Code agents

A fully functional web workspace for Claude Code CLI—chat, Kanban task board, task scheduling, multi-agent orchestration, MCP servers, skills, remote access (Web, SSH, Telegram), projects, and real-time data streaming.

Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with PostgreSQL, and real-time streaming responses. Built with TypeScript, React, Prisma, and Tailwind CSS.

Cross-platform Claude Code desktop client by hwwn. Multi-workspace, remote mobile access, session branching, BYO LLM. macOS / Windows / Linux.

Multi-objective multi-agent API and environments

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.

Doberman is an AI agent security framework for guardrails, prompt injection defense, runtime policy enforcement, tool-use permissions, agent monitoring, audit logs, LLM safety, autonomous workflow protection and secure AI deployment.

Claude Code skill: turn a Zillow listing into a cinematic room-by-room walkthrough video (Apify → Higgsfield → ffmpeg). Built to sell to real estate agents.

Shareable Claude Code + Codex infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows

Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF

OpenABCode is an LLM-routing coding agent that dynamically routes tasks to the best-suited models

Feishu/Lark group for Claude Code and Codex sessions, vibe coding anytime, anywhere

ChatGPT API Usage using LangChain, LlamaIndex, Guardrails, AutoGPT and more

Make WhatsApp ChatBot and use WhatsApp API to send the WhatsApp messages in python .

Web Application that can generate code and fix bugs and run using various LLM's (GPT,Gemini,PALM)

A comprehensive resource designed to help developers effectively use AI tools to develop websites, apps, and other projects.

OpenAPI definitions, converters and LLM function calling schema composer.

A useful drawer for MacOS. chatting, clipboard, webscraping, window managing, shotcuts. built with Rust and ai-sdk

🦙 echoOLlama: A real-time voice AI platform powered by local LLMs. Features WebSocket streaming, voice interactions, and OpenAI API compatibility. Built with FastAPI, Redis, and PostgreSQL. Perfect for private AI conversations and custom voice assistants.

本项目主要实现使用FastAPI后端框架+CrewAI实现AI Agent复杂工作流。代码实现CrewAI的Flows功能，并支持Flow运行中间结果进行持久化存储和查询(MySQL)，支持多Flow并行(Celery是一个强大的异步任务队列/作业队列库)。

The open source trading arena

从零搭建Agent框架(Build LLM ReAct Agent from scratch)

管理和控制小米/米家智能家居设备的SIKIL，兼容claude code或openclaw等agent，支持设备发现、开关控制、亮度调节、颜色设置等功能。

If it's on the screen, it's an API. Control any desktop app via REST + MCP. Rust.

Enterprise-ready self-hosted AI assistant runtime with sandboxed execution, secure credentials, approvals, and memory

Nemp - The memory plugin for Claude Code that remembers everything.

A professional research suite for conducting rigorous academic research using specialized agents and multi-platform CLI commands. Compatible with Claude Code, Gemini CLI, OpenAI Codex, and OpenCode.

📼 A declarative AI agent environment manager, written in Rust

这是一个为 Claude Code / AI Agent 设计的诊断技能（Skill）。它通过自省式分析和多项特定的压力测试，帮助用户检测当前使用的 API 是否为官方原版的 Claude 4.6 模型，或者是否存在第三方中转、提示词注入与封装。

Open-source library of AI agent skills — SKILL.md files for Claude Code, Codex, Gemini CLI, Cursor

Portable , scalable , secure AI Agents

About AI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading ,trading-agents,ai-trader,ai-trading

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.

Goink 桌面 AI 小说创作助手，对话式写作 + 自动状态追踪 + 本地语义搜索。跨平台开箱即用。AI Agent Novel Generator.

static leaderboard eval:code modality:tools modality:text region:us

Local Anthropic-compatible AI gateway with cheap-first routing, quality gates, safe model handoffs, and an embedded cost dashboard.

An advanced chatbot that utilizes your own data to provide intelligent ChatGPT-style conversations using gpt-3.5-turbo and Ada for advanced embedding, as well as custom indexes and knowledgebase for a seamless user experience.

