Python agents

Sora is a Discord bot that integrates with the Open Router API to facilitate conversation in Discord servers.

Minimal local-first multimodal RAG library powered by SQLite + sqlite-vec.

An LLM app with Retrieval Augmented Generation (RAG) built using OpenAI GPT models, Langchain Tokenizers, HuggingFace transformers, and Meta BART summarization model wrapped in a NextJS web app hosted completely on AWS

Self-evolving minor-user identification agent for anthropomorphic AI interaction, with trigger evaluation, evidence chains, and deployable protection workflows.

Convert documents, images to high-quality Markdown using Vision LLMs. Built for RAG ingestion pipelines.

Network scanner that maps infrastructure into a Neo4j graph and executes natural-language security operations via AI agents.

🤖 Advanced AI agent system combining ReAct reasoning and Plan-Execute strategies with unified memory, reflection patterns, and browser automation tools. Built with LangGraph, LangChain, and Google Gemini.

RAG-enabled multi-agentic system for medical diagnosis and assistance

✍️ Dive into this repository to explore a treasure trove of code examples, showcasing various methods and approaches for working with LLMs. These examples are inspired by my own learning journey and personal experiences, designed to ignite your passion for AI and machine learning.

MCP/API server that helps you to connect to different lead generation app

A structured framework for defining, verifying and certifying AI systems.

Chatnificent: LLM chat app framework – Minimally complete. Maximally hackable.

Speech-to-Speech conversational AI using Azure OpenAI Service and Azure Speech Services

一个《原神》AI驱动视频项目，利用LLM API生成角色互动文案，VITS技术进行语音合成，并结合先进的文生图和视频合成技术，创造出游戏角色之间有趣的场景。最终产出为短视频。

PyDoll MCP Server is a Model Context Protocol (MCP) server built on PyDoll, a next-generation browser automation library. It enables AI assistants like Claude to naturally control web browsers and perform complex web automation tasks.

[ACL 2025] Adaptive Retrieval without Self-Knowledge? Bringing Uncertainty Back Home

AI-powered tool that scrapes Google, extracts web content via Bright Data MCP, and uses AI to generate research-based articles with outlines and insights.

Extractive document compression for RAG and agent pipelines. +69% vs LLMLingua, +175% vs LLMLingua2 on information recovery. Compiled wheels, try it out.

An intelligent LinkedIn post generator powered by AI agents. This system uses Gemini, Brave Search, and web scraping to create engaging, research-backed professional content tailored to your audience and tone.

The bottleneck in AI coding isn't the model: It's the babysitting. Gobby is a local daemon that turns a task into a PR across Claude Code, Codex, Gemini, Qwen, and Droid. Stage dispatch, hook-time rules, progressive MCP proxy, and more. Gobby built Gobby: ~5K commits, ~15K completed tasks and counting.

A language-agnostic debugging interface for AI agents.

Task-steering — Implicit state-machine middleware for LangChain v1 agents. Ordered task pipelines with per-task tool scoping, dynamic prompt injection, and composable completion validation.

An integration package connecting PyMuPDF4LLM to LangChain

GLaDOS Terminal-based AI Assistant

The Google Gemini-Pro Chat Application is a Streamlit-based web interface that facilitates interactive conversations with Google's GenerativeAI. Users can ask questions or engage in dialogue, receiving responses generated by the powerful Gemini-Pro model.

An open-source AI system for TRIZ-based inventive problem solving with interpretable, step-by-step reasoning flow

Forkable code execution server for LLMs, agents, and devs

The most complete Claude Code toolkit in the wild. 348 skills, 80 commands, 35 agents, stage-gate pipelines, multi-model orchestration, and thinking frameworks -- distilled from six months and 19,030 commits across 104 repositories.

Autonomous multi-agent coding system on local LLMs. No frameworks, no API costs. Plan → Build → Test → Fix with Qwen 80B + 7B on your own GPUs.

Multi-Agent Reinforcement Learning for UAV-USV Cooperative Task Allocation in Offshore Wind Farms

AI agent evolving strategies through automated self-play overnight. Generic framework with GEPA-inspired feedback loop and Elo tracking.

Drop-in causal memory for AI agents. Append-only event store with associations and bounded memory injection.

