Yasyf Mohamedali

fortress. Stealth Chromium engine that stops scrapers and browser agents from getting blocked, with one line of code change.

pmb. Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.

tilth. Smart(er) code reading for humans and AI agents. Reduces cost per correct answer by ~40% on average. Install: cargo install tilth -or- npx tilth

paperclip. The open-source app everyone uses to manage agents at work

agent-vault. A HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.

diffx. A local code review tool designed for the coding agent workflow

beanie. Asynchronous Python ODM for MongoDB

ds4. DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

no-mistakes. git push no-mistakes

claudectl. Orchestrate a swarm of Claude Code agents with a local brain that learns from you.

exo. Run frontier AI locally.

d-inference. Private Inference Network on Idle Macs

nullclaw. Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig

nanoclaw. A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

AlexClaw. BEAM-native personal AI agent built on Elixir/OTP. Runs on your hardware. Your data stays yours.

placeholder. Operator overloading for fast anonymous functions.

Agent-S. Agent S: an open agentic framework that uses computers like a human

zse. The inference engine the open-source world built for itself.

tadpole. TypeScript

gastown. Gas Town - multi-agent workspace manager

faktory. Language-agnostic persistent background job server

a2ui. TypeScript

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

luminal. Inference at the speed of light.

ebook2audiobook. Generate audiobooks from e-books, voice cloning & 1158+ languages!

ZeroFS. ZeroFS: A log-structured filesystem for S3. ZeroFS serves S3-compatible buckets as POSIX filesystems over NFS and 9P, or as raw block devices over NBD.

agent-fuse. Example repo showcasing how to represent anything as a filesystem to an agent via FUSE

opencode. The open source coding agent.

toad. A unified interface for AI in your terminal.

ace. Evolve your language agent with Agentic Context Engineering (ACE)

vale. :pencil: A markup-aware linter for prose built with speed and extensibility in mind.

smartcommit. Enforce the habit of self-documenting code through better commit messages.

pctx. pctx is the execution layer for agentic tool calls. It auto-converts agent tools and MCP servers into code that runs in secure sandboxes for token-efficient workflows.

quibbler. Python

toon. 🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

patchy. :anchor: Patch the inner source of python functions at runtime.

readweb. read_web LLM tool that cleans up the page contents intelligently, saving tokens for your LLM workflow

firm. A text-based work management system for technologists.

optillm. Optimizing inference proxy for LLMs

tinyworlds. A minimal implementation of DeepMind's Genie world model

capnweb. JavaScript/TypeScript-native, low-boilerplate, object-capability RPC system

Paper2Agent. Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.

rloop. An AsyncIO event loop implemented in Rust

UltraPlot. A succinct wrapper for matplotlib

bake. Bake microVMs into standalone executables

PageIndex. 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

fast-plaid. High-Performance Engine for Multi-Vector Search

maxsim-cpu. Python

graph-mining. C++

muvera-py. Python Implementation of MUVERA (Multi-Vector Retrieval via Fixed Dimensional Encodings)

ghostty. 👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

any-llm. Communicate with an LLM provider using a single interface

openevolve. Open-source implementation of AlphaEvolve

chopdiff. Diff filtering, text mapping, and windowed transforms for LLM apps

morphik-core. Open-source multimodal retrieval engine (Morphik Core). By Morphik — AI back office for skilled nursing & senior living (morphik.ai).

pogocache. Fast caching software with a focus on low latency and cpu efficiency.

hurl. Hurl, run and test HTTP requests with plain text.

whathaveidone. A terminal tool to summarize your Git commit history for daily standups, using AI

forge. forge (python signatures) for fun and profit

jambo. Jambo - JSON Schema to Pydantic Converter

index. The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web

cua. Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

SciRIFF. Dataset and evaluation suite enabling LLM instruction-following for scientific literature understanding.

dia. A TTS model capable of generating ultra-realistic dialogue in one pass.

anubis. Weighs the soul of incoming HTTP requests to stop AI crawlers

uBOL-home. uBO Lite home (MV3)

graphiti. Build Real-Time Knowledge Graphs for AI Agents

python-blosc2. A high-performance library for compressed ND arrays and columnar tables, with compute and indexing engines

python-blosc. A Python wrapper for the extremely fast Blosc compression library

niquests. Drop-in replacement for Requests. Automatic HTTP/1.1, HTTP/2, and HTTP/3. WebSocket, and SSE included.

node-serp. LLM-as-SERP

pebble. This is the latest version of the internal repository from Pebble Technology providing the software to run on Pebble watches. Proprietary source code has been removed from this repository and it will not compile as-is. This is for information only.

aiologic. GIL-powered* locking library for Python

PyAV. Pythonic bindings for FFmpeg's libraries.

whisper_streaming. Whisper realtime streaming for long speech-to-text transcription and translation

siyuan. A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

ColiVara. Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has state of the art retrieval performance on both text and visual documents. using vision models instead of chunking and text-processing for documents. No OCR, no text extraction, no broken tables, or missing images.

