Python agents

A policy runtime for AI agents.

Bring Claude's Skill system to any MCP-compatible AI agent through progressive disclosure. Universal, standards-based, and easy to use.

A powerful AI agent for browser-based interactions powered by Fireworks AI models. Navigate the web, extract content, analyze websites, and provide intelligent feedback based on what it sees. Features web navigation, content extraction, SEO analysis, and an interactive UI leveraging high-performance vision and language models.

MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection

Checkmk special agent for checking unifi controller

The game snake (for playing by yourself run snake_env.py). Deep Reinforcement Learning agent learns to play the game (run agent_1.py)..

NAIL is an agent that plays text-based interactive fiction games.

Training Language Model Agents to Find Vulnerabilities with CTF-Dojo

Lumigo's Python Distributed Tracing and Performance Agent for AWS lambda

Generate CS2 signatures via Agent SKILLS with ida-pro-mcp

Agent for scheduling event generating processes and sending the results to Riemann

Code of the NeurIPS 2021 paper: Language and Visual Entity Relationship Graph for Agent Navigation

The resources for EMNLP-20 paper 'Profile Consistency Identification for Open-domain Dialogue Agents'

PGR is an experimental, stateless MCP code-search server for studying how ranking, latency, and output shaping affect agentic search.

OpenAI-compatible proxy for assistant-ui.com free LLM endpoint. Supports streaming, tool calling, vision, and 5 models.

This repository hosts a collection of custom web applications powered by OpenAI's GPT models (incl. o1, o3-mini, GPT-4.5, GPT-4o, and GPT-4o mini), Whisper model, and TTS model. These apps include an interactive chatbot ("Talk to GPT") for text or voice communication, and a coding assistant ("CodeMaxGPT") that supports various coding tasks.

Utilizing a LINE Bot integrated with LangChain in Python to assist with stock price inquiries.

Makes a improved prompts from a basic prompt

This repository provides a minimal, single-file implementation of SingLoRA (Single Matrix Low-Rank Adaptation) as described in the paper "SingLoRA: Low Rank Adaptation Using a Single Matrix" by Bensaïd et al.

Microsoft chatbot build using NLTK-Chatbot and django

Automate PR reviews with LLMs like OpenAI GPT and Google Gemini. Supports multilingual reviews, file exclusions, and custom model selection. Simple setup, smarter code reviews!

Sample with MCP-based Agent for practice

build_startup_using_AI_Agents

Official implementation of Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning at ICML 2021.

Terminal Agent is a DevOps-focused intelligent terminal assistant for system diagnostics, application deployment, service monitoring

Code for sim-to-real transfer of a pretrained Vision-and-Language Navigation (VLN) agent to a robot using ROS.

PoC for a Havoc agent/handler setup with all C2 traffic routed through GitHub. No direct connections: all commands and responses are relayed through Issues and Comments for maximum stealth.

The official repository of "ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models"

One prompt. Full delivery.

SQL-like query language and CLI for Qdrant vector search engine

Repository containing RL environment, model and trainer for GNN demo for ICRA 2022 paper "A Framework for Real-World Multi-Robot Systems\\Running Decentralized GNN-Based Policies"

[ICLR 2026 LLM Reasoning Workshop] Benchmarking agent reasoning capabilities in physical interactions, tool usage, and multi-agent coordination.

livekit agent plugins

MongoDB Agents with Google ADK

[ACL 2025] AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant

⛵️ Yet another lightweight agent sandbox runtime, support python interpreter, shell, file system components, etc. 🏖️

Whispers in the Machine: Confidentiality in Agentic Systems

🔁 AI-powered translator for gettext .po files using OpenAI, Azure OpenAI, Claude, DeepSeek and Ollama, supports bulk, fuzzy cleanup, and language auto-detection.

Declarative Document Indexing (DDI) framework for Python. Define schemas, extract structured indices, search smarter.

Write detections, investigate alerts, and query logs from your favorite AI agents

ARC Relay — WebSocket relay server for agent remote control by Axolotl AI

Starter template to develop agents for Agent Stack

Software repo for Team Expander Agent (Oregon State U., Institute for Systems Biology, and Penn State U.)

Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.

OSCAL tools for AI agents

Flakestorm — Automated Robustness Testing for AI Agents. Stop guessing if your agent really works. FlakeStorm generates adversarial mutations and exposes failures your manual tests and evals miss.

Self-hosted portfolio journaling and agent-driven stock research: reproducible experiments, backtesting, durable jobs, API/CLI/MCP extensions, and multi-currency tracking.

FIBO-Edit brings the power of structured prompt generation to image editing

Official code implementation of the paper: QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation

AI Agentic API Testing Platform - Automated testing with specialized ephemeral agents

This is AI implementation (not official) of the DreamGym framework from the paper "Scaling Agent Learning via Experience Synthesis" (arXiv:2511.03773).

Make your agents learn from experience. One protocol for weights, harness and routing.

A self-contained MCP server in docker that combines the Crawl4AI, SearXNG, and Supabase to provide AI agents and coding assistants with complete web search, crawling, and RAG capabilities.