Ruby Implementation of Nano Bots: small, AI-powered bots that can be easily shared as a single file, designed to support multiple providers such as Anthropic Claude, Cohere Command, Google Gemini, Maritaca AI, Mistral AI, Ollama, OpenAI ChatGPT, and others, with support for calling tools (functions).

.NET 7 SDK for OpenAI with a Blazor Server playground

OpenAI API Native bindings for React Native

🤖 A telegram bot that can sell products and the salespeople can add, delete, and manage them.

A simple NPM interface for seamlessly interacting with 36 Large Language Model (LLM) providers, including OpenAI, Anthropic, Google Gemini, Cohere, Hugging Face Inference, NVIDIA AI, Mistral AI, AI21 Studio, LLaMA.CPP, and Ollama, and hundreds of models.

Claude Code v2.1.88 source analysis: system prompts, 87 hidden feature flags, cost optimization, architecture diagrams, undercover mode, and comparison with Cursor/Cline. No source code redistributed.

A bash script using OpenAI Whisper API for continuous audio transcription with automatic silence detection

Portable Claude Code multi-agent pipeline - skills, agents, hooks, orchestration scripts, and quality gates

[ICLR'26] MedAgentGYM: Training LLM Agents for Code-Based Medical Reasoning at Scale

Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.

Privacy-first LLM proxy and AI gateway - load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hosted. Zero knowledge of your prompts.

Personal Context Manager for Claude Code. Your life in walnuts.

Official Edgee CLI to interract with Edgee's Agent Gateway. Route Claude Code, Codex, Cursor, VS Code + Copilot, and more through Edgee's hosted gateway to cut token spend.

AI Agency Command Center for Claude Code — orchestrates 5 AI teams (Marketing, Sales, Legal, Reputation, GEO/SEO) into a unified zero-employee agency. 9 skills, 5 parallel agents, composite scoring, and professional PDF reports.

Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, HTTP traffic tracking, and an analytics dashboard to track agent actions.

Serverless AI API Gateway / Vercel / Cloudflare / Multiple Provider / Fallback Chain

一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。

デジタル庁のガバメントAI「源内(GENAI)」を完全ローカル(ローカルLLM/OpenAI互換)で動かす非公式プロジェクト。SAML認証(Keycloak)・RAG(Qdrant)・文字起こし(Whisper)・画像生成(SD)・チーム単位ナレッジをローカル完結。

Bounded, typed, ablatable memory contract for long-horizon LLM agents — Slay the Spire 2 testbed

transformers pytorch safetensors llama text-generation license:other

Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT.

Run terminal AI coding agents (Claude Code / Codex / opencode) from your phone. Resilient sessions with replay, end-to-end encrypted.

Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。

Large Language Model (LLM) Inference API and Chatbot

Integrate AI-powered voice translation into a Twilio Flex contact center using our prebuilt starter app, enabling live conversations between agents and customers speaking different languages.

Self-hosted API execution layer that sits between your agent and the outside world. Your agent says what it wants to do. Jentic Mini handles the how — finding the right API, injecting credentials at runtime, and brokering the request

Token calculation for OpenAI models, using `o200k_base` `cl100k_base` `p50k_base` encoding.

Genspark AI open-source, self-hosted Super Agent. Free alternative to Genspark.ai with multi-agent orchestration, deep research, Sparkpages, AI slides & sheets, image generation and 80+ tools. One-command Windows install. Run locally with any LLM (OpenAI, Anthropic, Gemini, Ollama)

Production-ready RAG Framework (Python/FastAPI). 1-line config swaps: 6 Vector DBs (Weaviate, Pinecone, Qdrant, ChromaDB, pgvector, MongoDB), 5 LLMs (Gemini, OpenAI, Claude, Ollama, OpenRouter). OpenAI-compatible API. 2100+ tests.

Turn a stream of token into a parsable JSON object as soon as possible. Enable Streaming UI for AI app based on LLM.

MCP server that reduces LLM context usage when AI coding agents work with Go — structured documentation instead of source-file dumps.

Rewriting Project Claw Code — Python rewrite of Claude Code agent harness. Forked from instructkr/claw-code.

High-performance, code-first workflow automation engine. TypeScript-native with Rust core for enterprise-grade speed, efficiency, and developer experience.

