Code agents

LLM Security Platform Docs

This project is designed to collect, analyze, and summarize news articles using AI. It integrates multiple news sources for collection and uses AI models such as DeepSeek and Gemini for analyzing the content. The system interacts with the AI to provide insights.

LLM weather agent built on the MCP protocol, combining Groq, LangChain and multi-API orchestration to answer natural-language queries with real-time data, forecasts and historical context.

自托管 HTTP 编程 Agent 工作台：支持流式对话、持久会话、文件交付、后台任务和 Docker Chrome 真实浏览器访问。

A simple local python AI chatbot using HuggingFace inference API and streaming/history with Redis

Various OpenAI projects and experiments implemented in Python. Utilizes all OpenAI APIs to test different models, fine-tuning approaches, and implementation patterns for production applications with comprehensive functionality tests.

LLMSymphony is a Windows application for incognito chats with leading AI models using your own API keys

Stop AI agents before they do damage — behavioral sequence detection blocks credential exfiltration, config harvesting, and secret leakage before the network call fires

This is the Deno 2 implementation of all tasks I did during AI Devs 3 course. It's integrated with Anthropic and OpenAI APIs here. Many different tools regarding LLMs are used here.

Self-hosted AI assistant with web interface, integrated autonomous agents and sandboxed execution

OpenClaw Bootstrapping Benchmark is an automated test suite that evaluates how well local LLM models (served via Ollama or compatible OpenAI-API endpoints) can complete OpenClaw's first-run "bootstrapping ritual".

This is a File system mcp server that could allow an LLM to read and list files from a specified safe directory on your local machine.

🤖 Build and optimize an AI trading agent using JavaScript for efficient and intelligent trading decisions on financial markets.

Async Python implementation of the Claude Code agent harness — real Bash/Read/Glob/Grep tools, three-tier caching, multi-stage compaction, allow/ask/deny permissions, Pre/PostToolUse hooks, slash commands, subagent isolation. OpenAI + Anthropic + Ollama. ~1.9K LOC, 14 commits.

A skill for full-fidelity PDF-to-Markdown extraction, paper-specific Python reproduction, and bilingual README generation with embedded experiment figures.

Connect a dedicated WhatsApp number to an OpenClaw agent — without going through Meta's Business API.

This Chatbot helps farmers make informed decisions by leveraging the power of LLM Model from OpenAI.

🌐 Build a Model Context Protocol (MCP) server for seamless integration with LLM applications, enhancing automation and efficiency in workflows.

Artifact repository for the paper "MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair", In Proceedings of The 43rd International Conference on Machine Learning (ICML 2026), Seoul, South Korea, July 2026

A single-file multi-client MCP gateway with per-tool access control.

A lightweight AI agent that answers natural language questions about APIs using their official documentation. It leverages vector embeddings and Retrieval-Augmented Generation (RAG) for accurate, context-aware responses.

📊 Transform research papers into professional slides and posters seamlessly and quickly with Paper2Slides, saving you valuable time.

A lightweight dashboard to view and analyze test automation results. Built with Streamlit + PostgreSQL, and powered by AI (Gemini) to help debug test failures faster.

Handcrafted ReAct Agent Engine | Supports FS / web page / weather query + code sandbox, including observability + visualization tools, focusing on circular thinking detection and task quality optimization

Auditable benchmark framework for LLM trading agents with replayable trajectories, realistic execution, risk gates, and quickstart demos.

Practical cookbook examples for the Swarms API Client. This repository is a hands-on guide to building with Swarms, showcasing single-agent and multi-agent workflows, concurrent and sequential pipelines, content generation, data analysis, health and rate checks, and more.

Claude Code config with TDD workflow, plan -> tests -> red -> implementation -> green -> review -> shipment

Do LLM Agents Dream of Better Hyperparameters? Comparing 5 frontier AI agents as autonomous ML researchers on Karpathy's autoresearch framework. 819 experiments, 7 hypotheses tested.

[SSBSE'25] This repository provides the artifact for the "KrakQL: LLM-Guided Blind Introspection of GraphQL Schemas" paper

Drop-in convention kit that enforces honest reporting in repos using LLM coding assistants — CI validators, smoke gates, PR templates, and schema-drift checks to stop scaffolds from shipping as features.

Spec-driven, markdown-only control plane for AI-assisted coding with explicit agent boundaries and human approval gates.

Let Claude Code, Codex & Gemini CLI agents talk to each other — a local MCP message bus for multi-agent collaboration, cross-model code review, and fewer hallucinations.

Deterministic governance runtime plugin for OpenClaw.

