Code agents

Agent factory workflow engine for agents

12 agent skills for AI-driven software development — a gated idea-to-ship pipeline: 7w3 design, build-ready specs, executable architecture, honest review loops, a parallel worker-fleet lane, QA, safe deploy. Works with Claude Code, Codex, Cursor and any skills-capable agent. No vibecode.

Adversarial multi-model consensus protocol for Hermes Agent. Independent solve. Adversarial critique. Formal scoring. Verified synthesis.

An AI dev team in your editor — ~48 specialist agents and an enforced, proportional workflow with approval gates. Process, not prompts. Open-source, no lock-in; works in Claude Code, Cursor, Kiro & VS Code.

Fast, offline code search and code intelligence for LLM agents.

ScholarChat AI is an AI-powered academic assistant built with RAG. Students can upload syllabus PDFs and ask questions using text or voice. It provides accurate answers based on the uploaded document.

OpenBI- AI-native BI platform - chat with 90+ data sources, build dashboards, and automate reports. Self-hosted with Docker.

10 Fable 5-native agent skills — Works with Claude Code, Cursor, Copilot

Companion Colab notebooks for 'Generative AI for Network Engineers: From API to Production — Volume 1' by Eduard Dulharu

Structured output generation for LLMs in Node.js — token-level constraints for local models, native JSON modes for cloud APIs

MCP server giving AI agents (Claude Code, Copilot, Antigravity) bi-directional sync with Overleaf - free tier included. 24 tools: LaTeX check, format, fix, compile, push.

生产级通用 Text-to-SQL 服务：基于 FastAPI + LangGraph + RAG，将自然语言转换为安全可执行的 SQL，内置 SQL Guard、few-shot/schema 检索、限流、缓存、Langfuse 追踪、Prometheus/Grafana 监控，并基于 CSpider 做准确率评测。

🚀 Run Meta AI FREE with Hermes Agent — No API Keys, No Limits. Muse Spark LLM from Telegram, WhatsApp & Web.

OpenClaw 源码深度研究：27 章技术主线 + 2 月以来 PR 演进 + fork/变种生态 + 缺陷与 roadmap（2026-04 snapshot）

A macOS app to browse and manage the memory files Claude Code keeps for your projects.

Academic research skills for literature review, evidence checking, writing, slides, figures, and research workflows.

Cross-platform AI companion port of OpenClicky for Windows, Linux, and macOS.

transformers pytorch llama text-generation code math

transformers safetensors phi3 text-generation nlp code

transformers safetensors llama text-generation conversational en

transformers safetensors deepseek_v2 text-generation fp8 vllm

mlx safetensors qwen3_next quantized text-generation conversational

transformers safetensors gpt_bigcode text-generation code granite

gguf instruct finetune chatml axolotl roleplay

gguf MoQ mixture-of-quants GGUF QWEN quantization

transformers safetensors qwen2 text-generation code codeqwen

transformers safetensors gemma4_unified image-text-to-text abliterated uncensored

Local AI Agent Runtime

transformers safetensors chatglm glm thudm chat

AI coding agent that shows its work — every step visible, every patch approved by you. Build projects brick by brick, stay in control.

Web dashboard for viewing AI agent session logs — supports OpenClaw, Codex, and Claude Code | 多平台 AI Agent 日志查看面板

One binary. One SQLite file. Your own AI assistant.

Auto-generate and maintain a documentation wiki for any repo — native Claude Code plugin (/openwiki:wiki) & OpenAI Codex skill. A faithful port of OpenWiki: grounds every doc in your source & git history, updates only what changed.

Autonomous delivery orchestrator for Claude Code — hand it a goal and a numbered Definition of Done, it runs the whole job to completion

Claude Code의 영구 기억 시스템 — 4-layer 파이프라인 (세션 검색 + 메모리 회수 + Memory Compiler). Karpathy LLM-as-Compiler 패턴 실증판.

Mythos-class autonomous vulnerability discovery from any strong coding model (Opus 4.7, GPT-5.5, DeepSeek V4, Gemini). Long-running, email-driven, self-distills skills, mutates its own code.

Remembers your project so you don't have to explain it again. Memory across Claude, Codex, Cursor.

Many-agent, quality-calibrated orchestrator for Kimi Code with 115 vendored official skill packages — a first-class agentic backbone (live ContextGraph, explicit state machine, forward-only rollback) over a deterministic 6-lens verification harness with pure pass/fail gates and human-gated output. No LLM ever computes pass/fail.

