ai-model
Projects tagged with ai-model on GitHub.
283 projects
system-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
nativ
SwiftLocal AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.
dify
TypeScriptBuild Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
klaatcode
TypeScriptOpen-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.
hflow
PythonSDK for robotics teams to verify the quality of their data used for AI model training.
chorus
TypeScriptMulti-LLM peer review for code decisions. Bring your own CLI; Chorus convenes 2-4 other LLMs to review the work before you ship.
muscriptor
PythonA multi-instrument music transcription model developed by Kyutai and Mirelo.
open-science
TypeScriptOpen Science is an open-source, local-first, model-agnostic AI research workbench for reproducible scientific research on macOS, Windows, and Linux.
LocalAI
GoLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
sloptrim
PythonA local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.
unlazy
JavaScriptAnti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
maka
TypeScriptApache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorded as an append-only log.
understory
TypeScriptunderstory — memory that grows. Self-wiring, plain-markdown memory for AI agents (MCP + local models + a living graph).
mdflux
PythonTurn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.
personal-model
PythonBuild your HUMAN.md.
generative-ai-for-beginners
Jupyter Notebook21 Lessons, Get Started Building with Generative AI
world-model-optimizer
PythonAn open source model gateway that provides one control plane across closed, open-source, local, and custom models.
MiMo-Code
TypeScriptMiMo Code: Where Models and Agents Co-Evolve
ComfyUI
PythonThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
ai-sdk
GoGrafana AI SDK for Go — streaming, tool-calling AI backends that speak fluent @ai-sdk/react
open-sheet
TypeScriptThe spreadsheet framework built for agents — write the model as React, export a live .xlsx. The third medium, after open-slide and open-doc.
langflow
PythonLangflow is a powerful tool for building and deploying AI-powered agents and workflows.
deepseek-reasonix
GoDeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
PixelRAG
Pythonhttps://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
OpenChatCut
TypeScriptOpen-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.
doc7
GoTurn documents into AI-ready Markdown with visual understanding
improve
Use your most capable model to audit your codebase and write plans for cheaper models to execute.
PerceptionBench
PythonPerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models
ollama
GoGet up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Soup
PythonFine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
brain2qwerty
PythonNon-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model.
unsloth
PythonLocal UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
Audio8_TTS
PythonSOTA-Class TTS at Compact Scale
cursed_browser
SwiftTrue AI-Native Browser — a VLM reads the HTML and hallucinates the page.
gemma-chat
TypeScriptLocal AI chat + coding agent for Apple Silicon, powered by Gemma 4 via MLX / Supports Ollama
labs-OO-Agents
PythonNVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.
barehands
HTMLMove things on your screen with your bare hands. A webcam-powered, hand-tracked interface for your AI. No headset. No controllers.
evonic
PythonOpen Agentic AI Platform - The home your agents deserve
OpenTag
TypeScriptOpenTag: The Channels SDK starter application, a self-hosted AI on-call triage bot for Slack and Microsoft Teams, built with AG-UI and LangGraph. Fork it and ship your own.
cumora
TypeScriptWhere agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.
langchain
PythonThe agent engineering platform.
DeepSpec
PythonDeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
transformers
Python🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
agent-as-a-router
TypeScriptThe official implementations of Agent-as-a-Router: Agentic Model Routing for Coding Tasks.
Flowise
TypeScriptBuild AI Agents, Visually
img2threejs
PythonRebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
apex-inference-chip
PythonAn inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.
local-llm
ShellEverything I know about running LLMs locally