Python

DilawarShafiq/nietzschian-debugger

A CLI debugger that interrogates you instead of fixing your bug — Nietzschian Debugger flips the AI-assistant model: instead of giving fixes, it questions your assumptions via Claude's API in three intensity levels (socrates, nietzsche, zarathustra), pushing you to reach the insight yourself. Aimed at developers and learners who want to rebuild debugging skills rather than copy-paste answers.

It won't fix your bug. It'll fix you. The debugger that hands the question back instead of the answer.

i12bp8/decomp.wtf

What The Function: your AI agent decompiles games you own into C that compiles to the exact same bytes. Runs locally.

srinivasr/nirimod

NiriMod - A visual, interactive configuration interface for the niri Wayland compositor.

phongdaot/MocapAnything

Monocular video motion capture that works for any skeleton, not just humans — MoCapAnything V2 turns a single video plus a reference skeleton into BVH-ready joint rotations, end-to-end, without relying on a template-specific body model. It works for humans, animals, objects, and custom rigs, making it useful for animators and researchers who need mocap for non-standard skeletons where typical human-only mocap tools fall short.

[SIGGRAPH ASIA 2026]: End-to-End Motion Capture for Arbitrary Skeletons

JMS1717/ming-voice

Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux

google-research/kauldron

Google's JAX training framework built for fast research iteration — Kauldron is a modular JAX/Flax training library from Google Research that lets you mix any dataset loader, model, or optimizer while customizing every inner layer. It emphasizes a Colab-first workflow with built-in plotting, profiling, and post-mortem debugging to speed up research iteration.

Modular, scalable library to train ML models

EricJujianZou/rederive

Learn a codebase by re-deriving its design decisions yourself. A Claude Code skill.

CrocSwap/integer-mult-bounds

Crowdsourced AI agents chase a sharper integer-multiplication bound — This repo tracks community and AI-agent-driven research pushing the exponent in integer multiplication complexity below 2^-15, building on the OpenAI #109 framework. Contributions come as reviewed PRs with exact certificates and reproducible audits, coordinated via discussion threads and an autoresearch workflow for agents donating inference.

Conditional integer multiplication: kappa > 2^-15. Community proofs, exact certificates and reproducible audits; assumes the OpenAI #109 framework.

Comfy-Org/comfy-mcp

Local MCP server for ComfyUI — run your local ComfyUI from AI agents

uclanlp/OpenVLHarness

Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory

img2threejs/plugin-interior

Production interior authoring and interactive Three.js delivery plugin for img2.

recursive-oss/rec

Our lightning-fast inference engine.

xingjian-bai/opal

OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.

sybil-solutions/all-historical-evidence-of-jesus-christ

Evidence archive for Jesus of Nazareth: research dossier (PDF), New Testament, gnostic and extracanonical gospels, church fathers, ancient witnesses, Roman legal documents, archaeology, and all 238 cited references — searchable reader at https://sybil-solutions.github.io/all-historical-evidence-of-jesus-christ/

petergyang/video-short

Turn a raw recording into a polished video short with B-roll, motion graphics, captions, and music using your favorite AI agent

bhoult/correlation

Do stock correlations predict the market? 66 pre-registered tests, the data, and a triple pendulum that explains why not. If you have an idea you want me to try, submit it as a PR and I will test it and get back to you.

yuatemycat/SuperGhidra

SuperGhidra: Autonomous Agent Reverse Engineering, Lock-Free Ghidra Daemon & C++ Recovery Suite

jonathanhawkins/microduck-lab

Train RL policies for the Pollen Microduck 🦆 on an ordinary Mac, no CUDA GPU, and watch them learn live in the browser.

ptweezy/cronstable

A job scheduler with retries, alerts, saved run history, workflows, and dashboards for single machines and clusters.