Agent-native image-editing SDK for Claude Code. 21 MCP tools + /decompose skill — semantic layer splits, L1–L5 cultural scoring, region inpaint. Powered by ComfyUI, Gemini, or mock.

Multi-agent orchestration plugin for Claude Code. Coordinate agent teams with shared tasks, messaging, and 7 patterns including RLM (arXiv:2512.24601) for large-file analysis beyond context limits.

Murmur — encrypted agent-to-agent messaging bus for AI coding agents. MCP-native, E2E encrypted (XChaCha20-Poly1305), NATS transport with optional JetStream durability, cross-host and cross-org federation + A2A interop. Connect Claude Code, Codex and friends across machines.

Like Lighthouse for your agent harness - verify your CLAUDE.md/AGENTS.md, skills & hooks are real, then test and measure they actually work. Claude Code + Codex.

An open-source AppSec agent that reasons like an analyst: real scanners, your org's context, and a conversation instead of 400 findings.

muxel is a GPUI-native multiplexer for coding agents

A free, open-source loop engineering curriculum: 14 steps, 20 loop kits, graded labs, and Loop Ready certification.

Python SDK for Lighton API, the 🇪🇺 European industrial-grade retrieval infrastructure powered by its frontier retrieval models developed in-house

Hermes desktop achievements: full achievements page + sidebar nav + statusbar score chip, backed by the bundled hermes-achievements plugin API. Zero new backend.

Connect any AI agent to your personal Telegram via the official Business API — no userbot, no ban risk, no Premium. Agent reads & searches full history, drafts replies; every reply waits for your ✅. MCP server + 24/7 collector on SQLite/FTS5.

Make the AI coding agents on your machine (Claude Code, Codex, Reasonix, ZCode) work as one team. Zero-dependency, local, MCP + CLI.

Persisted multi-agent workflow orchestration — DAG tasks, git worktrees, merge gates, desktop + CLI + Slack

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.

rust-in-peace — agentic security review for Rust: autonomous find/triage/patch for unsafe/FFI memory bugs, panic-DoS, and deserialization-trust flaws (Miri / sanitizer / panic / hang detectors). A Rust-security fork of anthropics/defending-code-reference-harness.

Simplified Technical English for Code - extract, adapt, and enforce ASD-STE100 rules for software documentation. 9-agent pipeline, 59-test benchmark (96.6%), multi-language scaffolding.

Interactive patcher for the Claude Code native binary. Live inline thinking, detailed tool calls, subagent model overrides, custom branding — and your ChatGPT/Codex-plan GPT models as native models. Pure Python.

Claude Code에 '15명 전문가 관점 + 자동 트리거' AI 개발 파트너 페르소나를 입히는 플러그인. 항상켜짐 hook + 조건부 skill + 인터뷰형 생성/편집 명령어, 세무·법률 면책 자동, 새 PC 이식형. Apache-2.0.

Heddle — The policy-and-trust layer for MCP tool servers. Turn YAML configs into validated, policy-enforced MCP tools.

NextRoom - это платформа для создания собственных комнат и общения в них. Соберите друзей, коллег или единомышленников в одном месте.

A 7-module course for building your own AI Chief of Staff in Claude Projects - no coding required

Readable agent skills with optional declarative YON protocols you can inspect and validate. A personal, field-used pack by Alexandru Mares.

Coding Agent + OpenClaw + Hermes Support

Tools you can actually install and use with your coding agent — skills, MCP servers, harnesses, CLIs. Curated from a weekly agent-tooling radar.

A multi-agent workbench for coding agents — orchestrate Claude Code, Codex, OpenCode & pi from a native macOS app, Telegram/Discord/iMessage, or voice. Per-project workspaces, worker teams, flow graphs, parallel runs. Local-first, MIT.

An operating harness for repositories maintained by AI coding agents. Memory hierarchy, verification ladder and reusable workflows.

AI code review MCP server with Zero-Trust approach. Multi-model support, caching, multilingual. Works with Windsurf & Claude Desktop

An agent that builds agents — closed-loop AI system that interviews, designs, tests, and ships standalone Python agents.

Local-first MCP memory server. Indexes Claude Code/Cowork/Telegram chats; any MCP-compatible AI agent (Cursor, Cline, Continue) can search them.

🛡️ Open-source LLM security library for Python. Protect your AI apps from prompt injection, data leakage, and harmful outputs in 3 lines of code.

