spec-kit
github
💫 Toolkit to help you get started with Spec-Driven Development
Home › Category
💫 Toolkit to help you get started with Spec-Driven Development
Self-hosted AI workspace.
VS Code in the browser
An AI Hedge Fund Team
No fortress, purely open ground. OpenManus is Coming.
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds…
No description provided.
Kronos: A Foundation Model for the Language of Financial Markets
GitHub's official MCP Server
Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
🤗 smolagents: a barebones library for agents that think in code.
Algorithm powering the For You feed on X
Lightweight server monitoring with historical data, docker stats, and alerts.
Contexts Optical Compression
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model…
npx ccusage
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
Lets make video diffusion practical!
Apprise - Push Notifications that work with just about every platform!
Train your AI self, amplify you, bridge the world
Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase
Perfect Green Screen Keys
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
Offline, privacy-first grammar checker. Fast, open-source, Rust-powered
Transform your favorite cities into beautiful, minimalist designs. MapToPoster lets you create and export visually striking map p…
Minimal reproduction of DeepSeek R1-Zero
Your AI trading terminal assistant for US stocks, commodities, forex, and crypto.
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and…
IronClaw is an Agent OS focused on privacy, security and extensibility
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
No description provided.
OCR model that handles complex tables, forms, handwriting with full layout.
A fast, helpful, and open-source document parser
🦎 a tool to build and deploy software on many servers 🦎
A beautiful, powerful, self-hosted rom manager and player.
Spark-TTS Inference Code
Official repository for LTX-Video
Kimi Code CLI is your next CLI agent.
PersonaPlex code.
Distributed, offline-first bug tracker embedded in git
Self-hosted collection of powerful web-based tools for everyday tasks. No ads, no tracking, just fast, accessible utilities right…
High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboar…
Fully local web research and report writing assistant
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Local voice clone, video dubbing, dictation and audiobook maker. The open-source ElevenLabs alternative.
Native and Compact Structured Latents for 3D Generation
🛜 ESPectre 👻 - Motion detection system based on Wi-Fi spectre analysis (CSI), with Home Assistant integration.
Sharp Monocular View Synthesis in Less Than a Second
VSCode theme based off the easemate IDE and Jetbrains islands theme
The most user-friendly OpenID Connect Certified™ and OAuth 2.0 provider that lets users sign in to your applications with passkey…
High-Quality Voice Cloning TTS for 600+ Languages
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"
Google Workspace in your terminal.
Lore is a next-generation, open source version control system
⚡ A fast Git hook manager written in Rust, designed as a drop-in alternative to pre-commit, reimagined.
The tiniest OpenID Certified™ authorization and authentication server you have ever seen.
A TTS that fits in your CPU (and pocket)
Personal AI, On Personal Devices
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
A 5-20x faster experimental Homebrew alternative
Bare metal to production ready in mins; your own fly server on your VPS.
GLM-OCR: Accurate × Fast × Comprehensive
⚡️A native, local-first alternative to Logitech Options+, written in Rust 🦀 — remap buttons, DPI, and SmartShift over HID++. No…
No description provided.
git push no-mistakes
Fast and lightweight DNS proxy as ad-blocker for local network with many features
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
No description provided.
A continuation of HomeBox the inventory and organization system built for the Home User
On-device TTS model by Neuphonic
An interactive Formula 1 race visualisation and data analysis tool built with Python! 🏎️
Public repository of the Micro QuickJS Javascript Engine
Depth Anything 3
A rust implementation of the Quip Network's quantum virtual machine.
A feed-forward 3D foundation model for reconstructing scenes from streaming data
OpenClaw-RL: Train any agent simply by talking
DFlash: Block Diffusion for Flash Speculative Decoding
A simple GUI client to manage a Quip Network node
A simple server monitor tool.
"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)
General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
Open-source vacuum robot cleaner
No description provided.
The Programming Language for Agents
Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0
No description provided.
A powerful cross-platform port management tool for developers. Monitor ports, manage Kubernetes port forwards, integrate Cloudfla…
A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.
Read-only developer endpoint scanner for on-disk package, extension, and developer-tool metadata, built to check exposure to know…
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Portable, lightweight, self-contained virtual machine.
Our library for RL environments + evals
autonomous harness engineering
Write like a high-level language, run like C.
PaperSpine is a motivation-driven skill for learning from strong academic papers, building a paper’s central argument, and rewrit…
Advancing Open-source World Models
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and archite…
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
🌱 Private, quiet space for thinking. Simple app for .md files.
No description provided.
PostgreSQL extension for BM25 relevance-ranked full-text search. Postgres OSS licensed.
Ministack: Free, open-source local AWS emulator - 55+ services, Terraform compatible, real databases. Free forever. MIT license…
HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026
"Paper2Slides: From Paper to Presentation in One Click"
[CVPR 2026 Oral] VGGT Omega
Store your data from all your accounts and devices in a single cohesive timeline on your own computer
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
No description provided.
Speakr is a personal, self-hosted web application designed for transcribing audio recordings
[CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming
"Single-image Layer Decomposition for Anime Characters" (SIGGRAPH 2026 Conference Paper)
A modern selfhosted media management system for your media library
Specification and documentation for the Universal Commerce Protocol (UCP)
Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual spee…
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
Visual Causal Flow
Miso TTS is an 8 billion, highly emotive text-to-speech model
Wizarr is an advanced user invitation and management system for Jellyfin, Plex, Emby etc.
The fast all-in-one Node.js toolkit
Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.
Agent harness to make your slop code well-engineered and beautiful.
SQLite extension + bindings for Postgres NOTIFY/LISTEN semantics with durable queues, streams, pub/sub, and scheduler
Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages
No description provided.
No description provided.
Shadow any website for offline viewing, with the JavaScript stripped out
cliamp - Terminal music player inspired by winamp
Self-referential self-improving agents that can optimize for any computable task
Ideogram 4: Open image model at the forefront of design
[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
Official inference repo for FLUX.2 models
Library for reducing tail latency in RAM reads
Long Video Gen Infrastructure
HY-Motion model for 3D human motion or 3D character animation generation.
PyTorch implementation of JiT https://arxiv.org/abs/2511.13720
High Fidelity Detection Mechanism for RSC/Next.js RCE (CVE-2025-55182 & CVE-2025-66478)
An interface library for RL post training with environments.
Drive the full lifecycle of AI-assisted development — from idea to shipped code.
No description provided.
A collection of daily coding challenges designed to help you master idiomatic Go through deliberate, repetitive practice.
LUPINE is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.
Automatic Video Generation from Scientific Papers
Pre-submission compliance scanner for the Apple App Store
Diagram as Code Tool Written in Rust with Draggable Editing
"FastCode: Accelerating and Streamlining Your Code Understanding"
An experiment in durability