Code agents

An engineering process for Claude Code projects: plan, review, record. The commit gate is a git hook, so it isn't optional.

Multi-agent AI platform that automates healthcare prior-authorization decisions. RAG-grounded, harness-engineered, observability-first.

The world's first open-source AI development platform combining AI Coding Assistant, Security Scanner, and Self-Healing Engine — all free, private, and multi-model.

Multi-agent AI music discovery assistant that turns natural-language mood prompts into ranked Spotify recommendations and one-click playlist creation.

Repo-scoped Codex skill for launching and collecting independent Luna subagents.

DeepSeek Harness 多智能体编排模式 — 灵感来自 oh-my-opencode-slim

A personal AI assistant in one Go binary: WASM-sandboxed extensions, per-action permission gating, and mandatory out-of-band approval on your phone. No cloud, no database, zero-dependency engine.

Ralph Wiggum loop starter kit for Claude Code: a fresh-context autonomous build loop with stop conditions, guardrails, and spec/plan scaffolding.

Production style autonomous agent framework in Python + React that plans multistep tasks, persists state with SQLite, and recovers from failures using exponential backoff retry logic. Includes real time monitoring dashboard, deterministic recovery demo, and API for task orchestration.

Six MCP servers that automate the full academic research pipeline — from refining a vague research question to generating a publication-ready report. Each server handles a distinct stage of the workflow: question development, data processing, code generation, script execut

Agentic AI Agents - LangChain Agentic Pipeline with Streaming API

Apple Watch voice / text / image interface for AI agents such as OpenClaw.

Verifiable agent identity for A2A and MCP. Cryptographic claims, append-only transparency log, recovery-key revocation. Apache 2.0.

Core Agentic AI implementation using the OpenAI Agent SDK in Python. This repository demonstrates how to build intelligent, tool-using AI agents

A multi-database IDE for SQL and NoSQL workflows, with AI routing, schema-aware assistance, dashboards, and visual exploration built in.

Local-first mission control for your AI agent workforce — run CLI agents like employees (SquadCue)

Rowlite is an open-source, non-SQL, lightweight CLI tool and MCP server to work with markdown tables - create, read, update, delete

llama.cpp safetensors qwen35_moe MoE Qwen CobrIX-1.0-Coder-Flash

Autonomous LLM build orchestrator: plans a goal into tasks, edits code with anchored SEARCH/REPLACE, and verifies every change through build/test/lint/typecheck gates before reporting done. Runs as a CLI or MCP server.

DSH Math Modeling Team Plugin Pack: 2 role agent presets (modeling-coding / paper) for DeepSeek Harness, multi-folder Git collaboration + vision sub-agent; includes a full run on 2023 CUMCM-C. ｜ DeepSeek Harness 数学建模团队插件包：2 套岗位Agent预设(建模编程+论文)、多文件夹协同+识图子代理，含2023国赛C题全流程跑通示例。

Persistent memory scaffolding for AI agents - Trail, Destination, Improve, Retrospect, Intent, Probe. Self-built across 221 iterations; declared complete only when GPT, Claude, and Gemini independently found nothing left to change.

Companion reading list for the survey 'The Agent Loop: Control Strategies, Skills, and Harnesses for LLM Agents': 492 papers by section plus 28 open-source artifacts (frameworks, coding harnesses, skill libraries, registries).

Loadable skill and scaffold for building source-grounded agent harnesses

Bilingual source-grounded notes on agent harness architecture

transformers gguf code codeqwen chat qwen

Claude Code skills for LibreChat administration and configuration

Agentic AI system for real-time business decision making using RAG, APIs, and LLM reasoning

Persistent, shared memory for AI agents - so they stop forgetting and stop colliding. Markdown-native, on-prem, auditable. Speaks MCP.

Automate social media tasks using AI agents that coordinate workflows for efficient content management and scheduling.

SlideSpeak Agent Skills to create presentations using SlideSpeak API

Know what's real. An open engine for messy data. Find the entities, resolve who or what they are, and decide which records are the same thing.

Keeps your Mac awake only while Claude Code is working, and lets it sleep when the agent is waiting on you. A menu bar app for macOS.

Your AI pair programmer for Visual Studio 2022/2026 & VS Code - 100% local, no API key, no telemetry. Agentic loop with 28 tools: reads, edits, builds, tests, reviews your diff, even drives a live debug session. Ghost-text completions, semantic search, MCP, plans & background tasks, model bench/router. Ollama, LM Studio or OpenAI-compatible.

transformers safetensors qwen3_moe text-generation quantized w8a8

A Tauri desktop app for browsing local conversation histories from AI coding agents in one place.

gguf llama-cpp ministral openzero agent-zero local-ai

subagent-mcp is an MCP stdio server that turns an AI coding assistant (Claude Code, Codex, Gemini CLI) into a manager of local Claude and Codex sub-agents on macOS, Linux, and Windows.

