AI Infra agents

Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps, and Mihomo VPN workflows.

Revenant - A 3rd party agent for Havoc that demonstrates evasion techniques in the context of a C2 framework

Reflexion: an autonomous agent with dynamic memory and self-reflection

Framework to bring LLM applications to production

该仓库主要记录 LLMs 算法工程师相关的顶会论文研读笔记（多模态、PEFT、小样本QA问答、RAG、LMMs可解释性、Agents、CoT）

专业的 LaTeX 简历模板，专为大模型与 Agent 算法工程师设计 | Professional LaTeX resume template for LLM & Agent algorithm engineers

Documentation of AnythingLLM by Mintplex Labs Inc.

AlphaAgent is an autonomous alpha mining framework.

[ICLR 2025 Spotlight] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs".

🔧 Repair JSON！Solution for JSON Anomalies from LLMs.

Build LangGraph agents like Next.js apps.

Azan + Prayer Time + MCP + AI Agents + Islamic + Salah + A lightweight MCP library to calculate prayer times and trigger Azan with a single tool call. If you’re building an AI agent or prayer application, there’s no need to deal with astronomical calculations, timezones, or edge cases again.

Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)

A-MEM: Agentic Memory for LLM Agents

Embedded agents your customers use to automate work, build views, and connect their tools.

Tooling to build LLM applications: prompt templating and composition, agents, LLM memory, and other instruments for builders of AI applications.

Atlas World：一個實驗級 AGI 文明框架，包含憲法、安全卷與多代理協議的完整設計。Atlas World – Experimental AGI civilization framework: constitution, safety volume, multi-agent governance and simulation ethics.

Jupyter Notebooks for Mastering LLM with Advanced RAG Course

Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide.

Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.

ERNIE Bot Agent is a Large Language Model (LLM) Agent Framework, powered by the advanced capabilities of ERNIE Bot and the platform resources of Baidu AI Studio.

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

distill any book down to its spine

This document is a compilation of best practices for AI-Native development, curated by our community. Discover useful tips and tricks for leveraging tools to improve your AI development process.

ARCHIVED! A chatbot framework written in Go. All configurations are made in YAML files, or inside scripts written in your favorite language.

Browser based tool to convert PDFs to Markdown

The functional, composable, and typescript-first AI Agent framework for real-world LLM Apps.

OpenAI-compatible Python client that can call any LLM

siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems

AutoHarness: Automated Harness Engineering for AI Agents

A Massively Parallel Large Scale Self-Play Framework

🦛 CHONK your texts with Chonkie ✨ Type-friendly, light-weight, fast and super-simple chunking library

Agent Learning Framework https://alf.readthedocs.io

Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

[ACL 2024 Findings] MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning https://arxiv.org/abs/2311.10537

一个本地优先的AI知识库系统（RAG），用于把本地文档接入辅导搜索与大模型对话流程。目前支持md、txt、pdf（文本）、xlsx、cvs类型。支持mcp服务

transformers safetensors llama text-generation facebook meta

[ACL2024 Findings] Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

Official repository for "DynaSaur: Large Language Agents Beyond Predefined Actions"

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

A comprehensive set of LLM benchmark scores and provider prices. (deprecated, read more in README)

MCP Toolkit for Flutter AI Agent Driven Development (MCP/CLI + custom client side tools) - via closed feedback loop (visual & semantic snapshot) and high client side customization adaptable for any Flutter app. Nowadays it is often called as agentic harness.

Recipes for learning, fine-tuning, and adapting ColPali to your multimodal RAG use cases. 👨🏻‍🍳

Automate your mobile devices with natural language commands - the counterpart android app for the mobilerun framework

中文论文常用排版格式Skills，适用于课程论文、数模竞赛、毕业论文等场景，让llm agent写word论文或者将.md转.docx时可调用

transformers safetensors llama text-generation conversational arxiv:2403.04652

static region:us

Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

Agent Framework Samples - showcasing ways in which agent framework can be utilized.

