Python

google-deepmind/mujoco_menagerie

Ready-to-simulate robot models for MuJoCo — A curated library of well-tested MuJoCo models — arms, hands, quadrupeds, humanoids and more — designed to work correctly out of the box rather than producing unexpected physics behavior. Now distributed as a PyPI package for easier integration into Python robotics and simulation workflows.

A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

lwthiker/curl-impersonate

A curl build that mimics browser TLS and HTTP/2 fingerprints — curl-impersonate replicates the TLS Client Hello and HTTP/2 handshake settings of Chrome, Edge, Safari and Firefox, defeating fingerprinting used by sites to distinguish bots from real browsers. Usable as a CLI tool or libcurl replacement, it suits scraping, testing and privacy-focused clients facing fingerprint-based blocking.

curl-impersonate: A special build of curl that can impersonate Chrome & Firefox

NVIDIA/Model-Optimizer

NVIDIA's toolbox for squeezing and quantizing models before deployment — Model Optimizer bundles quantization, pruning, NAS, distillation and speculative decoding into one Python API for Hugging Face, PyTorch or ONNX models. It exports quantized checkpoints ready for SGLang, TensorRT-LLM, TensorRT or vLLM, and integrates with Megatron-LM and Accelerate for training-aware optimization.

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

owainlewis/awesome-artificial-intelligence

Curated list refocused on building production generative AI systems — This long-running awesome list has shifted focus to developers building, evaluating, and deploying generative AI and agentic systems, not just classic ML theory. Entries face a strict quality bar and the list is reviewed weekly by automation, making it a practical resource for engineers working with LLMs, retrieval, and coding agents.

A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.

uber/ADR

Uber's open-sourced security stack for enterprise AI agents — ADR is Uber's production-deployed security system for agentic AI, now open-sourced with its MLSys 2026 paper. It covers discovery of AI tools, cross-platform observability for coding agents like Cursor and Claude Code, a 300+ task benchmark against 17 attack techniques, and a two-tier threat detector—useful for security teams managing enterprise AI agent risk.

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

microsoft/apm

A package manager that makes AI agent setups portable — APM lets teams declare agent context, skills, prompts and MCP servers in one apm.yml manifest, then reproduce the full setup across tools like Copilot, Claude Code, Cursor and Codex with a single command. It supports transitive dependency resolution and plugin authoring, aimed at developers tired of manually configuring agent context per project.

Agent Package Manager

home-assistant/core

Local-first home automation core backed by a huge DIY community — Home Assistant's core engine runs locally on devices like a Raspberry Pi, favoring privacy over cloud dependence. Its modular architecture lets contributors add new integrations easily, making it a fit for tinkerers who want to build and extend their own smart home setups.

:house_with_garden: Open source home automation that puts local control and privacy first.

VictorTaelin/OptMem

A single-file memo tool that gives AI agents durable memory — OptMem adds persistent memory to AI agents via one dependency-free Python script and a 426-token prompt pasted into AGENTS.md or CLAUDE.md. Commands like wake, note, recall and nap read, log and summarize memories with append-only, fixed-width storage—fast even at a million entries. Useful for anyone wiring long-term memory into Claude or similar agent setups without extra infrastructure.

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

mozilla-ai/otari

A self-hosted gateway that unifies 40+ LLM providers behind one API — Otari is a Mozilla AI project that lets you run your own OpenAI/Anthropic-compatible gateway in front of 40+ model providers. It adds virtual API keys, pre-spend budget checks, usage tracking, and local routing policies for failover, useful for teams wanting to own their AI infrastructure instead of relying on a hosted proxy.

Open-source, OpenAI-compatible LLM gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.

odoo/odoo

A modular open-source ERP covering CRM to manufacturing — Odoo bundles dozens of business apps—CRM, eCommerce, inventory, accounting, HR, manufacturing—that work standalone or combine into a full ERP. Useful for businesses wanting to add modules incrementally instead of adopting one monolithic system, with developer tutorials for customization.

