Python agents

Your agent seeks what search can't find. A self-hosted perception MCP server that transcribes speech, reads behind logins, sees images and video frames, crosses languages, and remembers.

Open-source, white-label AI agent platform for agencies to deploy and manage branded WhatsApp agents across client accounts, with human handoff, knowledge bases, custom tools, and self-hosting.

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

Curated Claude Fable 5 use cases, tutorials, integrations, demos, and benchmark evidence with source links and multilingual README files.

命令行工具，用于查询和下载研究报告（行业研报、策略报告、宏观研究、券商晨报、个股研报），支持agent

中文公文与政务材料写作 Agent skill

OpenCode port of academic-research-skills: 4 skills, 13 slash commands, 38-agent pipeline for academic research, writing, peer review, and revision

734+ 网络安全技能中文翻译版 | AI Agent 网络安全技能库 | agentskills.io 开放标准

346 reusable character attributes for AI agent personas — compose, measure, and port system-prompt personas. Build once. Keep personality everywhere.

Multi-sport data science Agent Skills library. Portable judgment for sports modeling — doctrine, validation, leakage control, and honest evaluation.

Hermes Agent skill for Nextcloud - manage files, notes, calendar, tasks, and contacts via WebDAV and CalDAV

[ICML 2026] Milestone-Guided Policy Learning for Long-Horizon Language Agents

A simple, feasible repository to reproduce and learn self-evolving/recursive self-improvement agent.

gcov for what lines of code agents read

Link42 是一个 WireGuard 点对点链路管理面板，偏向 DN42、家庭网络和小型内网场景。主控使用 Docker 部署，节点侧运行 Agent，由主控下发 WireGuard 配置、启停任务、链路监测任务和连接中间层任务。

A CLI-based coding agent similar to Claude Code.

Give your AI coding agent a Roblox brain. Skill collection for Roblox Studio game development.

Author-in-the-loop toolkit for turning mature CFD evidence into defensible research directions, reproducible figures, and traceable scientific prose.

DeepTumorVQA benchmark for VLMs and Agents (10k testing samples)

Frontier ARC-AGI-3 agent: 99.86% RHAE, all 183 levels solved for $654

Epistemological database for agent and human efforts, beliefs, and findings.

Open-source Robot Agentic Layer

让 Agent 可以直接驱动你的Ansys HFSS 进行天线仿真

Codex-native harness with reusable agents, persistent multi-agent orchestration, and communication logs.

Autonomous Drosophila melanogaster (MaleCNS v1.0 / FlyWire) connectome agent playing Half-Life via biophysical LIF neural dynamics, 60x60 retina transduction, and DirectInput.

A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.

AI 辅助逆向工程工具清单，收录 MCP、Skill、插件、Agent 与工作站，覆盖 Web、二进制、移动端、浏览器自动化和流量分析。

Hermes Agent model-provider plugin: Claude Pro/Max subscription through the official Claude Code CLI (experimental)

Portable AI coding harness generator for Codex, Claude Code, OpenClaw, and generic AI CLIs. Creates workflow state machines, role agents, gates, artifacts, rules, context, and CLI adapters for structured AI-assisted development.

ACL 2026 Code and Skills for “AMA: Adaptive Memory via Multi-Agent Collaboration”.

codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testcase generation, browser replay & RCA.

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-with-feedback prompts.

Advanced MCP tool for Perplexity and OpenRouter API integration.

Open Source Embeddings Optimisation and Eval Framework for RAG/LLM Applications. Documentations at https://docs.vectorboard.ai/introduction

LangChain + LiteLLM that works

Qualitative Data Analysis done by AI (or LLMs). 🖥️ Streamlit & 🔗 Langchain

This Streamlit application provides a user interface for connecting to MCP (Model Context Protocol) servers and interacting with them using different LLM providers (OpenAI, Anthropic, Google, Ollama).

A telegram bot based on large language models (GPT-3) for image tasks like creating image, captioning, editing and general conversation like chatting about images based on stable diffusion, huggingface and langchain.

Introduction to LLM App Development Workshop: PDF Q&A App using OpenAI, Langchain, and Chainlit

An Example Plugin for ChatGPT, Utilizing FastAPI, LangChain and Chroma

Python framework for building scalable multi-agent systems with built-in orchestration, LLM integration, and intelligent task processing. Features dynamic scaling, fault tolerance, and advanced load balancing.

