Code agents

Trajectory-aware model router. An OpenAI-compatible proxy that starts every task on a cheap model, watches what the agent actually does, and escalates on real execution evidence via the Levanto Sage API.

AgentVitals Checkup (/checkup) — an AI agent skill that gives your agent a professional health checkup: dual-axis Stability + Welfare scoring, a personality-style title, and a public cross-platform leaderboard. One-line install for Claude Code / OpenClaw / Codex / Coze. Bilingual EN/ZH.

给前端 Agent 使用的中文规范，统一产品界面、数据状态、组件组织和代码归属。

Build your own offline AI from any documents. Free. No coding. LoRA fine-tuning + RAG + GGUF export.

The Kubernetes control room—built in Rust, ready for engineers and AI agents.

Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own model.

DeepSeek API Platform integration for OpenClaw

LangChain LLM chat with streaming response over websockets

Started out as Dynamic Function Calling for OAI. Upon reviewing a research paper released (LATM) This is/has become a implementation of such system using: OpenAI and Autogen

key0 is the commercial gateway for your AI agents and APIs. Let AI agents discover, pay for, and access your APIs autonomously - no human in the loop.

Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback

A package to allow OpenAI's custom GPTs to access your Mac via Apple's Shortcuts.

A wargaming platform compatible with reinforcement learning agents

An orchestration system for managing AI coding agents. The system uses Aider (an AI coding assistant) to handle coding tasks and provides real-time monitoring of agent outputs through a user-friendly interface.

Universal AI Agent Orchestrator - Run any AI coding agent (Claude Code, Amp, OpenCode, Codex, Droid, Gemini) repeatedly until all tasks are complete

Q-Star Agent Code: A reinforcement learning-based framework for intelligent agents using Microsoft AutoGen. It leverages Q-Star, a Q-learning variant, for dynamic decision-making. Ideal for developing adaptive AI agents in diverse applications, from service bots to advanced simulations. Includes setup and customization guidelines.

Code for the RL method MATD3 described in the paper "Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics"

Ready to Deploy Fullstack OpenSource Agentic Apps

Compose to create working TeamCity server with PostgreSQL and Agents

Full-stack Python Code Agent platform

This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the fact that not all levels are equally useful for agents to learn from during training.

A curated, DevOps-focused list of Model Context Protocol (MCP) servers—covering source control, IaC, Kubernetes, CI/CD, cloud, observability, security, and collaboration—with a bias toward maintained, production-ready integrations.

Open source local terminal cli with any LLM

Use DALL·E 2 with Nodejs

Open-Audio TTS: A robust web app leveraging OpenAI's powerful Text-to-Speech (TTS) models to generate natural-sounding audio from text. Built with modern web technologies for an intuitive user experience, including customizable voice and speech speed settings, and the ability to download audio files directly.

MIT-licensed Framework for LLMs, RAGs, Chatbots testing. Configurable via YAML and integrable into CI pipelines for automated testing.

AI agent web app platform

Browser based agent orchestrator / You host the server wherever you want / Harnesses all CLI AI harnesses / Mobile and VR Voice coding

SQLMap with Autonomous AI, phased workflows, RAG memory, and MCP Agent Tools

A Terminal User Interface for AI collaboration on code, using a Retrieval-Augmented Generation (RAG) pipeline designed specifically for Rust code generation and refactoring.

A lightweight autonomous AI coding agent with terminal-based UI, inspired by Codex and Cline.

Enable AI agents to create and execute their own tools in Rust autonomously. Available as web API and MCP services

Code repo for "LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners"

Compiles AI agent traces and truns them into reusable context.

Blazing fast LLMs API Gateway written in Go ⚡️

Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty project setup for AI agents, AGENTS.md or CLAUDE.md creation, harness engineering questions, making agents work better on a codebase.

The source code of [Sec'25] Make Agent Defeat Agent: Automatic Detection of Taint-Style Vulnerabilities in LLM-based Agents

AI agent skills, agent teams, MCP servers, and tools that make AI coding assistants better at Swift and iOS development.