AI assistant that answers Instagram DMs in your own voice, qualifies leads, and quotes from your rate card. Built on the Instagram Messaging API and Claude.

Static system dashboard for a Hermes Agent installation: host status, security, model routing, honest cost, memory, cron economics and a capability map — built by cron from the agent's own telemetry. Stdlib-only Python, EN/RU.

Düzenek Mühendisliği (Harness Engineering) — AI kod ajanlarını güvenilir kılan çevreyi tasarlayan Türkçe açık kaynak müfredat

Retrieval-Augmented Generation. A production-shaped reference stack for grounded chat over your own documents — FastAPI + LangChain agents, Qdrant vector search, and a Next.js 15 frontend with a deterministic calculator tool wired in.

A self-hosted RAG assistant using local LLM that combines document Q&A with citations and natural language to SQL database access - running entirely on local infrastructure

Hybrid Retrieval System combining keyword matching (BM25) with semantic similarity (Vectorstore) for improved retrieval.

API for reviewing resumes via gen ai

RAG Chatbot deployed to GCP with gpt-3.5 and Mistral-7B language models and gte-base-en-v1.5 with FAISS for vector search.

This project is a simple Table Talk RPG (TRPG) game master (GM) agent built using LangChain and LangGraph. Users can experience a “light TRPG” in which they interact with an AI (GM) on the console to advance the story.

smart-contract-reviewer is an open-source LegalTech tool that automatically checks the compliance of permanent employment contracts with Moroccan Labor Law. Leveraging Generative AI and RAG frameworks like Gemini and LangChain, it detects potential legal issues, suggests corrections, and ensures that contract clauses adhere to local regulations.

An LLM-powered repository agent for wiki-style documentation and deep codebase understanding

Este repositório contém implementações de agentes e ferramentas utilizando a biblioteca LangChain. Ele abrange o uso de Native Tools como PythonREPL, DuckDuckGoSearchRun e WikipediaQueryRun, além de agentes em Python e React. Também explora a integração com bancos de dados SQL usando o SQLDatabaseToolkit.

An AI assistant for working across multiple software projects. It indexes each project's codebase and documentation independently and can also answer meta-level questions across projects.

A simple yet powerful local AI Agent assistant that runs entirely on your machine. Option for remote LLM. Built for learning and deploy, Little MCP combines the power of open-source LLMs with advanced RAG that work with your personal documents. Included tools: real time weather, local documents RAG, local SQL database. Easy deploy your own agent.

Multi-Agent AI Business Automation OS with Security Intelligence — 5 AI agents (HR, Finance, Support, Analytics, Executive) on a unified dashboard. Next.js · Node.js/Express · Supabase · Gemini · LangChain | CSE4204 Team 8B-T04

Multi-agent DeepSeek Harness workbench with switchable Pi, OpenAI Codex, Claude Code, and native DeepSeek Agent Loops.

Run your own agent org: talk to an orchestrator, it hires & supervises worker agents you can watch and steer. Self-hosted; pluggable surfaces (Telegram, Web, VS Code) and agent backends (Claude Code, Codex).

Work goes in -> webs come out. Task optimizer for Codex.

Local Pi + Herdr multi-agent workflow kit with planning, review gates, phased coding, and Git commits

Local-first multi-agent programming collaboration platform. Orchestrate Claude Code & Codex CLI as visual AI agents with team collaboration, safety approvals, and one-click deployment.

Local-first AI Workforce Operating System that coordinates executive leadership (AI CEO/CTO) and specialized AI agents to autonomously plan, code, debug, and test software. Features Task DAG decomposition, 3-layer intelligent routing, and persistent Obsidian organizational memory for cross-project learning.

Make every Codex Goal teach the next one with evidence-backed orchestration.

问镜（Agentic Interviewer）：基于 LangGraph 的可追责 AI 模拟面试与复盘训练系统，实践评分合同、上下文治理、Trace 回放与产品控制面

an AI-assisted podcast generator: a FastAPI backend drives Python series workflows (LLM script + local Kokoro TTS + optional Tavily search and ACE Music)

Copy-ready AI workflow packs for Codex, Claude Code, Gemini, and GitHub Copilot.

Unofficial Codex Skill that auto-matches concrete team, model, and Skill setup requests, then recommends the smallest reliable AI setup.

Open-source workspace where AI agents talk, drive browsers, and recruit help — terminals, notes, and live browsers wired together on one canvas. Cables are the permissions; every agent speaks one CLI.

🏛️ Ask about a stock, get an argument: 27 investor-method lenses (Buffett, Munger, Burry, Taleb…) read the same filings, disagree in public, then a bull/bear debate and a PM verdict — watched live from a terminal client with typewriter transcripts. 31 keyless tools, zero deps. Claude Code · Codex · OpenCode · Grok

Dispatch and review AI coding agents, hand them disposable VMs to test in, capture and summarize meetings and keep tickets, pipelines and your calendar on one deck. Desktop on macOS, Windows and Linux, plus web and phone.

