Python agents

AI agent-native observability and debugging for Django.

AI-powered synthetic data generation — structured tables, unstructured documents, multi-provider LLM support, referential integrity, and code-gen mode for millions of rows

gradio region:us

A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.

A naive webui for ChatGLM

A multi-agent AI research system designed to know what it knows (and doesn't know) when conducting research and creating content.

Use DALL·E 2 in Python

AI Chat in Terminal + Package + REST-API

A solution guidance for Generative BI using Amazon Bedrock, Amazon OpenSearch with RAG

[NeurIPS 2024] Behavioral Topology (BeTop), a multi-agent behavior formulation for interactive motion prediction and planning

[ACL 2026 Oral] UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities

Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI, opencode).

Agent Skills lifecycle toolkit: mine repeated coding-agent workflows, audit and personalize skills, and generalize personal skills for public release.

An open-source engineering governance standard defining trust boundaries for conversational AI agents in high-stakes domains. MIT Licensed.

How to turn your Second Brain into a living research memory that your agents maintain. Workshop with slides, video and code.

Multi-agent AI article generation system based on LangGraph & DeepAgents, with RAG retrieval, hallucination suppression, parallel writing and context management.

DevAgent Studio is a multi-agent workbench for software project understanding and engineering governance. It helps teams review pull request risks, onboard new developers, understand unfamiliar systems, and continuously identify architecture drift and technical debt.无论是新人接手陌生代码、开发者提交 PR，还是团队进行架构巡检，都可以通过多 Agent 协作生成可追踪、可审核、可沉淀的项目治理结果。

RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly suited for the creation of agents that realistically emulate a specific human target.

Testing and evaluation framework for voice agents

GPT/DALL-E-based ChatGPT-like chatbot that runs on both CLI and Telegram, with sharable imprints.

Your friendly guide to building LLM chat apps in Python with less effort and more clarity.

DarkGPT Chat Explorer is an interactive web application that allows users to engage in conversations with various GPT (Generative Pre-trained Transformer) models in real-time. This repository contains the source code for the application.

Open source AI agent for e-commerce

The offical repo for "LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling"

All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.

ZYPHERON CLI Powerful command-line interface for automated security testing. Integrate ZYPHERON into your DevSecOps pipeline. Get CLI

Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.

Design Buddy: visual production Agent Skills for brand design systems, GPT-image-2 images, diagrams, infographics, logos, slide decks, WeChat layouts and social images

RoboCo: AI Agents Virtual Software Company. For solo-founders and solo-devs. If you need a team that works in an organized way, applies your best practices, and outputs quality code: Now you have it.

transformers pytorch safetensors llama text-generation llama-2

EvoPolicyGym is infrastructure for evaluating coding agents and generating training experience through Autonomous Policy Evolution.

Chapter-by-chapter teardown of a production coding agent — agent loop, context engineering, compaction, permissions, MCP. 13 chapters, Chinese and English.

Simple python WebUI for fine-tuning ChatGPT (gpt-3.5-turbo)

MESH-API — Off-Grid AI & API Router & with MCP server & over 30 API extensions for Meshtastic & MeshCore - Seamlessly connect LM Studio, Ollama, AI Providers , 3rd-party APIs, Agents & Home Assistant to your LoRa mesh. Supports custom commands, Twilio SMS, Discord channel routing, & GPS emergency alerts via SMS, email, or Discord + SO MUCH MORE

Python toolkit for Chinese LLMs, with flexible batch capacity, structured real-time visulization and automated accumulation for streaming, and explicit feedback on vendor-native parameter validation.

Create best skills based on best books

A curated hub of autonomous-research skills & agents — from idea to paper, on autopilot. | 自主科研技能与智能体精选库 —— 从灵感到论文全文，全程自动完成。

transformers safetensors qwen2 text-generation code qwen

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.

Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.

Arrest is a small utility to easily structure and validate your REST api calls using pydantic and httpx

Coding agent skill for Tensorlake. Routes Claude Code, OpenAI Codex, and other AI agents to live Tensorlake docs for sandboxes, orchestration, and SDK usage.

Conversational AI tooling & personas built on Cohere's LLMs

基于ReAct手搓一个Agent Demo

Official Repository for TimeSeriesScientist

专为闲鱼小商家打造的AI智能客服，经本人真实店铺实战打磨，懂人话不废话，会主动聊出单，支持多模态理解、消息聚合回复、跨会话记忆，支持后台静默运行，边挂机边工作，互不干扰。稳定可靠。（RPA+Coze工作流）

AI Experiments A public repository of AI/ML projects exploring generative models, NLP, computer vision, and autonomous agents. Includes code, documentation, and demos for educational purposes.

Collection of useful Claude AI skills and commands

Codes accompanying the paper "ROMA: Multi-Agent Reinforcement Learning with Emergent Roles" (ICML 2020 https://arxiv.org/abs/2003.08039)

MARLToolkit: The Multi-Agent Rainforcement Learning Toolkit. Include implementation of MAPPO, MADDPG, QMIX, VDN, COMA, IPPO, QTRAN, MAT...

Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)

AIRA-dojo: a framework for developing and evaluating AI research agents

Manage and orchestrate your Claude Code, Codex, Cursor, Antigravity, Kimi, Grok, Devin, Droid sessions on your Machine. Spawn in parallel, ship in parallel. Open source.