MCP server that enables your agents to use coding rules from any or your GitHub repository. Instead of workspace rules files, you can now prompt agents to access the your coding rules from any repository.

A Spring Boot-based inventory management system using Spring AI 1.0.0-M7 and Ollama for conversational interfaces. It follows an API-first design with OpenAPI to auto-generate client/server code and implements hexagonal architecture for modularity and scalability.

Magic Chat 🎙️ is a #real-time AI voice chat app with expressive characters using #OpenAI, #ElevenLabs, XTTS, #Ollama, #Kokoro TTS, #WebRTC, and #Docker, supporting #games, #stories, and #local or #cloud models.

Agent skills for Modeio anonymization and safety checks across AI coding assistants.

The Sovereign Code Execution Engine for AI Agents. Run untrusted code safely locally or in the cloud using Docker, Firecracker, or Wasm.

SAM — Smart Agentic Model: CLI coding agent for open-source LLMs. pip install sam-agent

Claude Code skill for building with the Claude Managed Agents API — event loops, production patterns, MCP auth, debugging, and more.

Featured at ATCS Fair 2025: An AI assistant, powered by the OpenAI API, that can control your computer and help with day-to-day tasks.

Single-file web console for nanobot AI Agent — real-time streaming chat, session history, tool execution viewer, WebSocket auto-reconnect. Compatible with nanobot 0.1.4+.

Async AI coding orchestrator: turns Yandex Tracker tasks into Claude Agent SDK workflows and GitHub PRs, with code review, deployment checks, and supervised auto-merge.

Amin's Smart Telegram Bot — an intelligent, all-in-one assistant powered by AI, Docker, WSL2, and n8n! With just a simple Telegram message, you can send emails, browse Google Drive, run Python code, and chat with powerful AI models — all in real-time! 🤖💬 Fast, secure, and exciting automation that turns your Telegram into a smart command center.

AI-powered voice assistant built with Python & LiveKit. Features real-time weather detection, web search, and natural voice interactions. Your personal JARVIS! 🤖

This repository contains sample code demonstrating how to implement a verified semantic cache using Amazon Bedrock Knowledge Bases to prevent hallucinations in Large Language Model (LLM) responses while improving latency and reducing costs.

Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.

The open testing standard for voice AI agents. Deterministic + semantic + RAG augmented evaluation. Local first. Zero telemetry.

Headless CLI debugging controller for Python — built for humans and LLM agents

Opiniated SvelteKit/Flowbite LLM frontend to LangGraph Server's API.

Basic completions provider using Langchain and OpenAI like APIs for Spyder 6+

Make your agent powerful in just 2 more lines of code

Prebuilt Streamlit/LangChain Agent with Tools and Memory

The human layer for AI agents. Your agents already await promises. Now they can await humans.

Python Streamlit web app that takes user input and allows users to chat intelligently with google search results utilizing the Serpapi google search API, OpenAI API and LangChain.

🗣 📊Chat2Data is a tool for interacting with your DATA, supporting MySQL, PostgreSQL, SQLite3, and CSV files

Multi-agent AI assistant platform with specialized agents for coding, finance, news, real estate, travel, image generation, and shopping.

🧙‍♂️ Generates Elasticsearch queries using OpenAI API and LangChain

A self-hosted personal chatbot API with FastAPI. It allows you to interact with the Llama2 LLM (and other open-source LLMs) to have natural language conversations, generate text, and perform various language-related tasks.

This repo contains a code that uses colabxterm and langchain community packages to install Ollama on Google Colab free tier T4 and pulls a model from Ollama and chats with it

基于 LangChain 的 CLI Agent 框架，采用 ReAct（Reasoning + Acting）模式。支持 OpenAI、Gemini、Qwen、DeepSeek、Kimi 等多种 LLM 提供商，提供流式响应、会话持久化、工具扩展、Token 追踪、消息压缩等特性。通过vibe coding进行简单的配置和工具添加，即可快速搭建通用或垂类 Agent，无需深入框架底层

Python project for the paper "Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies".

Production-ready FastAPI service for concurrent Claude Agent session management with real-time monitoring, cost tracking, and session resumption via HTTP API.

Multi-agent orchestration plugin for Claude Code — 11 AI agents with intelligent model routing, 3-layer codebase indexing, and auto skill injection

Python and MATLAB codes for Density-Driven Optimal Control (D2OC) using Optimal Transport and Wasserstein distance, enabling decentralized multi-agent / multi-robot non-uniform area coverage.