market Data

rattles. 🪇 Minimal terminal spinners/throbbers for Rust

eips. The efficient, intention-preserving sequence CRDT. Guaranteed logarithmic-time operations.

skill. NeuroSkill™ — State of Mind Brain-Computer Interface system

LabClaw. LabClaw – Operating Layer for LabOS (Stanford-Princeton AI Co-Scientists)

web-sdk. Gracia Web SDK

engine. Powerful web graphics runtime built on WebGL, WebGPU, WebXR and glTF

xr-objects. XR-Objects is an open-source prototype that anchors contextual interactions onto analog objects to not only convey information but also to initiate digital actions, such as querying LLMs for details or executing tasks. Creating an early form of Augmented Object Intelligence.

tribev2. This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction

3DTelecommunications. 3D Telecommunications project utilizing Holoportation technology to provide live volumetric capture. Used in one case to increase the reach of specialized medicine.

zep-python. Build Agents That Recall What Matters. Systematically engineer relevant context from chat history & business data. (Python Client)

graphiti. Build Real-Time Knowledge Graphs for AI Agents

plurality. Root repository for ⿻數位 Plurality: The Future of Collaborative Technology and Democracy by E. Glen Weyl, Audrey Tang and the Plurality Community

titans-trainer. Train TITANS models in 5 lines. Huggingface-style trainer for the TITANS architecture - transformers with neural long-term memory & test-time learning

pretext. Fast, accurate & comprehensive text measurement & layout

circuit-tracer. Python

Halo-CR4B-Tool. One-click game-accuracy tool for Halo 3/ODST/Reach assets in Blender that also exports assets from every Halo game

nightjarpy. Python library to add support for embedding natural code in Python with shared program state.

gd-pure. Grounded deduction atop Isabelle/Pure

d4m. Dynamic Distributed Dimensional Data Model

git4aiagents. All reasoning is stored in git. No external server. No database. No account. No hosting. Any developer on any system pulls the latest commits and gets the full reasoning history. Any future AI agent reads it before modifying shared code. It works through GitHub, GitLab, Bitbucket, or any internal git host at Google, Amazon, or anywhere else.

subconscious. JavaScript

ironclaw. IronClaw is an Agent OS focused on privacy, security and extensibility

dioxus. Fullstack app framework for web, desktop, and mobile.

MaixPy. Easily create AI projects with Python on edge device

infra. Infrastructure that's powering E2B Cloud.

rlm. General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

ffmpreg. An experimental safe multimedia toolkit

ACI_code. MATLAB code for the paper "Assimilative Causal Inference".

WeDLM. WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.

three-geospatial. Geospatial Rendering in Three.js

molecular-renderer. Renderer for molecular nanotechnology

slowrun. 100M tokens. Infinite compute. Lowest val loss wins.

autoresearch-go-ane. Autonomous AI research on Apple Silicon using ANE-accelerated training

meetily. Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows. Understand How to write meeting minutes

ml_forge. A visual-based graph node editor for training computer vision models.

get-physics-done. The first open-source agentic AI physicist, by Physical Superintelligence PBC (PSI).

ngrep. grep plus word embeddings

SimpleRecursiveModel. Simple Recursive Model

StableGen. Transform your 3D texturing workflow with the power of generative AI, directly within Blender!

rustdesk. An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

GR00T-WholeBodyControl. Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC

GENMO. Python

kit-app-template. Omniverse Kit App Template

OpenManus-RL. A live stream development of RL tunning for LLM agents

stable-worldmodel. A platform for reproducible world model research and evaluation

TurboDiffusion. TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

shuttle. Build & ship backends without writing any infrastructure files.

LatentMAS. [ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems

elide. fast multi-lang runtime

thread. Python

causationentropy. Implementation of Causation Entropy from Clarkson Center for Complex Systems Science (C3S2)

LeLamp. Open-source Expressive Robot Lamp

nvm-windows. A node.js version management utility for Windows. Ironically written in Go.

bdh. BDH (Dragon Hatchling) – Architecture and Code

PostLaborEconomics. Public repository for Post-Labor Economics research data.

manim. Animation engine for explanatory math videos

HyperNoise. Python

cosmos-transfer1-diffusion-renderer. Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework

polis. :milky_way: Open Source AI for large scale open ended feedback

PufferLib. Puffing up reinforcement learning

LLaDA-V. Python

HRM. Hierarchical Reasoning Model Official Release

open-collaboration-tools. Open Collaboration Tools: live-sharing solution for Eclipse Theia, VS Code and other editors and IDEs

optifine_alternatives. A list of recommended OptiFine alternatives.

dyad. Local, open-source AI app builder for power users ✨ v0 / Lovable / Replit / Bolt alternative 🌟 Star if you like it!

genjax. Probabilistic programming with programmable inference for parallel accelerators.

lorax. Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs