Python agents

Embodied-intelligence simulation backend for multi-agent orchestration and Unreal Engine integration.

Your durable workspace across AI agents.

EcoAssistant: using LLM assistant more affordably and accurately

A LLDB plugin which brings LLMs to LLDB

A Python SDK for claude-code hooks

LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing, optimized for cloud deployment.

Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, retries, circuit breakers, key rotation, singleflight, and Python/TypeScript/Rust parity.

Completely local RAG. Chat with your PDF documents (with open LLM) and UI to that uses LangChain, Streamlit, Ollama (Llama 3.1), Qdrant and advanced methods like reranking and semantic chunking.

A customizable Retrieval-Augmented Generation (RAG) implementation using Ollama for a private local instance Large Language Model (LLM) agent with a convenient web interface

Python Hydraulic Modeling Tools - 2D

Human memory, for agents. Scalable, private, personal knowledge base for any LLM provider.

About Facebook Chat (Messenger) for Python / Message Listening for E2EE (end-to-end)

AerialClaw: Towards General Intelligence for Autonomous Aerial Agents

"Never send a human to do a machine's job" - Open Source AI hacking agent

SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A3B FP8 ~240 tok/s, 27B-int4 hybrid GDN+Mamba, Gemma4 26B/31B AWQ, 256K ctx. 321 patches: TurboQuant k8v4 KV, MTP/DFlash spec-decode, FULL cudagraph, hybrid GDN. vLLM pin dev424 + Control Center GUI.

[COLM 2026] A Scalable Agentic RL Training Framework for Deep Research Agent

An open toolkit and public dataset hub for collecting, sanitizing, analyzing, and visualizing coding agent traces.

transformers safetensors qwen2 text-generation RLHF Nexusflow

transformers gguf llama llama-2 text-generation code

Security first LLM gateway and guardrails for AI applications, agents and AI powered IDEs

DeepSeek Harness (DSH) Python 教程：17 章从零实现 Agent Loop、插件系统、工具调用、Session、上下文工程、Subagent 与 Headless CLI

Agent2 — An autonomous AI agent for coding, cybersecurity, terminal automation, and intelligent task execution.

Open-source writing skills for Claude Code, Codex, OpenCode, Antigravity, Gemini, OpenClaw, and Hermes. Your creativity. Your agent. Your book.

A code implementation for our arXiv paper "Multi-agent Adhoc Team Play using Decompositional Q function"

Talk to your Obsidian notes!

An Implementation of 'Attention is all you need' with Chinese Corpus

A set of 🚀🚀🚀 components to be used with Botfront and/or Rasa

A Deep-Learning multi-purpose chatbot made using Python3

Train an adapter for any embedding model in under a minute

some Multiagent enviroment in 《Multi-agent Reinforcement Learning in Sequential Social Dilemmas》 and 《Value-Decomposition Networks For Cooperative Multi-Agent Learning》

A command-line personal assistant that integrates with Google Calendar, Gmail, and Tasks to help manage your digital life.

Scrappy assistant that automates web3 bug hunting workflows. Tracks ongoing bug bounties and launches autonomous agents that can perform arbitrary tasks.

Automated Miulti AI Agent for company research with LangGraph— scrapes web data, extracts business insights, and generates structured reports using LLM analysis.

Rewriting Project Claw Code — Python rewrite of Claude Code agent harness. Forked from instructkr/claw-code.

Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collaboration via bridge scripts with session continuity.

Simple AI-powered trading bot for Robinhood

Medea: An AI agent for therapeutic reasoning across biological contexts

ChinaTravel: A Real-World Benchmark for Language Agents in Chinese Travel Planning

Deterministic research MCP server on FastMCP 3 — 5-engine web search, 9-platform social search, 6 academic DBs, news aggregation, entity profiles, conflict detection, document analysis. No API keys. No in-server LLM. Structured outputs for agent chaining.

13 Claude Code skills for video production (transcribe / translate / dub / multicam / subtitles / reframe) + WeChat publishing. Compatible with Claude Code, OpenAI Codex CLI, Cursor, Gemini.

gguf code codeqwen chat qwen qwen-coder

aws-bench measures how well AI agents and model combinations perform on real AWS work — diagnosing misconfigurations, provisioning infrastructure, and operating live cloud environments.

Supervised, Hermes-native penetration testing profile with 35 routed playbooks, guarded target execution, persistent engagement state, evidence-backed findings, and release-gated reporting.

Multi & Single Agent Reinforcement Learning for Traffic Signal Control Problem

Extract structured data from any content using LLMs.

Coding agent for code modernization

[ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Курс "Разработка AI/LLM-приложений на Python: от идеи до релиза" предоставляет слушателям возможность пройти через полный цикл создания LLM-приложений, от идеи до релиза. В рамках курса вы познакомитесь с передовыми технологиями и инструментами, такими как Mistral AI API, LangChain, Arize Phoenix, FastAPI, PostgreSQL и Docker и т.д

AI agent平台开发 --以测试 方向为例，搭建了一套 harness 可落地方案，不需要手写一段代码，企业级通用 AI 智能体平台框架（平台控制面 + LangGraph 运行时），可以在这个基础轻松二次开发

AI 解说大师 — CLI 客户端；用于终端调用视频解说生成 API

6,000+ curated spinner verbs and spinner phrases for Claude Code across 151 themed categories

one Memory across your devices and apps

transformers safetensors qwen2 text-generation chat conversational

transformers safetensors qwen2 text-generation code codeqwen

Nobody ships AI slop on purpose. These skills make sure you don’t.

A Python Package to Access World-Class Generative Models

Examples on how to use various LLM providers with a Wine Classification problem

General-purpose AI agent that acts via code actions through a unified execution interface.

[ICLR 2026] InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents

LLM prompt language based on Jinja. Banks provides tools and functions to build prompts text and chat messages from generic blueprints. It allows attaching metadata to prompts to ease their management, and versioning is first-class citizen. Banks provides ways to store prompts on disk along with their metadata.

BioDiscoveryAgent is an LLM-based AI agent for closed-loop design of genetic perturbation experiments

A WhatsApp AI Agent powered by LangGraph, FastAPI, and Groq. Acts as an empathetic therapist, Dr. Sofia, handling text and voice messages with natural conversations. Supports multi-language, PostgreSQL-backed memory, and real-time synthesis.

A professional research suite for conducting rigorous academic research using specialized agents and multi-platform CLI commands. Compatible with Claude Code, Gemini CLI, OpenAI Codex, and OpenCode.

Personal Context Manager for Claude Code. Your life in walnuts.

An simple, reliable, and minimal implementation of the AI CoScientist Paper from Google "Towards an AI co-scientist" with Swarms Framework

File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.

Unofficial AI-powered Plex playlist generator with library awareness. Every track it suggests, you actually own.

LLM-powered Crypto Trading Framework with Vision AI chart analysis, real-time Neural Engine, and a live monitoring dashboard at semanticsignal.qrak.org. Features memory-augmented reasoning and professional risk metrics.

Ray Fernando's collection of Skill files for AI coding agents. First up: running-bug-review-board, a real-user QA workflow with a Bug Review Board (BRB) feedback loop.

static region:us

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

Turn ideas into autonomous research with Git-like evidence histories—inspectable, reproducible, and reversible.

An agent-native CAD SDK for language models to create, inspect, and reconstruct complex, editable 3D models.

The best-benchmarked open-source memory system for AI coding assistants

tensorflow+bert+seq2seq 周公解梦。AI遇上玄学，说出你的梦境(dream)，模型自动解析decode梦境的征兆。类似聊天机器人(chatbot，QA)，你问我答。

Bulk summarization of documents using ChatGPT API

A command line chat bot using the ChatGPT API from OpenAI

A reference application for a local AI assistant with LLM and RAG

A framework for the creation of autonomous agent services.

The open source trading arena

Circuitron: Agentic PCB Design Accelerator — Generate, plan, and layout circuits from natural language prompts.

Typst skill for agents.

RS-Agent: An LLM-driven Remote Sensing Intelligent Agent

Multi-agent AI scientist that turns experimental data into > publication-ready research papers.

VYNN AI Agent Backend is a standalone agent execution system for financial analysis. It orchestrates LLM-based agents to scrape historical financial data, build valuation models, analyze real-time financial news, and generate structured financial reports, with a focus on modularity and reproducible execution.

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.

transformers pytorch safetensors llama text-generation license:other

transformers safetensors gemma4_unified_assistant text-generation any-to-any arxiv:2607.02770

ClipTalk —— 通过对话完成视频剪辑的 AI Agent。说句话，片子就剪好了。ClipTalk — An AI agent that edits videos through conversation. Just say it, it's edited.

transformers pytorch safetensors llama text-generation facebook

Automate your job: local-first AI task hub. Email, Teams, Slack & reports -> one timeline -> AI triage -> your coding agents (Claude Code, Codex, Gemini) do the work, you approve.

🎉 Congratulations! This work has been accepted for publication as a Findings paper at ACL 2026! Mistake Notebook Learning (MNL) is a novel, training-free memory framework that enables Large Language Model (LLM) agents to systematically learn from their mistakes

A Model Context Protocol server implementation for operations on AWS resources

OCode is a sophisticated terminal-native AI coding assistant that provides deep codebase intelligence and autonomous task execution

A langchain based tool to allow agents to dynamically create, use, store, and retrieve tools to solve real world problems

Read translation intelligent agent for Google Mail academic paper subscription

🔥 Token-efficient JSON alternative for LLMs & agentic AI — same data, fewer tokens. Python · JS/TS · Rust · Go · C++

LangChain 을 더 쉽게 구현하기 위한 유틸 함수, 클래스를 만들어서 패키지로 배포하였습니다.