This is your work, valued
dw2md. Crawl a DeepWiki repository and compile all pages into a single, LLM-friendly markdown file
★ 23modded-llama2. (trying to) train llama2 7B fast
★ 10hive. Hive: A Lightweight Multi-Agent Coding Orchestrator
★ 10tau. A minimal, hackable coding agent harness in Rust
★ 9irradiate. Fast mutation testing for Python, written in Rust
★ 4labrat. Autonomous ML research agent skill (Agent Skills format). Designs experiments, deploys to Modal GPUs, tracks budget, iterates autonomously.
★ 3forest. Project repository for Drexel University Senior Thesis
★ 2gpu-study-group-leaderboard. Cuda
★ 2takeoff-protocol. TypeScript
★ 2pyorbit. Orbit -- yet another Python static site generator
★ 1pytrace. toy ray tracer implemented in python based on the book "The Ray Tracer Challenge"
★ 1lora-demo. LoRA demo (using Tinker API)
★ 1edit-bench. Python
★ 1agent-vault. Keep your secrets hidden from AI agents.
★ 427codex-plugin-cc. Use Codex from Claude Code to review code or delegate tasks.
★ 28ksuperdoc. 🦋️ SuperDoc - Modern DOCX Editor and Agent SDK
★ 872Manual. You were probably looking for our website... this is it. We moved our website here, so you can see the insides of how we work.
★ 1.7kcode. Noumena's internal version of your favorite coding tui but improved and optimized for our inference stack
★ 133kimi-code. Kimi Code CLI — The Starting Point for Next-Gen Agents
★ 3.1kharn. full Python port of earendil's pi agent
★ 19learning-opportunities. A Claude or Codex skill for deliberate skill development during AI-assisted coding
★ 2.2kdifftastic. a structural diff that understands syntax 🟥🟩
★ 26khunk. Review-first terminal diff viewer for agentic coders
★ 6.6kouroboros. Agent OS: Stop prompting. Start specifying.
★ 4.9kclaudesona. Claudesona Emotion Sprites is an unofficial fan extension for claude.ai. It watches normal page text for simple emotion tags such as <claude_happy />, <claude_thoughtful />, and <claude_skeptical />, then replaces each tag with a compact 128x128 transparent claudesona sprite.
★ 96prinzbench. prinzbench is a private benchmark that ranks LLMs based on their ability to conduct legal research and analysis and locate obscure publicly available information online.
★ 116Understand-Anything. Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
★ 73kdocling. Get your documents ready for gen AI
★ 63kopenweights. A python sdk for LLM finetuning and inference on runpod infrastructure
★ 30symphony. Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
★ 26ksondera-coding-agent-hooks. Hooking implementations and supporting tools for various coding agents (Claude, Cursor, Gemini, etc)
★ 220sgs. Python
★ 76MiroFish. A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物
★ 68kbiglaw-bench.
★ 168bloom. bloom - evaluate any behavior immediately 🌸🌱
★ 1.4kFailureLLMUnlearning. An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)
★ 39HVM2. A massively parallel, optimal functional runtime in Rust
★ 11kaudio. Data manipulation and transformation for audio signal processing, powered by PyTorch
★ 2.9kloom. A Loom implementation in Obsidian
★ 329loom. Multiversal tree writing interface for human-AI collaboration
★ 1.4kchrome-devtools-axi. The most agent-ergonomic browser automation
★ 234gh-axi. GitHub CLI for agents — designed with AXI (Agent eXperience Interface).
★ 158Malcolm. Malcolm is a powerful, easily deployable network traffic analysis tool suite for full packet capture artifacts (PCAP files), Zeek logs and Suricata alerts.
★ 2.5ksovereign-dna. Your genome, your device. Fully local DNA analysis — no cloud, no telemetry.
★ 9ruse.sh. Rust port of the charm.sh TUI ecosystem
★ 2mpp-specs. Specifications for the Machine Payments Protocol - powered by the "Payment" HTTP authentication scheme
★ 85glamour. Stylesheet-based markdown rendering for your CLI apps 💇🏻♀️
★ 3.6kultraviolet. Mystical terminal user interface primitives 🌈
★ 361cantrip. the extensible, customizable, self-documenting, real-time multi-agent computing environment
★ 119irradiate. Fast mutation testing for Python, written in Rust
★ 4supercollider. An audio server, programming language, and IDE for sound synthesis and algorithmic composition.
★ 6.6kparameter-golf. Train the smallest LM you can that fits in 16MB. Best model wins!