Agentic-AI-Workflows is a curated library of modular agentic pipelines featuring autonomous reasoning loops, tool-using agents, planners, memory systems, and multi-step automation flows to help you rapidly build powerful, real-world AI agent workflows.

The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

Benchmark AI code generation speed and cost across 13 programming languages using Claude Code for clear, data-driven language comparison.

Provide tamper-proof, CMMC-compliant execution receipts that document AI agent actions in regulated environments for clear accountability.

Build a stage-by-stage roadmap to become a production-ready AI engineer with Python, math, neural nets, RAG, FastAPI, and system design

Multi-Role AI Task Orchestrator — One task → 7 AI roles → One conclusion. Enterprise-ready with RBAC, Audit Log, Multi-Tenancy.

Agent state infrastructure: state-trace Python working memory plus @razroo/parallel-mcp durable MCP orchestration.

Open-source preview of *Claude Code for AI Engineers* - a methodology-first skill pack for RAG eval, agent debugging, MCP servers, paper reproduction, and benchmark reporting. Full pack (6 skills, 3 templates, 5 slash commands) at surpradhan.gumroad.com/l/claude-code-for-ai-engineers

Deterministic, self-improving AI agent execution harness and runtime for the AXIOM ecosystem. Enforces plan-deterministic execution, parallel swarm orchestration, and signal-level sandboxing.

Self‑hosted QA for AI agents: evidence packs, regression diffs, CI gates.

pm-agent (Octopus Assistant / 章鱼助手) — a multi-agent dev orchestrator that, like an octopus, dispatches tasks across multiple coding CLIs (Claude Code / Codex / Gemini) in parallel.

Standardized Test Case Generation for LLM Agents via Model Context Protocol. Bridging the gap between AI and QA (Xray/Jira).

Qualitative benchmark suite for evaluating AI coding agents and orchestration paradigms on realistic, complex development tasks

Provider-agnostic parallel agent coordination for LLMs — Anthropic, OpenAI, Ollama, or any OpenAI-compatible endpoint. Parallel worktree isolation, interface contracts, and tier-gated execution at scale.

An automated AI research-code writer and AI research-paper writer implementation through a skills+ autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

Smallest outsider-readable proof path through AgentGate + MCP Firewall: governed write_file, independent on-disk verification, and inspectable audit artifacts.

Background coding agents that execute, review, and land work unattended.

Research constitution and specification framework for comparing independently governed AI judgments without transferring authority.

Just A Rather Very Intelligent System.

Build Claude senior engineer skills for debugging, refactoring, optimization, hardening, and code review in Claude Code workflows

Toolkits for pydantic-ai agents: FS, SQL, pandas, memory, RAG.

AI-powered financial news analysis capabilities.

This project is an ATS Resume Agent that optimizes resumes for Applicant Tracking Systems. It uses Flask + CrewAI backend to clean, rewrite, and evaluate resumes against job descriptions, and a Next.js frontend to present polished resumes, ATS scores, missing keywords, and actionable recommendations in a user-friendly interface.

Catalogue technique des bugs critiques en architecture multi-agents IA. 11 fiches longues disponibles sur le site dedie.

🚀 Create and run TypeScript code on the fly with agent0, a self-healing tool that adapts to your API needs and provides seamless integration.

Welcome to the LatestAiDevelopment Crew project, powered by crewAI. This template is designed to help you set up a multi-agent AI system with ease, leveraging the powerful and flexible framework provided by crewAI. Our goal is to enable your agents to collaborate effectively on complex tasks, maximizing their collective intelligence and capabilitie

ChainWise is an AI-driven fullstack platform designed to optimize supply chain operations for mid-to-large enterprises. Powered by autonomous AI agents, it monitors, predicts, and manages supply chain processes in real-time, reducing costs, minimizing delays, and improving transparency.

Developed an AI marketplace that integrates various agents, including modular, independent agents like Professional Email Writer, Document Summarizer, YouTube Summarizer, Web Crawler, Image Generator, and Blog Writer along with a Job Agent, Case Study Agent and a Deep Research Agent, which can be combined with other agents in custom workflows.

Multi-agent AI system for mental health first-line workers. 3rd Place - Hackathon en Santé Numérique 2025.

security pentest ai crewai llm nmap cybersecurity python multi-agent

Context compiler for agentic AI — token budgets, cache-aware adapters, pytest-style eval layer, JIT references. Framework-agnostic, local-first, deterministic

Drop-in performance acceleration for CrewAI - Get up to 34x faster serialization, 17x faster tool execution, and 11x faster database search with zero code changes to your existing CrewAI projects.

fastapi backend powered by crewai agents for automated research, data retrieval, and synthesis. orchestrates multi-agent workflows for query analysis, information gathering, and summarization.