EmbedAnything. Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

uv. An extremely fast Python package and project manager, written in Rust.

netbird. Connect your devices into a secure WireGuard®-based overlay network with SSO, MFA and granular access controls.

nlm-ingestor. This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

entropix. Entropy Based Sampling and Parallel CoT Decoding

typst. A markup-based typesetting system that is powerful and easy to learn.

anki. Anki is a smart spaced repetition flashcard program

skyvern. Automate browser based workflows with AI

sentient. the framework/ sdk that lets you build browser controlling agents in 3 lines of code. join chat @ https://discord.gg/umgnyQU2K8

GOT-OCR2.0. Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

chai-lab. Chai-1, SOTA model for biomolecular structure prediction

Stella.

runcvm. RunCVM (Run Container VM) is an experimental open-source Docker container runtime, for launching standard container workloads - as well as Systemd, Docker, even OpenWrt - in VMs using 'docker run`

Liger-Kernel. Efficient Triton Kernels for LLM Training

equinox. Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

textgrad. TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

KAZU. Fast, world class biomedical NER

semantic-chunkers. Python

flair. A very simple framework for state-of-the-art Natural Language Processing (NLP)

turbopuffer-python. Official Python API client library for turbopuffer

continuous-eval. Data-Driven Evaluation for LLM-Powered Applications

magic-cli. Command line utility to make you a magician in the terminal

langevals. LangEvals aggregates various language model evaluators into a single platform, providing a standard interface for a multitude of scores and LLM guardrails, for you to protect and benchmark your LLM models and pipelines.

openinterpreter. A lightweight coding agent for open models like Deepseek, Kimi, and Qwen

katana. A next-generation crawling and spidering framework.

slackrock. Conversational AI assistant powered by Amazon Bedrock

vector-io. Comprehensive Vector Data Tooling. The universal interface for all vector database, datasets and RAG platforms. Easily export, import, backup, re-embed (using any model) or access your vector data from any vector databases or repository.

PyOxidizer. A modern Python application packaging and distribution tool

neo4j-runway. End to end solution for migrating CSV data into a Neo4j graph using an LLM for the data discovery and graph data modeling stages.

sandbox. Code editing environment with an AI copilot and real-time collaboration

text-splitter. Split text into semantic chunks, up to a desired chunk size. Supports calculating length by characters and tokens, and is callable from Rust and Python.

llama-fs. A self-organizing file system with llama 3

ragflow. RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

python-debouncer. Debouncer and friends for Python

sorcery. Dark magic delights in Python

logfire. AI observability platform for production LLM and agent systems.

ragas. Supercharge Your LLM Application Evaluations 🚀

deepdiff. DeepDiff: Deep Difference and search of any Python object/data. DeepHash: Hash of any object based on its contents. Delta: Use deltas to reconstruct objects by adding deltas together.

OpenAdapt. Record a workflow once, compile it into a deterministic, self-healing automation that runs on your own machines. Open-source demonstration compiler for desktop workflows — local-first, model-optional, audit-ready.

llama3. The official Meta Llama 3 GitHub site

surya. OCR, layout analysis, reading order, table recognition in 90+ languages

hermit. Hermit launches linux x86_64 programs in a special, hermetically isolated sandbox to control their execution. Hermit translates normal, nondeterministic behavior, into deterministic, repeatable behavior. This can be used for various applications, including replay-debugging, reproducible artifacts, chaos mode concurrency testing and bug analysis.

infinity. Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

SJOT. Fast and lightweight JSON validation and JS type checking. SJOT schemas are as simple as JSON templates.

fast_vector_similarity. High-performance vector similarity library in Rust with Python bindings: Spearman, Kendall, distance correlation, Jensen-Shannon, Hoeffding's D, and bootstrapped confidence intervals

mlc-llm. Universal LLM Deployment Engine with ML Compilation

sglang. SGLang is a high-performance serving framework for large language models and multimodal models.

sweep. Sweep: AI coding assistant for JetBrains

plandex. Open source AI coding agent. Designed for large projects and real world tasks.