Multi-Agent Generative AI system to automate CA workflows — Tax, GST, Audit, Compliance & Financial Advisory for Indian MSMEs. Built with LangGraph, LangChain, FastAPI, RAG, and GPT-4o.

The natural-language command layer for an AI workforce — direct governed AI agents to deploy cloud infra, train ML, and run research, all under human policy & approval. Agentic command-and-control.

Private, self-hosted coordination control plane for coding agents

A Agentic AI-Powered Newsletter Generation System Built for the Portia AI Hackathon

WhatsApp-first accounts-receivable agent for invoice reminders, payment events, and human-reviewed collection workflows.

🥧 Apple Pie — AI coding agent harness for native Android & iOS apps: drives Claude Code to take a Jira or markdown ticket through plan → implement → verify and out as a reviewed pull request. Android ships today; iOS is under development, preview coming soon. Parallel agents, one TUI dashboard, never auto-merges.

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.

The Debian COSMIC Desktop Brewery: Unified .deb and systemd-sysext delivery for Debian Testing/Sid.

Future of Software

Three hooks that fix Claude Code's attention drift. Cited research, one-line install.

Yana AI 🐰 One runtime. Any AI. Human-governed. A local-first, cross-platform system for running, connecting, orchestrating, and governing AI — with deterministic control over what it can access, change, and execute. Your AI can act. But who decides how far it can go?

HxSync: An Android AI Agent client with 4-tier scheduling (local/API/remote/gateway), MCP-compatible memory, and human-in-the-loop confirmations. Bring your own LLM.HxSync 是口袋里的 AI Agent 客户端：四档调度（本地/API/远端/网关），MCP 记忆内核，人在回路确认卡。自带模型，也可接你自己的 AI 服务。

Spring Boot + Vue 3 教务管理系统 / academic management system for graduation projects, with Redis 抢课, course selection, grades, exams, timetable, AI assistant, natural language SQL, and load testing.

Maestro is an open-source, multi-agent AI development framework written in Go. It orchestrates specialized AI coding agents across a deterministic software engineering workflow

gguf GGUF qwen3 qwen quantized cerebellum

A local, SQLite-backed memory and autopilot layer for coding agents (Claude Code, Codex).

A highly compatible proxy bridge with translation for API requests to multiple backend providers (OpenAI-Oauth, RunPod, Ollama,,etc.). Configure endpoints through a web admin UI and map virtual model names to actual backend models. Create API keys to share and monitor usage and costs by tools / teams. Opencode/Claude to queue servers too.

Yang Code Review (YCR) - A lightweight GitHub Action for AI-powered, OWASP-aligned code review with your own LLM provider.

A curated directory of open-source AI repositories for agents, LLM apps, coding assistants, MCP servers, RAG, generative AI, automation, developer tools, research, and AI security.

mlx safetensors qwen3_5_moe text-generation conversational base_model:Kwaipilot/KAT-Coder-V2.5-Dev

transformers safetensors qwen2 text-generation text-to-cad code-generation

gguf code text-generation dataset:JetBrains/KExercises base_model:deepseek-ai/deepseek-coder-6.7b-base base_model:quantized:deepseek-ai/deepseek-coder-6.7b-base

Empathetic AI engineering partner with cognitive memory, multi-agent orchestration (10 agents), 132-signal skill routing, and self-improving reflection loops. Built on Model Context Protocol. By Aldo Karendra.

Bounded Agents: Delegation Security for Multi-Agent AI Systems - Reference Implementation and Evaluation Artifact

Multi-agent orchestration for pi; chain, parallel, and dependency-graph delegation with per-step model routing, preset-driven tool scoping, and background execution with live monitoring.

Production reliability, benchmarking, and evaluation layer for MCP agent runtimes — protocol negotiation, A2A interop, circuit breakers, connection pooling, adaptive streaming, and autoscaling, with measured throughput/latency and a 109-test suite.

Nine-agent AI framework automating quant research from hypothesis generation through leakage-aware backtesting

GraphRAG Lore & World-Building System

FinSight AI is a multi-agent due diligence platform that turns real SEC 10-K filings, live financial metrics, and news into concise analyst-style reports with risk assessment, investment signal, and downloadable PDF

A deterministic SQL access guard for LLM text-to-SQL agents: enforce each user's real data-access rules on generated queries, keep the agent aware of the full catalog, and answer honestly about what it can't see.

Multi-agent data analyst — CrewAI agents that write and run SQL, analyse results, draft executive reports and build Plotly charts from natural-language questions over any uploaded dataset.

Chat-first film preproduction skill for Codex: director-room ideation, story/script/shot design, visual review, model-specific prompts, and verified releases.

Provide and generate AI agent prompts with industry guides, glossaries, and multi-provider LLM support for scalable, automated content creation.