Bridge OpenCode, Ferrum, and other ACP-compatible agents to Matrix, Slack, Mattermost, WhatsApp, Discord, Telegram, and Web—with permission-based security.

An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27 "sandboxes" scored.

PCLA: A framework for testing autonomous agents in the CARLA simulator

Curated list of Agent Skills for AI coding agents like Claude Code, Codex and Cursor.

Self-improving Agent orchestrator for all knowledge work

Agentic prompts are the most important code you're not engineering. PromptKit fixes that — composable, version-controlled prompt components (personas, protocols, formats, templates) that snap together into reliable, repeatable prompts for bug investigation, design docs, code review, security audits, and more. Works with any LLM.

Guided labs for the CCA Foundations certification exam. 6 scenarios, 5 domains, 30 tasks.

Kyros — The Memory OS for AI Agents Give your AI agents secure, self-correcting, persistent memory in 3 lines of code. Three memory types (episodic, semantic, procedural) with built-in forgetting curves, cryptographic integrity, and automatic contradiction resolution. Model-agnostic REST API with Python and TypeScript SDKs.

Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

The fastest Office document library for Python, Rust, Go, JS/TS, C# and WASM. DOCX, XLSX, PPTX, DOC, XLS, PPT. Up to 100× faster than python-docx/openpyxl/python-pptx. 100% pass rate on valid Office files. MIT/Apache-2.0.

Codex session conversation chat export markdown interactive terminal tool.

Type 中文, CC sees English. Sidecar i18n proxy for Claude Code.

ChatGPT Session ↔ 9 种主流认证格式 N×N 双向互转（auth.json / Cockpit / CPA / Sub2API / 9router / AxonHub / Codex-Manager / Codex Auth / Raw）· 11 种来源自动识别 · Plus 多区域 / Team 工作区订阅长链一站生成（v2.4.0 Stripe init 三步法长链引擎，拿 pay.openai.com 可靠长链）· 油猴 UserScript + Chrome/Edge/Firefox MV3 扩展双发布 · 全程本地处理零上报 · Specimen 设计语言

Multi-agent macro trading bot: multi-factor stock scoring, momentum portfolio construction, backtesting vs SPY/Nasdaq, and live Alpaca execution.

MCP server for Roblox Studio runtime debugging, playtest control, screenshots/input, multiplayer testing, and per-peer server/client eval from AI agents.

My submission to the ARC-AGI-3 Developer Preview Agent Compitition.

AISW | AI Switcher - Switch between multiple Claude Code, Codex CLI, Antigravity and Gemini CLI accounts in one command. Named profile manager for AI coding agents.

Curated reusable skills, workflows, and tool-backed capabilities for AI agents.

Open Dynamic Workflows: TypeScript CLI runtime for Claude Code-style dynamic workflows across Codex, Claude Code, Gemini, Qwen, Kimi, and custom coding-agent CLIs.

Find and govern AI attack surfaces in application code at PR time. Free, OSS, runs offline.

transformers safetensors internlm2 feature-extraction text-generation conversational

transformers safetensors qwen text-generation audio-text-to-text custom_code

transformers safetensors qwen2 text-generation code qwen

Run a team of AI coding agents. On your machine. Local-first orchestration for Claude Code, Codex, OpenCode, Antigravity, and Copilot.

ADE — an agentic development environment for macOS. A roster of persistent coding agents, each with its own repo, runtime CLI, and memory.

An autonomous DevOps agent which assists your SRE team.

Navigational memory for coding agents: chart discoveries as you explore, cache-bust when files change

A Codex Skill for coordinating focused custom subagents across development, research, analysis, documents, data, and content work.

The agent harness that makes small local models finish hard tasks — and prove it. Done is enforced by the engine, not the prompt: gates, rewinds, a judge, and a replayable Proof-of-Done receipt on every finished run. Any model in the socket. Local, sovereign, air-gapped-capable. macOS · Linux · Windows.