The set of AI agent model implementations, benchmarks, and others used in our paper "The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective"

This is the repo for the paper A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression

Automatos AI: Open-source platform for advanced context engineering and multi-agent orchestration in enterprise automation. Built on frontier research in RAG, vector embeddings, cognitive tools, emergent symbols, and neural field theory—powered by FastAPI, Next.js, and PostgreSQL.

Personal AI agent harness powered by Claude Code. Always-on access through Discord, Telegram, or a built-in web UI.

An AI agent that controls your Flipper Zero that uses PyFlipper, LightLLM, RAG, and can connect to your local Ollama instance!

Give your AI agent eyes and hands on any desktop — cross-platform accessibility API with MCP server

AI Agent Skills for Google Play Console CLI (gplay)

AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results

An open standard by LiveRamp defining how intelligent agents exchange user context, enabling interoperability from prompt-based LLM coordination to embedding-based optimization.

Oracle AI Data Platform Workbench Samples

Build AI agents with Google's Agent Development Kit (ADK). 20 modules from basics to advanced topics.

🕵️‍♂️ Privacy-focused AI job scraper, local storage, and interactive dashboard. Auto-scrapes AI/ML roles from top companies using ScrapeGraph-AI + LLM and LangGraph Agents, filters for relevance, and provides a Streamlit UI for tracking applications. Built for developers seeking AI careers.

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any scenario in one line. Claude / Codex / Cursor / Hermes. Zero LLM, zero network, zero deps.

Autonomous GUI agent — give it a task, it operates the desktop. Visual memory, one-shot UI learning. Built for OpenProgram.

AgenticPay: A Multi-Agent LLM Negotiation System for Buyer–Seller Transactions

Code for Paper: Benchmarking Multi-step Scientific Tool-use in LLM Agents

智能体系统设计与实战：基于langchain与langgraph，Agent System Design and Practical Applications: Based on LangChain and LangGraph

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Multi-tenant LangGraph runtime that isolates each business's agent, catalog, tools and LLM across Telegram, Instagram, WhatsApp and web.

Your local-first AI ad ops crew. Works with Claude Code, Cursor, Codex & Gemini.

Zettelkasten knowledge base template for Claude Code projects. Bootstrap + interactive interview.

AgentDNS-lite-client is a lightweight command-line tool for interacting with the AgentDNS network. It enables fast querying and invocation of intelligent agents directly from your terminal.

LangGraph-powered agents for offer hunting, workflow automation, and memory-assisted job search.

Codes and data for paper: GrepSeek: Training Search Agents for Direct Corpus Interaction

This Guidance provides a sample foundation for building real-time voice AI agents on AWS. It demonstrates how to build a voice assistant that handles phone calls and voice interactions in web and mobile applications via WebRTC.

Persistent memory and codebase intelligence for AI coding agents, indexes symbols, tracks sessions, and exposes structured project knowledge through an MCP server so agents stop re-reading files and start building on what they already know.

A practical, no-hype workflow for AI coding agents: context, plan, implement, review, QA, ship, retro. Templates, two Claude Code skills, and a 40% context rule - every claim traced to official docs.

[ICLR 26] Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow

A research-informed AI agent composition, assignment, and evolution engine.

Dont guess. Simulate. Multi-agent market prediction engine.

VoidClaw is a universal autonomous AI command centre that runs seamlessly on Windows, Mac, Linux, and Android. It acts as a local-first digital assistant that manages your files, automates web tasks, and controls your devices with an evolutionary memory that adapts to your unique workflow.

Ontology-based MCP server that analyzes database schemas (PostgreSQL, Snowflake, ClickHouse, Dremio) and generates RDF/OWL ontologies with SQL mappings for fan-trap-free Text-to-SQL.

Official benchmark reproduction code for the SAG paper

Açıklama: Self-evolving Hermes agent that writes, tests, and publishes reusable Skills autonomously. Uses Memory + Skills + Atropos RL.

RE:从0开始的RAG学习生活。包含LangChain、LangGraph、LangSmith、PydanticAI等框架和工具的学习教程。

让 Claude Science 一键接入 DeepSeek、硅基流动 Kimi、OpenAI 等第三方 API 的 macOS 本地代理与安装器

Открытый бенчмарк LLM: какая нейросеть лучше пишет код 1С:Предприятие (BSL). Объективная оценка LLM по методике SMOP с реальным исполнением в 1С — Claude, GPT, Gemini, DeepSeek, YandexGPT, GigaChat.

Open-source, voice-first AI mock interviewer. Upload your CV + a job description, practice out loud with an adaptive multilingual interviewer, get scored and coached on your weak areas. LiveKit · LangGraph · Next.js

gradio region:us

docker region:us

transformers pytorch llava text-generation region:us

gradio region:us

gradio region:us

gguf text-generation base_model:cerebras/Qwen3-Coder-REAP-25B-A3B base_model:quantized:cerebras/Qwen3-Coder-REAP-25B-A3B endpoints_compatible region:us

transformers gguf quantized vlm vision agentic

transformers gguf code expert-pruning moe qwen3.6