Code agents

Max gateway adapter for Hermes Agent

Windows system tray app that shows your Codex weekly usage limit at a glance. Native C++/Win32, no runtime required.

Turn your iPhone into an AI agent host. 165+ native tools, 30 agents, 10 channels, 5 AI providers. Pure Swift + Claude API.

Stream Deck plugin for Claude Code — live usage gauges, session status, and approve/deny keys. macOS + Windows.

Local-first desktop command center for running and supervising teams of AI coding agents — embedded Claude Code terminals, a live agent constellation, kanban work board, cron schedules, and spend budgets. All state in local SQLite. Tauri 2 + React + FastAPI.

🚀 AI Books MCP Server - Extend LLM context 15-60× via gravitational memory | Official MCP server for Claude Code & Anthropic

MCP remoto que fornece alguns dados estatísticos brasileiros.

Unofficial Windows always-on-top widget for remaining Codex and Claude usage

Claude Code 完全學習指南— 從零開始的 34 章教學 + 85 個實作練習

Disciplined task pipeline for AI agents: SPEC interrogation, self-contained tickets, proof-based execution, replan, retro. EN/RU docs.

Stateful agentic AI workflows on Aurora PostgreSQL with MCP, AgentCore, Strands Agents, pgvector, RLS, and LangGraph checkpoints.

Remote For Xirp — mobile web control surface for the Xirp agent daemon: machines, projects, sessions, live tmux pane. Unofficial.

ChatBI Studio - governed open-source ChatBI and NL2SQL platform with verifiable results, semantic models, RAG, and bounded agents.

AWS Bedrock RAG tutorial: Build a Q&A agent with Knowledge Bases and S3 Vectors (preview). Includes CDK deployment, web UI, and debugging tools.

Visual video search & RAG — ask questions about videos by what's seen on screen. CLIP + Qdrant + bring-your-own-LLM. Apache 2.0.

20 free production-ready domain skills for Claude Code, Antigravity & AI agents — LangGraph, RAG, GEO/AEO, MCP, security

A 股量化交易工作台 — Java 21 + Spring Boot + Next.js 15 + FastAPI AI Agent + AI 投研問答（ToolCalling + MCP）的 Web 量化交易平台

📚 Interactive RAG knowledge base — 25 course videos + 20 advanced topics + production cheatsheet

Java + Python 企业知识库 RAG 工程项目：混合检索、可回归评估、有界并发与公网演示

Local-first AI fanfiction writing system with structured context engineering. Keeps your characters consistent across 100+ chapters. 本地优先的 AI 同人写作系统。

Form-filling agent built on browser-use: describe yourself once, point it at any web form, and it fills every field automatically. You review and submit manually.

AI agent skill for generating structured academic paper reading notes (Claude Code / Cursor / Codex)

Agent 的个性化 Agent：面向Windows 10/11，连接Codex及ACP Agent，提供桌面角色、认知、监督、陪看、情绪反馈和可扩展能力路由。

AI工程纪律框架——从6次真实事故中长出来的29条规则。不是提示词模板，是让AI少犯错、犯了错能被抓住、同样的错不犯第二次的纪律系统。

DeepSeek Harness plugin: auto-repairs invalid tool_calls/tool message pairing in the messages array to stop 400 INVALID_REQUEST session crashes.

Open-source e-commerce AI image generation platform with multimodal RAG, AI agents, bestseller retrieval, product photography, quality evaluation, and batch workflows.

A runtime for reliable multi-agent systems with durable workflows, resumable execution, and human-in-the-loop control

Automatic isolated secondary review for Pi coding agent sessions

🔍 面向 AI Agent 的防篡改审计溯源系统 | Tamper-evident audit trail for AI Agents — generates hash-chained JSONL logs to answer: what did the agent do, how did it decide, and was anything altered? Framework-agnostic core + OpenClaw plugin.

本地优先、Agent 友好的中文创作工作台：把 Markdown 变成图文卡片和长文，支持 Codex CLI 与可选云端协作。

Ryx Sidekick Lite — open-source AI coding assistant for the Unity Editor (Claude).

A verification-first Codex plugin for mathematical modeling competitions: problem analysis, reproducible modeling, rigorous figures, evidence-bound papers, and final audits.

Battle-tested patterns from running AI agents in production daily: the CLAUDE.md that finishes work, a 5-layer agent memory stack, overnight autoresearch loops, and LLM-judge alignment.

MacBook-sized decoder-only Transformer trained in an executable Sokoban RL environment

AI Multi-Agent Documentation Writer using LangGraph, LangChain, and Google Gemini API

Track, visualize, and optimize LLM API spending. Monitor OpenAI & Anthropic costs per feature, detect waste, suggest savings. Zero-config Python profiler.

Deterministic investment decision system — discipline as code, every decision traceable and backtestable.

