GitHub Trending: AI, LLM, CLI & agent repos

VowpalWabbit/vowpal_wabbit

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

★ 8.7K+1 last 7 daysC++

machine-learning reinforcement-learning

View ↗

EvoMap/evolver

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

microsoft/TypeChat

TypeChat is a library that makes it easy to build natural language interfaces using types.

★ 8.7K+0 last 7 daysJavaScript

llm ai

View ↗

deeplethe/utopia

World's first open-source enterprise world model.

★ 8.7K+59 last 7 daysRust

llm rag

View ↗

WenyuChiou/awesome-agentic-ai-zh

A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。

bitsandbytes-foundation/bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

★ 8.5K+1 last 7 daysPython

llm machine-learning

View ↗

vaexio/vaex

Out-of-Core hybrid Apache Arrow/NumPy DataFrame for Python, ML, visualization and exploration of big tabular data at a billion rows per second 🚀

★ 8.5K+0 last 7 daysPython

machine-learning data-science

View ↗

qualcomm/GenieX

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

★ 8.5K+20 last 7 daysGo

llm local-ai

View ↗

jnMetaCode/superpowers-zh

🦸 AI 编程超能力 · 中文增强版 — superpowers（250k+ ⭐）完整汉化 + 4 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活

★ 8.5K+61 last 7 daysJavaScript

mcp claude-code

View ↗

Gentleman-Programming/gentle-ai

Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.

★ 8.4K+281 last 7 daysGo

llm mcp

View ↗

py-why/dowhy

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

★ 8.4K+7 last 7 daysPython

machine-learning data-science

View ↗

PriorLabs/TabPFN

⚡ TabPFN: Foundation Model for Tabular Data ⚡

★ 8.4K+42 last 7 daysPython

machine-learning data-science

View ↗

mikel-brostrom/boxmot

BoxMOT: Pluggable Python and C++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

★ 8.3K+5 last 7 daysPython

machine-learning deep-learning

View ↗

lmcinnes/umap

Uniform Manifold Approximation and Projection

★ 8.3K+2 last 7 daysPython

machine-learning visualization

View ↗

jev-chat/jev-chat-jarvis

The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill in with one tap. You press send. Android · Windows · macOS · iOS | 聊天辅助决策工具：先看懂对方再回复，发不发由你。

★ 8.3K+103 last 7 daysKotlin

llm ai-assistant

View ↗

GetStream/Vision-Agents

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

★ 8.2K+7 last 7 daysPython

ai ai-agents

View ↗

InternLM/lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

★ 8.1K+10 last 7 daysPython

llm llama

View ↗

osaurus-ai/osaurus

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

★ 8.1K+38 last 7 daysSwift

llm mcp

View ↗

LibrePhotos/librephotos

A self-hosted open source photo management service.

★ 8.1K+10 last 7 daysPython

machine-learning selfhosted

View ↗

repowise-dev/repowise

Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

★ 8.1K+31 last 7 daysPython

ai mcp

View ↗

FailproofAI/failproofai

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.

coroot/coroot

Coroot is an open-source observability and APM tool with AI-powered Root Cause Analysis. It combines metrics, logs, traces, continuous profiling, and SLO-based alerting with predefined dashboards and inspections.

★ 8.0K+4 last 7 daysGo

ai observability

View ↗

plastic-labs/honcho

Memory library for building stateful agents

★ 8.0K+134 last 7 daysPython

llm ai

View ↗

MaartenGr/BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

★ 7.9K+15 last 7 daysPython

machine-learning nlp

View ↗

steel-dev/steel-browser

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.

★ 7.9K+41 last 7 daysTypeScript

llm ai

View ↗

NirDiamant/Prompt_Engineering

22 prompt engineering techniques with hands-on Jupyter Notebook tutorials, from fundamental concepts to advanced strategies for leveraging LLMs.

★ 7.9K+10 last 7 daysJupyter Notebook

llm ai

View ↗

stanfordnlp/stanza

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

★ 7.9K+2 last 7 daysPython

machine-learning deep-learning

View ↗

aircrack-ng/aircrack-ng

WiFi security auditing tools suite

★ 7.9K+32 last 7 daysC

security audit

View ↗

flyteorg/flyte

Type-safe, distributed orchestration of agents, ML pipelines, and real-time inference on your k8s — in pure Python with async/await, also other languages (rust, go and ts)

★ 7.8K+21 last 7 daysGo

machine-learning mcp

View ↗

ParthJadhav/app-store-screenshots

end to end app store screenshot creation using AI

★ 7.8K+90 last 7 daysTypeScript

claude skills

View ↗

EricLBuehler/mistral.rs

Fast, flexible LLM inference

★ 7.8K+29 last 7 daysRust

llm uqff

View ↗

Human-Agent-Society/reef

Infrastructure for continually self‑improving agents

★ 7.8K+36 last 7 daysPython

llm ai-agents

View ↗

2FastLabs/agent-squad

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

Osmantic/ODS

ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.

★ 7.8K+58 last 7 daysPython

llm ai-agents

View ↗

mufeedvh/code2prompt

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

★ 7.7K+2 last 7 daysRust

llm ai

View ↗

tailcallhq/forgecode

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models

★ 7.6K+0 last 7 daysRust

llm openai

View ↗

BuilderIO/agent-native

A framework for building agentic apps

★ 7.6K+70 last 7 daysTypeScript

ai mcp

View ↗

xerrors/Yuxi

可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.

★ 7.6K+68 last 7 daysPython

mcp ai-agents

View ↗

ValueCell-ai/ClawX

ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal. China website is https://clawx.com.cn.

★ 7.6K+0 last 7 daysTypeScript

ai agents

View ↗

guardrails-ai/guardrails

Adding guardrails to large language models.

★ 7.6K+14 last 7 daysPython

llm ai

View ↗

agmmnn/awesome-blender

🪐 A curated list of awesome Blender add-ons, extensions, AI/MCP tools, tutorials, and 3D resources.

★ 7.6K+33 last 7 daysUnknown

awesome-list awesome

View ↗

open-compass/opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.

★ 7.6K+7 last 7 daysPython

llm evaluation

View ↗

HIPS/autograd

Efficiently computes derivatives of NumPy code.

★ 7.6K+4 last 7 daysPython

machine-learning deep-learning

View ↗

refly-ai/refly

The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.

★ 7.5K+6 last 7 daysTypeScript

agent codex

View ↗

traceloop/openllmetry

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

★ 7.5K+11 last 7 daysPython

llm open-source

View ↗

tw93/Waza

🥷 Engineering habits you already know, turned into skills AI assistants like Claude Code, Codex and Cursor can run.

★ 7.5K+59 last 7 daysPython

ai-agents claude-code

View ↗

h2oai/h2o-3

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.