網頁聊天機器人 | tensorflow implementation of seq2seq model with bahdanau attention and Word2Vec pretrained embedding

整理：基于Rasa-NLU和Rasa-Core的任务型ChatBot

Conditional Sequence Generative Adversarial Network trained with policy gradient, Implementation in Tensorflow

AME IS DISCONTINUED, SEE: https://github.com/mochiagents/mochi

This package can be used to connect Telegram bot to AI engines such as OpenAI ChatGPT, Dall-E, Midjourney, Stable Diffusion, etc.

Python script that uses ChatGPT to automatically generate Confluence pages

Build a RAG dataset for your domain in just a few lines of codes, using your XML sitemap

Agent Studio is an AI agent application designed to handle real-time interactions through phone calls, web-based voice user interfaces (VUI), and SIP capabilities.

DeerFlow 2.0 Windows Native - 字节跳动 AI Agent 系统的 Windows 10/11 原生适配版，无需 Docker/nginx

TakedownGPT combines a LangChain Agent with OpenAI function calling to automate the discovery of domain registrars and drafting of takedown requests for malicious / copyright infringing domains.

A basic voice agent built with Python agents framework

Lane Changer Agent DQN

Local STT/TTS plugins for LiveKit Agents - no cloud APIs required

double (dostoevsky reference) local memory system for agents

This Reinforcement learning agent uses Policy-Gradient method to trade the market

I/O Mapper Agent

Code for paper "Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents"

TADtool is an interactive tool for the identification of meaningful parameters in TAD-calling algorithms for Hi-C data.

MCP-enabled AI conversation engine with MCTS analysis, FastAPI backend, and async operations for building advanced LLM applications

SafeChat Slack Bot is an open-source project designed to enhance data security within Slack workspaces.

Strawberry Groq is a streamlined demo application showcasing the power of chain of thought reasoning using PocketGroq. Experience the advanced capabilities of Groq's language models, enhanced by reasoning techniques inspired by OpenAI's "Strawberry" o1 LLM.

Streamlit Audio Transcription with OPENAI's Whisper Ai: An interactive Streamlit app demonstrating real-time audio transcription using OPENAI's Whisper Ai.

This tool has been deprecated. Use Agentic Document Extraction instead.

htop for AI coding agents — monitor token usage, costs, and workflows across Claude Code, Cursor, Kiro, Codex, and Copilot

This is the repo for the paper Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining.

Official implementation of the Neurocomputing paper "Multi-Vehicle Trajectory Prediction and Control at Intersections using State and Intention Information"

The Starcraft Multi-Agent challenge lite

Sliver agents for Mythic

Code Hacker - VS Code Custom Agent + Web + TUI

Faraday Agent Dispatcher launches any security tools and send results to Faradaysec Platform.

Zero-human, cold-start construction of long-chain agents in professional domains

🤖 Home Assistant custom integration for using webhook-based systems (e.g. n8n) as conversation agents and voice assistants.

Agent-to-Sim Learning Interactive Behavior from Casual Videos.

Agen is a minimalist language for agent loops and state machines.

DaveLovable The Most Advanced Open-Source AI Web Development Platform Build React applications at lightning speed with AI-powered multi-agent orchestration

A telegram AI Agent for managing Google calendar.

Real-time Slack ingest and MCP server to power your agentic Slack bots

A short set of exercises that showcase the usage of autogen to create agents

[ACL 2026] Code, benchmark and environment for "OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows"

[ACL 2026] LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark

Agentless Lite: RAG-based SWE-Bench software engineering scaffold

The Open Source Voice Agent Platform. Orchestrate ultra-low latency AI pipelines for real-time conversations over WebRTC.

深度优化多Agent自主执行编码 Harness 框架，支持从自然语言任务出发，完成任务规划、代码生成、自动验证与迭代修复闭环，并成功接入 Terminal-Bench 2.0 评测体系，任务完成率约 40%，榜单排名约 70。

[ICLR'26] Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

Benchmarking Language Agents Under Controllable and Extreme Context Growth

Browse & Inspect CLI agents : Claude Code, Codex, Gemini CLI code & conversation history

Sharepoint to text: A python-libraries which extracts the plain text from legacy and modern office documents and PDF. An enabling library for the agentic age which is driven more by Sharepoint content that you would think ...

A suite of open-ended, non-imitative tasks involving generalizable skills for large language model chatbots and agents to enable bootstrapped recursive self-improvement and an unambiguous AGI.

Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

Prediction market harness for AI agents — skills, MCP server, and Python SDK