Multi-agent AI system for Etsy digital products. Scrape competitors → Analyze gaps → Generate PDFs → Track performance.

Production-ready skills for Claude Code and multi-agent systems

team-task for DeepSeek Harness (dsh): long-horizon multi-agent tasks — reviewed plan DAG, runtime-owned settlement, event-log truth, resident reconciler

Evidence-governed multi-agent decision system with blind expert rounds, red teaming, RAG, decision memory and typed verdicts.

Adversarial AI code review that declares what the round could not close. Python CLI + GitHub Action, MIT.

Local-first AI portfolio intelligence console for personal market research, portfolio monitoring, and risk-aware decision support.

Resident peer agents for pi — long-running partners inside your session that tick on their own rhythm, watch the work, and push findings back into the conversation.

Design and audit autonomous agent loops using a tested framework for triggers, verification, guardrails, and human escalation.

Local-first Agent OS — project management, agent orchestration, docs, memory, and developer tooling. Runs on PGlite. SaaS-ready.

An agent for coding and everyday tasks, powered by your own ChatGPT or DeepSeek account. No API key, no per-token billing.

Pi-native implementation of SKILL.state for scalable long-horizon agent execution

Rate limit? Switching coding agents? Stele keeps write-ahead task state so work resumes in any harness with nothing to re-explain.

transformers gguf code llama llama-2 text-generation-inference

Local dual-agent room for official Claude Code, Codex, and Grok Build. Efficient collaboration, token-friendly, mix a strong planner with an economical executor. Native harnesses — not a replacement. Interruptible and auditable.

Prolog Agent Framework, Reusable Agent Skills, MCP Server Pattern, Neurosymbolic AI, and Safe Multi-Engine Execution (Scryer, SWI, Trealla, Tau).

A modern, terminal-based dashboard for managing tmux workspaces. Built with Python Textual, it features a command palette, live previews, robust session persistence, and seamless zero-friction resumption for AI coding agents.

"Too Many Tools" CLI coding agent.

11,000+ Agentic AI APIs, AI model APIs, autonomous agents, and MCP servers for building AI agents, copilots, automation, and LLM apps.

Send Facebook Messenger and Instagram messages from Laravel — every message type, with pre-flight validation and clear, structured errors.

MCP server for educational dermatology knowledge, MoleCare API tools, and MLOps operations tooling. Runs in mock mode with no credentials. Not a medical device.

🚀 Discover and install new skills for your AI Agent with OneSkill, your gateway to a vast library of capabilities and seamless automation.

Rewrites convoluted AI output into plain language — separate rule sets for English and Traditional Chinese | 把繞口的 AI 回覆改寫成白話，中英各一套規則

Autonomous engineering loop for Claude Code: queue a goal, get it researched, designed, planned, built and reported in fresh-context workers. Self-feeding hooks, tiered agent fleet, script toolbox, token & noise-floor measurement, memory/context MCP. Plain files, plain Python.

Local dashboard to switch the active Claude Code account with one click, showing each account's 5-hour and weekly quota. Zero dependencies, host and WSL, Docker-ready.

Latex Editor Assisted by AI (Use your gemini | openai | anthropic Key or Ollama Url)

Run Claude Code through a local gateway with Opus 5, direct Codex, Kimi K3, Qwen 3.8 Max, and Codex-backed agents.

Display Claude.ai usage limits on a $30 desktop WiFi clock (GeekMagic SmallTV ESP32)

AI-powered social media strategist for Claude Code. Drop your @handle, get a full strategy. Audience psychology, viral content systems, growth analysis — zero fluff, pure results.

Context compression for LLM pipelines that proves nothing protected was lost before it emits, and refuses when it cannot. Refusals count against the published numbers. Paper, benchmarks and receipts ship with the code. Open core by LaconIQ. Apache-2.0.

AI-powered placement intelligence for students. Analyze your resume, match job descriptions, identify skill gaps, and get a personalized roadmap.

Self-hosted cross-grounding Q&A for code and documents, with verifiable evidence.

Understand long videos by decoupling perception and reasoning through hierarchical graph memory and an agentic retrieval mechanism.

🛡️ Open-source AI security scanner & LLM red-teaming platform. Test LLM APIs, chatbots, agents, MCP servers & RAG for prompt injection, jailbreaks, data leaks & unsafe tool use — with OWASP LLM Top 10 mapping and plain-English, audit-ready reports.

AWS-native AI Security Posture Management for AI agents (Observe • Govern • Defend). Discovery, OWASP/NIST/MITRE posture rules, runtime detection & Bedrock Guardrails enforcement, and AIDR integrations (Security Hub, GuardDuty) — open source, in-account, extensible.

Agnara is a Python 3.14-native capability framework for building modern services for humans, apps and AI agents. Define business capabilities once and expose them through HTTP, MCP, A2A, events and tasks. Protocol-neutral, agent-first, async, observable, secure by design, modular and built for the post-REST era. Fast by architecture, not magic.