真正记得住你、认识你、随你成长的 AI 长效认知记忆引擎 Long-term Cognitive Memory Engine for LLM Agents

Intergrating Atomistic Skills into Agentic IDEs (Cursor, Claude Code, Codex, Google Antigravity, Hermes Agent, etc)

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming) as open-standard Agent Skills. Verification-gated; native on Claude Code, portable across Codex, Cursor & other Skills hosts.

Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No vector database, no embeddings.

简历通 ResumeForge —— 本地优先的 AI 简历工作台：岗位管理、事实台账防虚构、AI 定制/手写简历、多格式导出、模拟面试与面试深挖、自动投递台、求职进度与数据看板。FastAPI + React + SQLite，单机运行、数据不出本机。 | AI resume builder, job tracker & interview prep workspace (local-first, self-hosted, Chinese-first).

Evaluation tools for Retrieval-augmented Generation (RAG) methods.

GraphRAG / From Local to Global: A Graph RAG Approach to Query-Focused Summarization

Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"

Multi-agent LLM system for intelligent replenishment decisions in manufacturing supply chains

Alexa Skill that provides turn based conversations with an AI LLM. Bringing AI to your Alexa, because Amazon doesn't.

⚡ TubeCLI — The Ultimate Open Source AI Agents Ecosystem | Agents Browser · Agents Workflow · Agents Studio World

transformers pytorch baichuan text-generation custom_code en

GEO（AI 搜索引擎优化）智能内容优化平台 — 帮助品牌在 ChatGPT、Perplexity 等 AI 回答中被优先引用。支持关键词策略、多平台内容生成、E-E-A-T 优化、多模型验证和数据分析。

AI4AI Survey: can AI reliably improve AI? 223 papers on long-horizon agents, benchmarks, harness design, and recursive self-improvement · updated weekly

Telegram bot implemented by OFFICIAL OpenAI ChatGPT API (gpt-3.5-turbo, released on 2023-03-01)

Machine learning algorithms applied on log analysis to detect intrusions and suspicious activities.

⚡Chat with GitHub Repo Using 200k context window of Claude instead of RAG!⚡

An autonomous AI agent extension for Oobabooga's web ui

网页版 ChatGPT 包装成 API

Open Source Text Embedding Models with OpenAI Compatible API

Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)" and "Social Reasoning-Aware Trajectory Prediction via Multimodal Language Model (TPAMI)"

🦙 Free and Open Source Large Language Model (LLM) chatbot web UI and API. Self-hosted, offline capable and easy to setup.

This repository contains an implementation of a UAV-based task offloading model using the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm.

Educational tool demonstrating IDE bypass techniques for Kiro IDE. ⚠️ Partially compatible - Machine ID reset ✅ | Auto-update disable ✅

Job search Agent (AI) searches and applies to jobs on your behalf, creating tailored applications for positions that match your skills, making your entire job search hassle-free.

AnyKB — 私有 RAG 知识库 + 透明 Agent

SkillLens: a framework for studying model-generated agent skills across the full raw experience generation → skill extraction → skill consumption lifecycle.

Self-Improving Agents -- A Progression Four levels of self-improving code agents, from the simplest loop to a full adversarial arena with self-modifying agents. Each level adds one key idea.

transformers safetensors llama text-generation facebook meta

为 Claude Code 赋能多模态视觉能力，适配 纯文本 LLM 底座，用于截图 / UI / 图表分析；搭配 browser-harness 可做前端布局自动化检查。

Deep Search Pro —— 一个不到 1000 行的多智能体协作搜索系统。基于 LangChain + FastAPI + WebSocket，主智能体调度 3 个子智能体（网络搜索、数据库查询、知识库检索）协同完成复杂任务。AI Agent 入门学习的最佳实战项目。

MerchantBench is a 365-day, order-level benchmark for evaluating the long-term coherence of LLM agents in seller-side e-commerce operations.

⚡Chat with GitHub Repo Using 200k context window of Claude instead of RAG!⚡

Shrinkflation detector for Codex

An agentic job search that runs on Claude Code: a recruiter, a crawler, and a market analyst writing to an Obsidian vault.

CLI tool for running text through OpenAI Text to speech

Run any Large Language Model behind a unified API

GPT Enhanced with Real-Time Web Browsing 🔗

⚡ "Value" - https://value.valmi.io . Valmi Value is Outcome-based billing and payments infrastructure for AI agents. Meter usage, configure flexible pricing, and track costs & profitability - so you can focus on building great AI products.

AI-powered tool to audit and optimize website content by crawling URLs, analyzing H1s, and generating actionable GEO recommendations with CrewAI.

This repo compiles a collection of examples that demonstrate the effective use of the ReAct pattern in LLM prompting. It includes variations and implementations of agents that leverage the ReAct pattern, optimized for Gemini.

Multi-agent investment team powered by Agno and Gemini — 7 AI analysts collaborate across 5 architectures to deploy a $10M equity portfolio

Iron-Man-style voice assistant + holographic HUD for Hermes Agent. Local Whisper STT, ElevenLabs voice, agent-summoned media panels, runs on your own hardware.

Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Local, fast, free.