Odoo. Open Source Apps To Grow Your Business.

microsoft/VibeVoice

Microsoft's open voice AI grows into streaming speech recognition — VibeVoice now ships VibeVoice-ASR-Streaming, transcribing 'who said what' live across 10 languages with custom hotwords, plus a BitNet-quantized CPU engine that shrinks the ASR model to 1.58GB for real-time, GPU-free inference. It's aimed at developers wanting open, deployable speech recognition without cloud GPUs.

Open-Source Frontier Voice AI

microsoft/agent-lightning

A lightweight RL framework to train AI agents using real harnesses — Agent Lightning v1.0 is a ~3,500-line framework that trains agents via reinforcement learning without modifying existing agent harnesses, tools, or environments, using a proxy layer and native Kubernetes job support. It targets MLOps and RL researchers, with examples showing SWE-bench Verified gains from fine-tuning Qwen models on limited training samples.

The absolute trainer to light up AI agents.

microsoft/graphrag

Microsoft's graph-based RAG pipeline, now in maintenance mode — GraphRAG turns unstructured text into structured graph data to give LLMs targeted context for question answering over private data. Microsoft Research built it as a research exploration; it's now largely maintained for bug fixes and CVEs rather than new features. Useful for those wanting a documented, citable RAG architecture rather than active new development.

A modular graph-based Retrieval-Augmented Generation (RAG) system

MobSF/Mobile-Security-Framework-MobSF

All-in-one pen-testing framework for Android, iOS and Windows apps — MobSF combines static and dynamic analysis for APK, IPA and APPX binaries, plus runtime instrumentation and network traffic inspection. REST APIs and CLI tools let it plug into CI/CD pipelines, making it useful for security researchers, pentesters and DevSecOps teams who need repeatable mobile app assessments.

Mobile Security Framework (MobSF) is an automated, all-in-one mobile application (Android/iOS/Windows) pen-testing, malware analysis and security assessment framework capable of performing static and dynamic analysis.

davila7/claude-code-templates

Ready-made agents and monitoring for Claude Code setups — A CLI and template collection for configuring Anthropic's Claude Code, offering ready-to-use AI agents and monitoring tools. It's aimed at developers who want to skip manual setup and quickly apply proven configurations, backed by recognition from Vercel's and Neon's open-source programs.

CLI tool for configuring and monitoring Claude Code

google-research/timesfm

TimesFM 3.0 brings zero-shot multivariate forecasting to Google Cloud — Google Research's pretrained time-series model now ships a 3.0 checkpoint for zero-shot multivariate forecasting, already rolled out in BigQuery ML, Connected Sheets, and Vertex Model Garden. Useful for data scientists wanting forecasts without training custom models per dataset.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

qbittorrent/search-plugins

Community-maintained search plugins powering qBittorrent's built-in search — This repo hosts the Python search plugins used by qBittorrent's search tab, now maintained by community contributors rather than the core team. It points users to a wiki for installing plugins, writing new ones, and configuring Jackett, since official upkeep is limited and PRs to fix existing plugins are welcomed.

Search plugins for qBittorrent search feature

onyx-dot-app/onyx

A self-hosted context layer that connects LLMs to your team's apps — Onyx indexes knowledge from 50+ applications and exposes it to any LLM, aiming to act as an AI coworker rather than a generic chatbot. It runs self-hosted for data control and adds features like web search, sandboxes, and skills on top of RAG search. Useful for enterprise teams wanting an internal knowledge/search layer without vendor lock-in.

Open Source AI Platform - AI Chat with advanced features that works with every LLM

BitterSecurity/Decepticon

An autonomous agent framework for red team pentesting — Decepticon is an open-source autonomous agent built on LangChain/LangGraph that performs red team tasks beyond running nmap and writing reports. Trending on Trendshift, it targets security researchers and pentesters wanting LLM-driven, agentic exploit testing rather than scripted scanners.

Autonomous Hacking Agent for Red Team

EbookFoundation/free-programming-books

A massive, searchable index of free programming resources — This long-running Ebook Foundation project curates free programming books, courses, and references across many languages, now with a dedicated search site for quickly finding a book or author. It's maintained under the Awesome list format and stays active via Hacktoberfest contributions.

