Python agents

The official Python library for the Steel API

advanced-rag 是一个"纯粹的开源高级RAG系统"，基于 FastAPI + Next.js 构建，仅保留 AI 助手对话（含深度研究/深度思考） 与 知识库检索/入库 两大能力，所有 API 匿名访问。

copilot proxy for glm coding plan, will support more in the future (maybe?)

Battle-tested utilities for AI coding assistants. Self-guard hooks, memory GC, pitfall tracking.

Ragbot.AI is an augmented brain assistant developed by Rajiv Pant

A completely free python discord chat bot which uses Google's Gemini API.

MCP server that enables LLM agents to talk with IFC (Industry Foundation Classes) files

Portable Agent Skill to plan, spawn, review, and merge parallel CLI agents in isolated git worktrees, with deterministic Python/Bash runners for condition-gated, backup-safe, log-heavy workflows. Includes a Kimi CLI example; easily adapted to Codex CLI, Claude Code, OpenCode, Droid Factory, Pi, or any CLI harness.

The official Implementation of HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems

Create and interact with Knowledge Graphs using Generative AI

A framework for AI WhatsApp calls using Whisper, Coqui TTS, GPT-3.5 Turbo, Virtual Audio Cable, and the WhatsApp Desktop App.

Insurance AI Assistant A smart system combining PostgreSQL, Milvus, and specialized AI agents (Life/Home/Auto) to answer insurance queries accurately. Features real-time sync, semantic search via OpenAI embeddings, and a Streamlit UI. Perfect for insurance tech demos or customer service augmentation.

这是一个基于AgentScope框架的AI助手应用，支持自动技能发现、智能任务匹配和终端交互，兼容claudecode的skill文件。

Local-first SQLite memory provider for Hermes Agent

Local FAISS vector store as an MCP server – Agent Memory, drop-in local semantic search for Claude / Copilot / Agents.

Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes.

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution [ICSE 2026]

VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation

AI-powered SOC for OT/ICS networks — 6 autonomous agents, MITRE ATT&CK mapping, Suricata/Zeek ingestion, human-in-the-loop response, 330+ tests. Open-source alternative to Claroty/Dragos for SMBs.

[AAAI'26, Oral] Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG

Official implementation of the paper "Learning and Planning Multi-Agent Tasks via a MoE-based World Model"

The source code for the Autonomy framework and command. This SDK is what you use to build agents and applications that you can deploy to the Autonomy platform.

MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), domain & web intel, threat intel.

Simulated environments for robot agent evaluation and reinforcement learning.

Excel MCP Server - Manipulate Excel files without Microsoft Excel. Model Context Protocol for XLSX, XLSM with Claude AI integration

Project setup generator for Claude Code. Pick framework + workflow, get a fully configured project - CLAUDE.md, hooks, agents, commands, skills, plugins, memory.

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out, Pipeline, Supervisor, Swarm, Glyph), and deploy as a REST/WebSocket API with RAG, memory, MCP tools, guardrails and OpenTelemetry observability.

Production-ready Claude Code 2.0 setup for autonomous development

Operational patterns for AI agents and infrastructure from solo to enterprise scale. Applies DevOps + SRE principles to the intersection: infrastructure FOR AI + AI FOR infrastructure. Alpha framework extracting meta-patterns from mission critical environments.

Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Reinforcement Learning

AI-powered multi-agent platform for evidence-driven scenario simulation and strategic decision-making. Supports corporate \& military domains with debate protocol.

Benchmark for evaluating LLM agents in bioinformatics

Full-stack LangGraph real-estate agent for lead intake, property search, Google Calendar scheduling, chat, SMS, and voice workflows

Fix "Codex cannot access its local database" / "migration 1 was previously applied but has been modified" / "timed out waiting for state db backfill after 30s" on Codex Desktop (Windows/WSL/Mac/Linux) after the 0.130 → 0.131 update. CRLF/LF sqlx checksum drift in state_5.sqlite + logs_2.sqlite. Sessions preserved. See openai/codex#23787.

Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and RAM usage by 3x.

Open Source Solution for Claude Creative Work

Awesome all-in-one research skills for AI agents — covering every academic discipline. Works with Claude Code, Codex, Gemini CLI & Cursor.

First formal security scanner for AI agent skills & plugins. Static analysis, supply chain verification, SBOM generation. 22 frameworks supported including MCP, LangChain, CrewAI.