This repository serves as the comprehensive workspace for Quarter 4-5 academic endeavors, encompassing assignments, technical documentation, experimental implementations, and applied projects.

High-accuracy web research via Parallel.ai API - outperforms Perplexity and Exa on benchmarks. Rich excerpts, citations, source filtering, batch search, agentic mode. OpenClaw skill.

Self-hosted Hindsight management platform — multi-tenant access control, user/group permissions, Terraform-managed infrastructure, and client integrations for AI agent memory.

AI-powered development orchestrator: Supports Claude Code, Codex and Langchain Deepagents + Openrouter backend

Open-source platform for reproducible AI/ML workflows, from local experimentation to distributed workers and long-lived services.

Meridian - A graph-powered AI chat application integrating intelligent parallelization for advanced, aggregated conversational experiences. Nuxt3 & Python.

使用TG Bot管理的AI模型中转工具，支持Anthropic、OpenAI Chat/Respones、Grok协议，支持OAuth登录，支持第三接口接入.

Waifu for hermes-agent. Dashboard plugin with multi-emotion support.

The industry-standard Agentic Identity & Inventory Scanner. Automatically inventory autonomous agents (LangChain, AutoGen, CrewAI, PydanticAI) using static analysis, network heuristics, and eBPF. Foundational tool for AIBOM compliance and AgentOps governance.

Supercharge Claude Code with 109 specialized components — 22 agents, 32 commands, 55 skills across 13 modular plugins. Deep reasoning, autonomous dev loops, DDD architecture, design system enforcement, git automation, and more.

🔐 Replayable RAG — a local-first, auditable knowledge-reasoning platform. Graph-RAG + append-only audit log + deterministic contradiction arbitration + human-gated self-evolution. Replay any past knowledge state byte-for-byte. 100% local (Ollama). MIT.

Self-extending AI agent system running on local Ollama - creates its own capabilities autonomously

Privacy-first, AI native agents For E-Commerce (and beyond), create skill (langgraph based workflow), tasks, agents, graphically with low code or no code. Deploy agents across network.

Multi-agent simulation platform where AI agents self-organize on a Kanban board — built with LangGraph, Google A2A, and MCP.

[ICLR 2026] A framework to "create benchmarks" and "evaluate AI co-scientists" in experimental data-driven real-world scientific research.

42 SEO commands for Claude Code — site audits, Ahrefs backlinks, GSC analytics, SERP research, content briefs, technical SEO, schema validation, and more

一站式智能任务执行、多Agent协作、企业级报告生成解决方案

Hybrid Knowledge Graph + RAG security intelligence platform for CVE analytics and semantic search. Llama3 integrated.

Ultra-lightweight AI agent framework. Shannon Entropy routing, zero-trust sandbox, GraphRAG memory. Only 2 dependencies.

Tool-native dataset generation skill for Codex, Claude Code, and Antigravity with SFT/DPO pipelines, verification, deduplication, and flexible export.

✈️ AI智能旅行规划助手-这是一个前端基于Uniapp、Vue3、TS、Pinia、uview-plus、Websocket，后端基于Python、FastAPI、PostgreSQL等框架及语言并结合LangGraph、LangChain大模型框架以及阿里云百炼MCP、腾讯地图、腾讯云语音识别等技术实现的AI智能旅行规划助手。

🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.

🧠⚡ Neurodiversity-affirming AI assistant for ADHD executive function support. Features crisis detection, circuit breaker psychology, and local-first processing.

Serial port MCP server for Claude Code and other MCP-compatible agents.

Agentic code-review CLI that records each review/fix/test run trajectory, building a corpus for fine-tuning open-weight models.

GitHub-ready Codex plugin bundle for Yandex Direct, Wordstat, Metrika, Roistat, Audiences, and Yandex Search API workflows.

🔍 一键检测 AI API 服务商是否如实提供所标注的模型 | 支持 OpenAI / Claude / Gemini / DeepSeek 等 9 大模型原厂对比验证

Allows AI Agents like Hermes Agent, OpenClaw, Claude Code, and others to make a VRM (anime avatar used for either VRchat, V-Tube, or other purposes) all via agent only processes, using either MCP, command line, or API.

MCP server for Chart Library — visual chart pattern search engine. Find similar historical stock charts and see what happened next.