:books: Freely available programming books

Fosowl/agenticSeek

A fully local, voice-enabled agent that browses and codes for you — AgenticSeek positions itself as a private, local alternative to Manus AI: it browses the web, writes and debugs code, and plans multi-step tasks using local reasoning models like DeepSeek-R1, with no cloud or subscription fees. Voice interaction is in progress. Useful for privacy-conscious developers wanting autonomous agents without API costs.

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

suitenumerique/docs

A self-hosted, real-time collaborative editor from France's digital agency — Docs is a web-native text editor built with Django, React, BlockNote and Yjs for real-time collaborative editing of nested documents. Backed by France's government digital service and verified as a Digital Public Good, it suits organizations wanting self-hosted, data-sovereign alternatives to proprietary docs tools.

Docs is an open-source text editor: web-native, made for real-time collaboration, cleanly structured documents and sub-documents with full ownership of your data. Built to scale with Django and React.

filby89/spectre

3D Facial Expression Reconstruction That Preserves Speech Perception — SPECTRE is the official PyTorch code for a method that reconstructs 3D facial expressions from video while keeping lip and speech cues intact, useful for talking-head applications. It builds on the FLAME model and has already been integrated into EMOCAv2; the authors' newer project SMIRK extends this work further.

Official Pytorch Implementation of SPECTRE: Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videos

agno-agi/agno

Own your full agent stack, from build to runtime to UI — Agno is a Python framework paired with the AgentOS runtime and UI, letting teams build, run, and manage agent platforms themselves. It adds JWT-based RBAC, Postgres-backed traces, and starter templates for Railway, Docker, AWS or GCP deploys, giving developers control over data, memory, and security instead of relying on a hosted service.

The self-improving agent platform

Crosstalk-Solutions/unifi-toolkit

An unofficial dashboard and monitoring suite for UniFi gateways — UI Toolkit adds a real-time dashboard, client tracking (Wi-Fi Stalker), IDS/IPS alerting (Threat Watch), and one-click zone-based device blocking (House Arrest) on top of UniFi networks, with webhook alerts to Slack, Discord, or n8n. Useful for self-hosters and network admins wanting deeper visibility than UniFi's own UI offers.

A suite of tools for UniFi network management

Z4nzu/hackingtool

An AI layer now picks the right tool from 219 curated hacking tools — hackingtool bundles 219 tools across 21 categories (recon, OSINT, web, wireless, phishing, forensics, post-exploitation) and adds an AI layer that translates plain-English requests into the correct tool and exact command. Aimed at pentesters, red/blue teamers, OSINT researchers, bug-bounty hunters and CTF players working on authorized systems.

ALL IN ONE Hacking Tool For Hackers

m-bain/whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

arc53/DocsGPT

Self-hosted AI agents that answer strictly from your own documents — DocsGPT is a private, self-hosted platform for building AI agents and assistants grounded in your own docs, with a visual Agent Builder, deep research, document analysis, multi-model support and API connectors. A one-line install script makes it quick to run locally, aimed at teams wanting enterprise search without sending data to third parties.

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

atsushi-green/ds-ai-coding-skills

Pre-built AGENTS.md skills to guide AI coding tools for data scientists — A collection of AGENTS.md router files, Claude/Codex skills, and prompts designed for data science workflows, covering Python, SQL, Polars, visualization, and statistics. It includes paired 'diagnostics' skills that force AI assistants to output standardized charts alongside analysis results, with a gallery of generated examples.

A collection of AGENTS.md configurations, skills, and prompts tailored for Data Scientists to maximize productivity with AI coding assistants.

karmanyaahm/budget-tools

Local-only tooling for exploring Buckets budgeting data — A set of Python scripts and a browser app for analyzing the Buckets budgeting app's SQLite database. It offers an interactive pie-chart explorer for allocations, income and spending, plus helpers to merge Venmo CSV exports and convert UsageDirect app-usage into cost rows—all processed locally, keeping financial data private.