PsyChat 是一款基于范例引导与Agentic RAG的智能 AI 心理咨询助手。基于高度匹配的Few-shot与学习笔记，应用理性情绪行为疗法（REBT）帮助用户识别并调整非理性信念，缓解负面情绪。

🚀 多Agent协作智能知识库系统 — 五层可编排Agent架构 + RAG全链路 + 统一ToolRegistry，Spring Boot + FastAPI + React，核心亮点是 五层可编排 Agent 架构——Interface、Orchestrator、Tool、Memory、Evaluation 五层解耦，支持意图识别→问题改写→检索→充分性判断→答案生成的完整工作流。系统内置 Router / Retrieval / Ops / Inspection 多 Agent 协作，通过统一 Tool Registry 管理 AI 能力，支持 runId/traceId 全链路追踪、四级记忆体系与 Caffeine + Redis 多级缓存。适合Agent后端开发学习与简历展示

An opinionated Obsidian second-brain template, built for long-term human-AI collaboration

Production-grade memory operating system for agentic AI. Interoperates with every major framework via MCP, OpenAI-compatible gateway, and native /v1/* REST — Claude Code, OpenClaw, ZeroClaw, Hermes, MemPalace, LangChain, LlamaIndex, CrewAI, AutoGen, Mem0, Letta, Zep. In production use since December 2025. Apache 2.0.

Official Code of LabOS: the AI-XR Co-Scientist that Sees and Works with Humans

把高质量播客和长文 RSS 自动转成 karpathy-claude-wiki 兼容的 source-summary 页面 / Turn high-signal podcasts and long-form RSS into karpathy-claude-wiki compatible source-summary pages. Part of the zero-code AI investment research toolkit.

Curated archive of agentic AI samples, reference implementations, and tooling from the Agentic AI Acceleration program in Korea. AWS-native patterns covering Bedrock, AgentCore, and end-to-end agentic AI pipelines.

Multi-agent inference framework for RTL generation. A Verilog agent and a Python reference-model agent independently propose implementations and cross-verify each other's outputs on random stimuli — no golden testbench required. Open-source companion to the ChipMATE paper.

WormGPT CLI V2.0 is here but is still in the development stage from the previous version which I did not optimize for its function, please be patient and calm!.

对话即创作 · AI Agent 驱动的小说写作工作台 ｜ Chat to create — an AI-agent-driven novel-writing workbench

Coral is an open-source, local-first session bridge that lets AI agents borrow a user's already-authenticated browser sessions on a per-site, per-action, fully audited basis.

MCP server for Home Assistant: give each AI agent its own token, scoped to only what you allow, with per-entity safety, full audit, and instant revoke.

A GDB debugging tool designed for AI Agents (Claude Code, etc.)

[ECCV2026] Official Implementation of "VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement"

Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous simulations. Evaluate with LLM judges.

Open-source legal knowledge + data layer для российского права. 145 AI skills + 8 MCP-интеграций с госреестрами (pravo.gov.ru, ЕГРЮЛ, kad.arbitr, ЕФРСБ, Роспатент, Росреестр, госзакупки). Apache 2.0.

Open ScholarPeer: Implementation of DeepMind's ScholarPeer Protocol for AI Peer-Review. Use in Claude, Codex, Antigravity, Pi, etc.

gradio mcp-server-track agent-demo-track region:us

gradio region:us

transformers safetensors stablelm text-generation causal-lm conversational

transformers safetensors qwen3 feature-extraction dflash speculative-decoding

gradio region:us

transformers safetensors gguf stablelm text-generation causal-lm

transformers safetensors llama text-generation en fr

transformers pytorch safetensors llama text-generation conversational

gradio region:us

🗞️ AI 驱动的每日资讯采集与智能推送平台 — 将 RSS / GitHub Trending / AI 搜索汇聚为个性化日报，推送至飞书、企微、公众号、小红书、钉钉等平台。

Tmux manager for running, monitoring, saving, restoring, and looping Codex, Claude, Gemini, and custom agent CLIs.

面向中文食谱问答的端到端 RAG 工程实践，覆盖数据清洗与索引构建、混合检索、多轮状态管理、结构化生成，以及基于真实大模型服务的 Live E2E 测评闭环。

Ask, compare, and synthesize across 10 LLM providers. Python SDK, CLI, local Arena, MCP, and privacy-aware

Three voice-agent backends (LiveKit, OpenAI Realtime, Google ADK Live) sharing one console interface, each instrumented for LangSmith

MCP server that extracts, chunks, embeds and stores PDF documents into a pgvector database for semantic search and RAG pipelines.