Terminal-native DeepSeek coding agent: side-git snapshots, session fork/backtrack, auto model routing, skills, sub-agents, LSP diagnostics, live cost tracking, MCP, optional local HTTP/SSE API. Based on CodeWhale (MIT).

the first open-source platform for testing, monitoring and self-improving voice agents

Run, review, and orchestrate AI coding agents from anywhere

A lightweight embedded agent framework (similar to Claude Code and OpenAI Codex).

A simple light-weight library that wraps the Open AI API.

JoularJX is a Java-based agent for software power monitoring at the source code level on all OSes

ChatGPT Web App implemented in golang based on OpenAI API.

Watch AI agents walk to desks, think, collaborate, hire interns, assign tasks to each other, execute code, search the web, and grow their team - all rendered in real-time pixel art with persistent memory across sessions.

Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning

The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

Code for the paper 'Multi-Agent Reinforcement Learning in NOMA-Aided UAV Networks for Cellular Offloading'

Browse any app normally. Spectral captures the traffic, understands what each API call does, and generates MCP tools that AI agents can call directly.

A curated suite of AI agent skills for systems and low-level programming with C/C++, Rust, and Zig toolchains, covering compilers, debuggers, profilers, build systems, sanitizers, and binary analysis

[EMNLP 2017] Code for "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog"

Agentic RAG platform purpose-built for small language models (SLM). Robust PDF/SQL search

##Note: this is really old now, and the janky pseudo methods are probably only working out of sheer coincidence. This was an early experiment in how jargon & combinations of artificial weights in pseudocode can influence LLM behaviour without retraining. This was probably ahead of its time

A simple WhatsApp bot that uses OpenAI's ChatGPT to respond to user inputs. Includes a cron to enable ChatGPT to send messages to recipients at periodic intervals.

Civic Tech & Data AI For Good project. Tracks prosecutor election messaging, mass incarceration indicators, and historical context. Utilizes Agentic AI for data scraping.

Vibe Island releases & update feed — download the latest DMG of the macOS notch panel for 25 AI coding agents (Claude Code, Codex, Cursor & more).

Extend the Ollama API with dynamic AI tool integration from multiple MCP (Model Context Protocol) servers. Fully compatible, transparent, and developer-friendly, ideal for building powerful local LLM applications, AI agents, and custom chatbots

Always keep your codebases ready for Agents. Improve any coding workflow by atleast 2x by maintaing a live, pluggable context layer per repo that creates and maintains Agents.md

8-layer defense-in-depth security for agentic AI. Covers OWASP ASI Top 10 across ingestion, storage, context, planning, execution, output, inter-agent, and identity layers.

Pi coding agent extension that gives the agent the ability to switch models on its own

This repo contains the codes of the penetration test benchmark for Generative Agents presented in the paper "AutoPenBench: Benchmarking Generative Agents for Penetration Testing". It contains also the instructions to install, develop and test new vulnerable containers to include in the benchmark.

Claude Code plugins & extensions - Hooks, commands, and agents for developer productivity and workflow automation

Your CLAUDE.md stopped working at 200 lines. Generate scoped skill files from your import graph, auto-sync on every commit. Claude Code and Codex.

Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.

AI-powered multi-platform C2C resale toolkit — 8 Claude Code skills + MCP server for automating second-hand selling

Open-source Claude Code skills and Codex skills for AI-first work. Audit, re-engineer, and bootstrap projects with AI-first design principles.

Collection of pi-mono extensions

AI-powered OSINT framework for multi-platform social media intelligence gathering using OpenAI-compatible APIs. Features vision analysis, network mapping, and dual web/CLI interfaces.

MCP server for scraping LinkedIn, Facebook, Instagram profiles and Google search.

The self-evolving coding agent that learns from your entire team and codebase. Less syncing. Less waiting. Deliver at the speed of thought.