📰 Discover and summarize top news stories effortlessly with the News Aggregator AI Agent, saving you time while keeping you informed on any topic.

A minimal Ruby client for interacting with CrewAI AMP APIs, supporting kickoff, status tracking, health checks, and workflow resumption.

The Lobbying Crew is an AI-powered tool designed to streamline and automate the lobbying process.

🤖 Automate coding, testing, and deployment with a local AI environment powered by a team of intelligent agents.

Open-source observability platform for AI agents. Trace every LLM call, tool use, and decision in real-time. Supports OpenAI, Anthropic, Gemini, LangChain, CrewAI, LiteLLM, MCP. Self-hosted. Zero dependencies.

TheBlend.ai Website code that create blog content using AI

A sophisticated system that converts natural language questions into SQL queries through a 12-agent pipeline with schema reasoning, self-correction, safety validation, and explainable AI.

Explore Genkit agents for YouTube video searches and content generation. Find workflows to streamline your video discovery and blogging process. 🚀📂

An intelligent multi-agent system that automatically generates comprehensive documentation for GitHub repositories using CrewAI's collaborative agent framework.

Code recipes for email & SMS in AI agents — LangChain, CrewAI, OpenAI Agents SDK, Claude, n8n. Inbox, threading, webhooks, phone numbers. commune.email

Runtime authorization layer for AI agents. Every action is ALLOW, DENY, or REQUIRE_APPROVAL before it hits the real world.

A demonstration project showing how to orchestrate a multi-agent “engineering team” using the crewai framework. This repo defines a crew of specialized agents (engineering lead, backend engineer, frontend engineer, test engineer) and a set of tasks (design, code, frontend, test) which are executed sequentially to satisfy a simple account-management

A demonstration of using the CrewAI framework to automatically plan, write, execute, and collect output from Python coding assignments using an LLM-based “Coder” agent.

🤖 Explore and utilize top open-source tools for running, fine-tuning, and building LLMs entirely locally, without cloud dependencies or API keys.

This GitHub repository, "Meeting-Prep-Using-CrewAI", is a project that aims to utilizeCrewAI to assist in meeting preparation.

🏆 1st Place – OpenAI Track (National Security) | SCSP x AGI House Hackathon 2025

An AI-powered assistant platform combining medicine stock prediction, real-time skin diagnosis with product recommendations, and a chatbot assistant for quick access to drug information and extracting prescription information.

Chonost Manuscript OS คือระบบจัดการต้นฉบับอัจฉริยะที่ออกแบบมาเพื่อรองรับการทำงานร่วมกันระหว่าง AI agents, RAG pipelines และแอปพลิเคชันเดสก์ท็อปแบบ native โดยใช้สถาปัตยกรรม MCP (Modular Component Protocol) เพื่อให้ทุกส่วนของระบบสามารถสื่อสารกันได้อย่างเป็นอิสระและตรวจสอบได้

Automated ticket handling and approval workflow integrating ServiceNow, CrewAI, n8n, and AWS WorkSpaces. Classifies tickets, manages workspace approvals with reminders and escalations, provisions AWS WorkSpaces, and handles non-workspace requests automatically.

An AI-powered financial research crew built with CrewAI. It finds trending companies, researches them, and selects the best investment candidate using hierarchical task orchestration, structured outputs, and custom tools like push notifications.

Multi-agent AI pipeline in Python that turns a plain-text idea into a complete, scaffolded full-stack project — backend, React UI, tests, and git-ready to push. Powered by CrewAI, Anthropic Claude and Inspect AI

Utilizing state-of-the-art AI-driven components, MemoGen handles the writing, outlining, and reviewing of memos. The final output is a detailed and well-structured document in DOCX format.

Bootstrapping GNU Autogen without relying on pre-expanded code

A Personal Voice Assistant that performs a multitude of tasks for you on command (Codeshastra X Project by Tensionflow)

This project demonstrates a conversational AI simulation between a high school student and a math tutor using the AutoGen framework and the Groq API (with LLaMA 3 model). The use case focuses on helping students understand quadratic equations through a multi-turn dialogue.

Sample code on AutoGen for the Latoken hackathon

📈 Generate AI-driven investment reports using multi-agent orchestration and real-time data for informed equity research and decision-making.

Multi-agent AI platform with a real-time web UI built on Microsoft AutoGen

This repo contains the code for the AutoGen + MCP tutorial

VSCode extension that provides verification for files including auto-generated code

Enables Autogen agents to securely execute code in isolated remote sandboxes using YepCode’s serverless runtime.