影刀 xbot AI Agent 开发知识库｜影刀编码版 API、RPA 自动化、浏览器、Excel/WPS、市场指令、Claude Code 与 Codex

Self-hostable, MCP-native testing platform. Manual test management, deterministic runs, optional AI. Your stack, your LLM, your data.

The Cost of Remembering: filesystem memory matches long-context accuracy on LongMemEval while reading 97% fewer tokens and costing 95% less. Harness, run data, 129 agent-built memories, and paper source.

GraphRAG Agent 是一个面向私有知识库的全栈图谱问答系统。它将文档上传、文本解析、分块、知识图谱抽取、索引任务编排、可视化编辑和问答记录整合在一个受认证保护的工作流中，并为多用户场景提供用户自带 API Key（BYOK）能力。

Whitebox & Blackbox AI red-teaming framework for LLMs & Agentic AI apps. It analyzes your app's source code to discover tools, roles, and guardrails, then generates new attacks chains across several categories and adapts over multiple multi turn rounds to find vulnerabilities

AI agent skills for IELTS Writing Task 1 & Task 2 review with DOCX comments, customizable target bands, and model answers.

Facebook Pages marketing skills for Claude Code and Codex: high-share posts, hooks, engagement replies, and a weekly plan. Publish via Publora. Open source, MIT. Content engineering by Creative Content Crafts.

AI proposal-writing & deal-closing engine for Claude Code. Research a prospect, price the engagement (3-tier + ROI), define scope, pre-handle objections & generate client-ready PDF proposals. 14 skills, 5 parallel agents. Auto-builds from your GEO/SEO/reputation audit reports.

Self-hosted, private family AI health steward. Multimodal AI structures health data into a person-centric profile with dashboard & AI consultation (Feishu/Lark integration). 开源可私有化部署的家庭 AI 健康管家：多模态大模型 + 健康画像看板 + AI 咨询 + 飞书渠道。

transformers gguf mistral code text-generation-inference text-generation

Agent-native embedded systems lab for pluggable simulation, evidence-driven validation, and controlled evolution.

This project is a fully automated AI blogging platform built with LangGraph and Groq’s LLM. It generates and publishes technical blog posts automatically to a modern, responsive website. The system dynamically renders Markdown content without requiring complex build setups.

Korgo Bot: persistent AI bots with built-in Orgo cloud computer use.

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

🔍 Stop refreshing LinkedIn. This pipeline scrapes new job listings based on your settings, uses AI agents to summarize each one and score it against your CV, then delivers only the best matches straight to your inbox 📬 — so you're always first to apply 🚀

Research and scraping agent skeleton: tool loop, loadable skills, fallback chains. No data included, configured via .env.

MCP server for Kdenlive — wraps kdenlive-api for Claude Code and other LLM agents

gguf qwen3.8-flash-next qwen4exp imatrix agentionai text-generation

Code repository for World Model From Scratch book

Python SDK for Scalekit — auth stack for agents. SAML, OIDC, SCIM, MCP Auth, agent auth, tool-calling.

A stress-testing benchmark for partial-completion evaluators in stateful multi-turn agents, focusing on temporary progress, rollback, and attribution failures.

Free, dependency-light Internet intelligence MVP for grounded research, extraction, citations, and page monitoring.

Humane Agentic Design — a human-centric design method cycle for people and agents

A lightweight, modular post-exploitation framework for Linux and Windows. Manages interactive reverse/bind shell sessions over TCP/TLS/mTLS and provides plugins for enumeration, execution, pivoting, and operational tasks without deploying a separate agent or dropping enumeration binaries on target.

A GPT-6 Astra agent that runs a live board of every Robinhood Stock Token against its real price and calls the gap while the real NYSE is closed. Built with Minara.

This collection of AI sub-agents for Claude Code leverages a powerful agent-assembler to dynamically generate a personalized and project-specific AI development team based on your unique tech stack.

用最简单的代码带你实现基于大模型的本地知识库问答系统

GPT-2 based neural conversational model with TensorFlow.

🤖 OpenAI. No account required.

A ChatGPT powered chatbot for the AWS Well-Architected Framework