Chatbot framework

Hermes Agent setup, migration, LightRAG, Telegram, and skill creation guide

This is the official repo for "PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization". PromptAgent is a novel automatic prompt optimization method that autonomously crafts prompts equivalent in quality to those handcrafted by experts, i.e., expert-level prompts.

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Build full-stack, type-safe, LLM-powered apps with the T3 Stack, Turborepo, OpenAI, and Langchain

SpringAI，LLM，MCP，Embedding

Repo for paper "Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration"

MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding

gradio region:us

Markdown for the AI era

Drag & drop UI to build and run a flow of autogen AI agents

Plan-Validate-Solve (PVS) Agent for accurate, reliable and reproducable workflow automation

AdaRubric: Adaptive Dynamic Rubric Evaluator for Agent Trajectories

Restack AI examples for Python

A Production-Ready Framework for Building Composable AI Agents

A lightweight SwiftUI chat UI framework with 11 built-in message types, 8 themes, and cross-platform iOS/macOS support

Setup and run a local LLM and Chatbot using consumer grade hardware.

Let AI think and express like you. This framework provides a complete assembly line: from the noise processing of original chat records, to the seamless switching of multi-model adaptation layers, to local lightweight fine-tuning (LoRA).

Agent benchmark for medical diagnosis

Build AI agents that run for hours, not seconds. Async-first Python harness: auto context-compaction, cost budgets & death-spiral guards, persistent cross-session memory, self-evolving SKILL.md, /goal long-task loop, 40+ tools, 20+ models, MCP/ACP. Ships a CLI + Web Gateway out of the box.

AI agent skill that transforms dream descriptions into cinematic videos — auto-generates prompts, submits to Jimeng via browser automation, and downloads finished videos with post-processing effects.

Automatically reformat any JSON into any schema with AI

syftr is an agent optimizer that helps you find the best agentic workflows for your budget.

Open-source, free, multi-platform, one-click deploy, AI Agent–integrated personal bookmarking system｜完全开源、免费、多端、一键部署、AI Agent 集成的个人收藏夹系统

🦛 CHONK your texts with Chonkie ✨ Type-friendly, light-weight, fast and super-simple chunking library

⛓️ build cognitive systems, pythonic

Laddr is a python framework for building multi-agent systems where agents communicate, delegate tasks, and execute work in parallel. Think of it as a microservices architecture for AI agents — with built-in message queues, observability, and horizontal scalability.

[CVPR2024] ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts

9 Different Ways to Optimize AI Agent Memories

ChatGPT Plugin starter template built with Next.js 13 App Router, Edge Functions, and Vercel

Chatbot system for Final Year Project. Chatbot made in Python using Natural Language Toolkit especially Machine Learning. Easy to Understand and Implement.

Cloud-native agent-as-a-service framework with one-click IaC deployment.

⚡ Local chat assistants with AI superpowers

MoLing is a computer-use and browser-use based MCP server. It is a locally deployed, dependency-free office AI assistant.

Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

Generate a full-stack Next.js app from an AI prompt

gradio region:us

基于seq2seq模型的简单对话系统的tf实现，具有embedding、attention、beam_search等功能，数据集是Cornell Movie Dialogs

Give you decision-ready references for the most common AI engineering problems

Reference implementation of a RAG-based documentation helper using LangChain, Pinecone, and Tavily..

The production-ready agent harness framework for Python

Canonical source and governance toolkit for Zhijian AI public Agent Skills

transformers safetensors llama text-generation nvidia chatqa-1.5

A repository of examples using Python AI Agent frameworks that work with GitHub Models and Azure OpenAI.

smart-llm-loader is a lightweight yet powerful Python package that transforms any document into LLM-ready chunks. Spend less time on preprocessing headaches and more time building what matters. From RAG systems to chatbots to document Q&A, SmartLLMLoader handles the heavy lifting so you can focus on creating exceptional AI applications.

When RAG and agents fall in love

Extracted artifacts from Kimi OK-Computer (and other agents) system for AI studies in agentic architecture.