★ 5.1kabsurd. An experiment in durability
★ 2.3khermes-agent. The agent that grows with you
★ 213ksystem-prompts-and-models-of-ai-tools. FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models
★ 142khelium. Private, fast, and honest web browser
★ 18khive. Multi-Agent Harness for Production AI
★ 11kLibCST. A concrete syntax tree parser and serializer library for Python that preserves many aspects of Python's abstract syntax tree
★ 1.9katheris. Python
★ 1.6kllmorpheus. new repository for the LLMorpheus project
★ 16clanker. autonomous systems engineering cli agent for any cloud environment: AWS, GCP, Cloudflare, etc
★ 371Marketing-for-Founders. Practical marketing resources to get the first 10 / 100 / 1000 users for your SaaS / App / Startup
★ 6.5kwikipedia-markdown-generator. A simple python script to convert any Wikipedia article to Markdown.
★ 64revealjs-skill. Coding agent skill for making reveal.js presentations
★ 369promptfoo. Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
★ 23khelios. TypeScript
★ 308staticfg. Python3 control flow graph generator
★ 216autoresearch. AI agents running research on single-GPU nanochat training automatically
★ 91ksemgrep. Lightweight static analysis for many languages. Find bug variants with patterns that look like source code.
★ 16kcode2flow. Pretty good call graphs for dynamic languages
★ 4.6kShadowbroker. Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to all but rarely aggregated in the open, until now.
★ 9.7ksimply. Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.
★ 541agentskills. Specification and documentation for Agent Skills
★ 23kjj. A Git-compatible VCS that is both simple and powerful
★ 30kratatui. A Rust crate for cooking up terminal user interfaces (TUIs) 👨🍳🐀 https://ratatui.rs
★ 22kmutmut. Mutation testing system
★ 1.3kcargo-mutants. :zombie: Inject bugs and see if your tests catch them!
★ 1.2krich_rust. Beautiful terminal output for Rust inspired by Python's Rich: tables, panels, syntax highlighting, progress bars, and full-color rendering
★ 72pi_agent_rust. High-performance AI coding agent CLI written in Rust with zero unsafe code
★ 1.3koh-my-pi. ⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
★ 17kpi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
★ 70kTensor-Slayer. Tensor-Slayer : Manipulate weights and tensors of LLMs to achieve performance upgrades and introduce a novel inferenceless mechanistic interpretability
★ 28safety-tooling. Inference API for many LLMs and other useful tools for empirical research
★ 132neuronpedia. open source interpretability platform 🧠
★ 1kcontrol-arena. ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
★ 208inspect_evals. Collection of evals for Inspect AI
★ 577Tapestry-Loom. A power user focused interface for LLM base models.
★ 76use-sound. A React Hook for playing sound effects
★ 3.2kterminal-notifier. Send User Notifications on macOS from the command-line.
★ 7.3kfirecrawl. The API to search, scrape, and interact with the web at scale. 🔥
★ 149kagent-browser. Browser automation CLI for AI agents
★ 38kskills. Give your agents the power of the Hugging Face ecosystem
★ 11kmodeling-api. KittyCAD Modeling API
★ 26heiretsu. Educational WIP
★ 73aesthetic-predictor. A linear estimator on top of clip to predict the aesthetic quality of pictures
★ 721deno_core. The core engine at the heart of Deno
★ 474libprocessing. An experimental implementation of the Processing API in Rust
★ 56rusty_art. Creative coding and visual illusions in Rust.
★ 220nannou. A Creative Coding Framework for Rust.
★ 6.7kp5.js. p5.js is a client-side JS platform that empowers artists, designers, students, and anyone to learn to code and express themselves creatively on the web. It is based on the core principles of Processing. Looking for p5.js 2.0? http://beta.p5js.org
★ 24kweathr. a terminal weather app with ascii animation
★ 2.9kgoatcounter. Easy web analytics. No tracking of personal data.
★ 5.8kobsidian-skills. Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.
★ 41kralph. Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
★ 21krubrics. a bunch of rubrics I made in different format and structure for llm judge and other use cases
★ 16slop-guard. Slop Scoring to Stop Slop
★ 150gsplat.js. JavaScript Gaussian Splatting library.
★ 1.6kpython-telegram. Python client for the Telegram's tdlib
★ 718Monolith. RLM for coding agent
★ 103onediff. OneDiff: An out-of-the-box acceleration library for diffusion models.
★ 2kcli. 📜 Entire CLI hooks into your Git workflow to capture AI agent sessions as you work. Sessions are indexed alongside commits, creating a searchable record of how code was written in your repo.
★ 4.7kpierre. pierre’s open source code
★ 5.4kelectrobun. Build ultra fast, tiny, and cross-platform desktop apps with Typescript.
★ 13k