Open-source, fully automated multi-agent content pipeline: Web content → AI Script → Voiceover → Video → Telegram Approval → Social Media Upload

20位天涯大神的多智能体决策系统，multi-agent team

Open-source middleware for AI agents — catches mid-run failures,compresses stale context, and grows a reasoning library across runs. Any model, any framework.

Edit videos from your terminal with natural language. 18 commands: cut, merge, compress, subtitle, GIF, watermark, speed, stabilize. Zero dependencies.

Doubt, until what remains is certain. An MCP server that recursively doubts every plan decision — grounding each in real evidence or asking you — until it converges. Runs on Claude alone, no keys. Sibling of The Asker → github.com/pranjalbhatia710/the-asker

Claude Code skills to bootstrap, compact, and maintain AI-readable project documentation — doc-init · doc-compact · doc-update

🪝 透明可控的 AI Agent 终端 | 状态机 · 多层记忆系统 · 沙箱防御 · 完整审计 · 多人设多技能

Self-hosted personal knowledge brain for Telegram, WhatsApp, n8n, Groq, and Obsidian. Save links, voice notes, and images; auto-summarize, categorize, tag, transcribe, set reminders, share guest access, and ask questions later from your Markdown knowledge vault.

Fragaria is a powerful and flexible Chain of Thought (CoT) reasoning API that leverages various Language Model (LLM) providers and incorporates Reinforcement Learning (RL) techniques to solve complex problems and answer intricate questions.

Visual RAG workflow studio that auto-generates eval sets, runs RAGAS evals, and deploys workflows as local HTTP APIs.

Autonomous AI research harness for Claude Code. Sibling to rockie-codex (OpenAI Codex CLI). Apache-2.0.

The meta-harness that brings real agentic collaboration as a first-class citizen

2-in-1 for Claude Code: a live system-tray usage widget (5h/7d plan limits) + local token & cost analytics — per project/model/tool, budgets, forecasts. Unofficial; not affiliated with Anthropic.

Train computer-use agents end-to-end on real desktops, at scale: a high-performance runtime where 8K+ live environments on one laptop thread.

Hermes Agent profile for adaptive multi-agent coding teams with GitHub issue-to-PR automation, blind critique, synthesis, CI schemas, and fail-closed unattended merge policy.

A self-hosted, keyboard-driven cockpit for running a whole fleet of Claude Code agents at once. Worktrees, command palette, scheduler, voice — every layer stacks, so you ship far more than hand-juggling terminals. Your machine, your keys, no telemetry.

AI pull-request reviewer: hybrid RAG + a code graph + Claude Code/Codex. Whole-repo context, inline GitHub comments grounded on exact code. MCP server + Claude Code/Codex plugin.

A Python package for text-classification tasks associated with the production of official statistics, utilising semantic search and Retrieval Augmented Generation

Architectural drift prevention for the agentic AI SDLC.

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.

Lightweight multi-agent trading analysis framework with A-share, HK, and US market support

Unraid CA template and Docker build for Mem0 (OpenMemory). This mega-container utilizes s6-overlay to seamlessly bundle the pre-compiled Qdrant Vector Database, the Python FastAPI/MCP server, and the Next.js Dashboard UI into a single, click-and-play local AI memory layer. Built for homelabs, privacy, and true agentic AI memory retention.

AI-native observability for production systems. Automatically understands your application from runtime data and logs. No dashboards. No manual configuration.

Turn any OpenAPI spec or Postman collection into an ownable Python MCP server in 30 seconds

Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground

Senior Architect Agent: AI architecture skill for existing system mapping, software architecture documentation, Mermaid diagrams, and AI agent handoff.

Fugusashi — Federated Learning of LLM Routing with Human-Interpretable Decisions. Open-source alternative to Sakana AI Fugu.

gradio mcp-server-track ultralytics yolo image processing human pose mcp-server region:us

gradio agent-demo-track region:us

docker mcp-server mcp-server-track chess chessboard games region:us

gradio region:us

gradio region:us

gradio region:us

gradio region:us

gradio region:us

gradio region:us

transformers safetensors llama text-generation conversational en

transformers safetensors mistral text-generation openchat C-RLFT

transformers pytorch llama text-generation dataset:Aeala/ShareGPT_Vicuna_unfiltered arxiv:2312.16886