AbuZar-Ansarii/Ultron

A Voice-First Desktop AI That Rewrites Its Own Python Tools on the Fly — Ultron is a voice-controlled desktop assistant styled after MCU's Ultron, offering 51 native tools, gesture control via OpenCV, a local SQLite knowledge graph for semantic recall, and a self-evolution engine that compiles and hot-loads new Python actions without restarting. It targets users who want a fully local, persona-driven PC automation agent rather than a generic chatbot.

Autonomous desktop intelligence with MCU Ultron persona, mood-aware workspace orchestration, cyber security sentry, and full PC control.

menloresearch/cyclotron

Open training pipeline for Asimov 1 humanoid locomotion — Cyclotron is Menlo Research's Isaac Lab extension for training and deploying locomotion policies on the open-source Asimov 1 humanoid robot, using PPO and adversarial motion priors. It covers the full workflow from training through export, viewing and benchmarking with simple commands, aimed at anyone building or customizing policies for sim-to-real humanoid control.

Official reinforcement learning training framework for Asimov humanoid robots, built on Isaac Lab.

RFnexus/partyline

Mumble-style group voice chat over Reticulum mesh networks — Partyline brings encrypted, realtime group voice to Reticulum networks, built on the LXST codec stack and inspired by Mumble. It runs over any transport above 6 kbps, supports Opus or low-bitrate Codec2 per room, offers password/allowlist access control, and lets LXST clients like rnphone or Sideband dial in. A lightweight server spins up in under 30 seconds, with GUI and terminal clients included.

A group voice application for Reticulum, built on LXST

anubhavmalhotra/r2d2-tv

A root-level webOS TV hack turns remotes into a voice assistant — This project replaces a webOS TV's home screen with a private Chromium browser streamed from a local Linux compute host, plus push-to-talk voice commands captured natively on the TV. It targets one specific firmware build via root patches and offline speech models, aimed at hackers willing to risk bricking an LG TV for a fully local, ad-free smart TV experience.

Local home screen, private remote browser, and push-to-talk voice assistant for webOS TVs

ROBOTIS-GIT/robotis_hand

Official ROS 2 packages to drive the ROBOTIS Hand robot — Official ROS 2 packages for controlling the ROBOTIS Hand (HX5-D20), covering control interfaces, sensor integration, MuJoCo simulation models, a Docker image, and links to tutorials, datasets and pre-trained models. Useful for robotics developers building hand/gripper control or Physical AI applications on ROS 2.

ROS Packages for Robotis Hand

thomasunise/casecite

Self-hosted legal RAG platform that keeps documents on your own infrastructure — CaseCite bundles nine tools — document chat, deep research against your corpus and CourtListener, contract review, and tabular review across hundreds of contracts — behind one login. It's self-hosted and BYOK: documents, search index, and chat history stay on your servers, with no telemetry to the maintainers. Aimed at firms wanting legal RAG without sending data to a third-party SaaS.

CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.

SyphoDev-yt/roblox-ai-skills

Claude Code skills turn Roblox game ideas into playable builds — A free pack of Claude Code skills and sub-agents that takes one Roblox game idea through research, design, build and playtest. Separate skills handle code scaffolding, UI, maps, 3D models, textures, VFX, SFX and animation, with an orchestrator running asset stages in parallel and a setup skill that configures everything on your machine automatically.

Free Claude Code skills for making Roblox games with AI: code, UI, maps, 3D models, VFX, SFX, animation. From the SyphoDev YouTube channel.

lxyeternal/MalSkillBench

A benchmark and generation framework for malicious agent skills.

tmatens/compose-lint

Security-focused linter for Docker Compose files. Catches dangerous misconfigurations before they reach production. Grounded in OWASP and CIS Docker Benchmark.

NVIDIA/Kumo-TS

Kumo-TS (formerly NV-Tesseract) is a comprehensive time series analysis package that provides foundation models for various time series tasks including forecasting and anomaly detection.

ps5-linux/ps5-linux-patches

Linux patches and configuration to run on PS5