EasyLM. Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

LaTeX-OCR. pix2tex: Using a ViT to convert images of equations into LaTeX code.

llama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

nmslib-metabrainz. Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces. (metabrainz fork for python3.11 and 3.12)

cornflakes. A zero-copy serialization library and networking stack.

candle. Minimalist ML framework for Rust

FastUI. Build better UIs faster.

Grapher. Code that implements efficient knowledge graph extraction from the textual descriptions

marker. Convert PDF to markdown + JSON quickly with high accuracy

dspy. DSPy: The framework for programming—not prompting—language models

Ensemble. Cast Mac windows to visionOS

deskhop. Fast Desktop Switching Device

StreamDiffusion. StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

mamba-minimal. Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

microagents. Agents Capable of Self-Editing Their Prompts / Python Code

pythonrc. lonetwin's pimped-up pythonrc

funcchain. ⛓️ build cognitive systems, pythonic

ix. Autonomous GPT-4 agent platform

galactic. data cleaning and curation for unstructured text

deepface. A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

code-indexer-loop. Code Indexer Loop is a Python library for indexing and retrieving source code files through an integrated vector database that's continuously and efficiently updated.

ts-morph. TypeScript Compiler API wrapper for static analysis and programmatic code changes.

modelfusion. The TypeScript library for building AI applications.

vanna. 🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.

marvin. an ambient intelligence library

HeimdaLLM. Constrain LLM output

FLARE. Forward-Looking Active REtrieval-augmented generation (FLARE)

sqlmodel. SQL databases in Python, designed for simplicity, compatibility, and robustness.

guidance. A guidance language for controlling large language models.

hyperDB. A hyper-fast local vector database for use with LLM Agents. Now accepting SAFEs at $135M cap.

craft. The universal Sentry release CLI 🚀

langchain-hub. Python

examples. Example implementations of common Sym Flows

codon. A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support

inngest. The leading workflow orchestration platform. Run stateful step functions and AI workflows on serverless, servers, or the edge.

pavex. A backend framework for Rust professionals

awardwiz. Search for flight availability with award miles

api-firewall. Fast and light-weight API proxy firewall for request and response validation by OpenAPI specs.

django-pgtrigger. Write Postgres triggers for your Django models

codeline. Run context-aware commands from your source code comments

simple-screenshot-feedback. A simple plug and play feedback component for your website.

nubia. NUBIA (NeUral Based Interchangeability Assessor) is a new SoTA evaluation metric for text generation

terraform-okta-ssm-modules. Terraform modules that help you explore Okta and AWS Session Manager integrations

artichoke. 💎 Artichoke is a Ruby made with Rust

chronic. Chronic is a pure Ruby natural language date parser.

steep. Static type checker for Ruby

new-grad-offers. some notes about how to navigate new grad software engineering job offers

mini_racer. Minimal embedded v8

zenbot. Zenbot is a command-line cryptocurrency trading bot using Node.js and MongoDB.

emoji-mart. 🏪 One component to pick them all

jquery-emoji-picker. A jQuery picker for emojis

faas. OpenFaaS - Serverless Functions Made Simple

from-python-to-numpy. An open-access book on numpy vectorization techniques, Nicolas P. Rougier, 2017

davidnotes. dont read me

lolrecaptcha. We try to break the recaptcha for the Merry Christmas for all!

hardest-game. MIT 6.867: Reinforcement Learning to beat The World's Hardest Game

emojicode. 😀😜🔂 World’s only programming language that’s bursting with emojis

vc. VoteCollector - Voting Platform for Dorm Room Fund

drfbot. Slack Bot for Dorm Room Fund

interviews. CS interview study sheet

flask-start. Skeleton Flask and Angular App

bcferries. BC Ferries Python Library

mochi. Dynamically typed functional programming language

streem. prototype of stream based programming language

natural. general natural language facilities for node

tortilla. Wrapping web APIs made easy.

mit-textbooks. MIT Textbooks

dashing. The exceptionally handsome dashboard framework in Ruby and Coffeescript.

petulant-adventure. It's a Petulant Adventure!

data-viz-challenge.

sweetalert. A beautiful replacement for JavaScript's "alert"

controlio. Control your computer through SMS!