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

We read all 512K lines of Claude Code's accidentally exposed source. 82 docs, 15 diagrams, every subsystem mapped — from the hidden YOLO safety classifier to multi-agent swarms.

MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron CDP, template matching. macOS, Windows & Android. Works with Claude, Cursor, and any MCP client.

An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.

Build an AI agent harness in Rust, from a minimal loop to tools, subagents, memory, teams, worktrees, MCP, and typed tool routing.

CLI, MCP server, and npm library that turns any website into an API — no docs, no SDK, no browser.

Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux/Mac/Windows that provides a durable state, MCP control, and BYOK with full autonomous browsing. Use with Hermes Agent, OpenClaw, or connect to your favorite API provider.

🎨 World-class AI presentation generator · 26 styles · 18 charts · benchmarked against Linear/Anthropic/Stripe/Apple/NYT — a Claude Code Skill that turns one sentence into design-agency-quality decks (HTML + editable PPTX)

End-to-end educational RAG system: dual-engine retrieval (BM25 + BGE-M3 hybrid vector search), adaptive query strategies (HyDE/sub-query/backtracking), BERT intent classification, BGE-Reranker precision ranking, Chinese-optimized text splitting, and FastAPI SSE streaming — from documents to real-time answers.

AI-powered development toolkit with 7 production agents for React Native/Expo mobile apps. Automates accessibility, design systems, security, performance, and testing. Built for Claude Code v2.0.5+

Agentic-first Cursor Rules powered by MiniMax M3 - clarify-first prompting, interleaved thinking, and full tool orchestration for production-ready AI coding

20 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and quality audits (eval-leakage, doc-drift). Works with Claude Code, Codex, and Cursor.

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models

AI-first Turborepo monorepo where Claude Code, Cursor, Copilot, Gemini CLI, Kiro & Windsurf read one AGENTS.md handbook and ship identical, production-grade code. Next.js 16 dapp, React 19 admin SPA, Astro landing, Connect-RPC backend — TypeScript strict, deployed to Cloudflare.

A plugin for AI agent evaluation. Plan evals, generate test cases, interpret results for Copilot Studio agents. Grounded in Microsoft's Eval Scenario Library & Triage Playbook.

MAANG-level AI Engineer interview prep mapped to the AI Engineering Roadmap 2026 newsletter. Deep conceptual, coding, system design & behavioral questions with detailed answers. Covers LLMs, Python for AI, tool calling, agents, RAG, embeddings, vector DBs, eval frameworks & more. Biweekly added with each episode.

Open-source mission control for coding agents. Run cross-vendor workers in isolated worktrees, audit every submission, and revert an entire mission.

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

Chatbot framework

🍣 TunaCode AI CLI coding agent with safe git branches, rich tools & multi-LLM support.

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Model https://arxiv.org/pdf/2411.02433

Code for paper 'Learning transferable cooperative behaviors in multi-agent teams' (ICML 2019)

A Clawdbot skill to run Claude Code (Anthropic) on the host via the claude CLI (Agent SDK).

A self-evolving subagent system for Claude Code

Legal Research Copilot Example Solution built with Generative AI capabilities of PostgreSQL on Azure

Unlock GitHub Copilot as a local API Gateway. Use Copilot with Cursor, LangChain, and any OpenAI-compatible tool.

🦞 Open-source browser-based voice chat for AI assistants. Self-hosted, private, free. Whisper STT + ElevenLabs TTS. Works with OpenAI, Claude, or custom agents.

Agentic Chat App is an advanced AI-powered chat application designed for seamless real-time communication and intelligent responses. Built with Next.js, OpenAI, and Exa API, it leverages cutting-edge technologies to enhance user interactions and provide contextual, relevant information dynamically.

A powerful AI observability framework that provides comprehensive insights into agent interactions across platforms, enabling developers to monitor, analyze, and optimize AI-driven applications with minimal integration effort.

A living collection of frontier research on code agents, from the code we build to the worlds we act in.

Rust MCP server for multi-agent coordination: 34 tools, Git-backed archive, SQLite indexing, advisory file locks, and an interactive TUI console