Real-time interview and meeting assistant: captures system audio, transcribes with Groq Whisper, detects questions, and streams AI answers to an overlay hidden from screen capture. Runs on one free API key.

Free, open-source, local-first AI agent desktop app — a Claude Code / Cursor / Copilot alternative. Reads & writes files, edits code, runs commands. No setup, no API key needed. Windows, macOS, Linux.

A native VS Code client for DeepSeek Harness (DSH) with sessions, streaming replies, tools, model controls, and workspace-aware workflows.

可供 coding agent 调用的标准化招投标编制 Skill + Agent：九步流程、评分镜像目录、风控隔离、五专家评审、DOCX 一键整合，含监测/测绘两个完整样例

A Claude Code harness in Java 25 that goes beyond the CLI it mirrors: built-in multi-protocol model routing, a Feishu connect surface, a live usage HUD, and a project drawer with true cross-project resume — all in the terminal.

PlotRail companion skill for existing manuscript intake, diagnosis, refinement, style learning, continuity audit, and compact handoff.

AI 足迹 — 跨平台智能收藏管理工具。AI自动分类整理、共享协作、Agent API接入。支持PC/手机H5/浏览器扩展。

Cross-agent marketing strategy pack with 29 Agent Skills, 24 specialist agents, neural marketing graph, evidence challenge gates, and deterministic utilities.

Run your entire job search from one local, AI-powered dashboard: find the roles worth your time, tailor for each, work the right people, and keep every follow-up alive. Open source, your data stays yours.

dsh plugin: DeepSeek Harness 的模型层 = raincode(模型池/缓存/重试) + /skills 浏览

Autonomous Red vs. Blue AI Fraud Simulation & Defense System for UPI & Digital Payments. Features LLM-driven zero-day attack generation (F3 Taxonomy), PyTorch Bidirectional LSTM + LightGBM + GraphSAGE multi-model defense, and real-time SIEM dashboard.

桌面端 Claude Code 工作台，支持会话级上下级协作（主管派活 / 员工执行 / 汇报验收）。

Pin, blitz, merge. Autonomous coding pipeline: GitHub issue → EC2 spot instance → OpenCode agent → pull request. From issue to PR. With a trail.

Rust multi-agent coordination platform: HTTP/SSE gateway, agent runtime with token-budgeted context, per-tool sandboxing, multi-provider LLM support.

ARI is a production-grade, open-source AI voice assistant and agentic orchestration platform. Powered by FastAPI, Go Fiber, React & WebGL, ARI delivers real-time voice command processing, intent detection, multi-step LLM planning, and localized telemetry optimization.

An autonomous AI agent that lives inside your real Telegram account over MTProto — not a bot. Reads and searches your chats, acts under a permission policy you control, answers people while you're away, and takes instructions from any chat. Sandboxed code execution, prompt-injection defence, installable plugins.

The open-source, self-hosted backend for agent-built, agent-powered SaaS—auth, Postgres, AI runtime, sandbox, browser, jobs, billing, security, and observability in one stack.

Agent skills for Cursor, Claude Code, and Codex — reliable agent loops with scope, verify, and resume

openEHR assistant AI plugin suite with Skills, commands, and MCP server configuration for clinical workflow integration

Catch AI-hallucinated package names before you install them

An agent-first calendar for an AI companion's own social life, projects, rituals, and temporal orientation.

呱邻国🐸 AI-powered immersive language learning platform. Paste any text — articles, lyrics, news, scripts — and AI auto-generates vocabulary, sentence translations, and exercises. 120+ languages TTS, any-to-any language pair. The Duolingo alternative that lets YOUR content be the curriculum.

Codex diagnostics and worker governance for Windows: detect approval loops, quota/context amplification, SQLite churn, rollout duplication, rule risks, and long-session degradation.

A coding agent that cannot say "done" without proving it. Terminal and desktop; any OpenAI-compatible model or Anthropic; receipts, a hash-chained journal, and a bar the model cannot lower.

The most comprehensive open source resource for Forward Deployed Engineer and AI Engineering interviews. DSA · AI Engineering · GCP · System Design · RRK · Company Guides. Built in public.

Deep bug audit for coding agents: three sweeps, 12 named defect classes, findings marked confirmed vs hypothesis, a mandatory coverage table, defined P0/P1/P2 — then autonomous fixing, questions only at the end. Works in Claude Code, Cursor, Windsurf, Copilot, Codex and anything reading AGENTS.md

Claude Code skills & full project harness for AI-assisted development — continuous improvement cycle (evaluate → issue → plan → resolve → verify), strict CI + security gates (gitleaks/semgrep/trivy), guard hooks, and score-aligned coding rules. Harness engineering / loop engineering.

Run coding agents in isolated sandboxes, stream their work, and get reviewable pull requests with attached evidence. Self-hostable.