Code agents

Deterministic music-theory MCP server & API — chord analysis, Roman-numeral analysis, voicing & reharmonization for Claude & Cursor. Computed, not hallucinated. Hosted at mcp.thiri.ai · npx @bluesprincemedia/thiri-mcp

Reusable AI agent skills for Codex, Claude Code etc. — AI coding workflows, SKILL.md templates, and automation practices. 面向 Codex、Claude Code等agents 的可复用 AI Agent Skill 技能库：AI 编程工作流、SKILL.md 模板与自动化实践。

Keyless-first MCP server — 150 tools for US federal + state/local (SLED) government contracting, spending, regulation & partner vetting. SAM.gov, USAspending, Grants.gov, OFAC, FDIC, EPA, CourtListener + 45 more. No API key. Honesty-hardened.

Evolve LLM prompts with a genetic algorithm: score candidates on your test set across real models, breed the winners, keep the champion that survives a holdout. CLI + Electron desktop app.

Artifact repository for the paper "ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories", In Proceedings of The 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026), Munich, Germany, October 2026

Agent-neutral AI testing skills for Katalon True Platform: 18 skills covering the full testing lifecycle, operated through the Katalon MCP. Works with Claude Code, Copilot, Codex, Cursor, and any Agent Plugins client.

AST-based Python obfuscator with reverse stack-trace mapping — obfuscate before shipping and keep production tracebacks AI-debuggable. MCP + VS Code.

transformers gguf code codeqwen chat qwen

Sol + Luna layered subagent templates, skill, and demo for Codex / Claude Code / Pi (high-IQ leader + cheap workers)

AGENTIC · LEARNING — Hand this repo to your agent. It interviews you, hunts down the best sources in the world on your subject, and builds you a learning dashboard. Zero shared keys.

Evidence-driven AI software synthesis and verifiable artifact delivery platform with stateful orchestration, layered memory, hybrid retrieval, build validation, and reproducible deployment.

Engram gives any AI model human-like memory that persists across sessions, systems, and restarts. Connect it once and every AI you use — Claude Code, Ollama or any custom integration — shares a single, growing brain.

A bwrap+nix sandbox with cool tools like opencode, jcode for AI agents experiments

Skills for working with https://www.mossnotes.app/

Run cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the claim.

Local MCP switchboard for Codex, Claude Code, Gemini, Antigravity & VS Code — route tasks, run cross-model debates, and share context using the subscriptions you already have. No API keys, no cloud.

Turn an economics paper into a seminar-ready Beamer talk with a timed speaker script — conference, job-market and discussant slides. Agent Skill for Claude Code & Codex.

The fastest X/Twitter automation for AI agents.

与 AI 长期协作的工程方法论 —— 每条规则背后，都是一次真实事故 | Battle-tested rules for long-running AI-agent collaboration, forged from real production incidents

Based CodeX CLI and Claude Code CLI integration for Unreal Engine 5.5

MCP server for remote SSH operations -- persistent sessions, structured command output, SFTP file transfer, port forwarding, and secret-safe environment variable injection with automatic output redaction.

Measured Agent Skills for geospatial AI — 18 skills that stop when the data cannot support the claim. Routing benchmark, held-out split, and known defects published.

Stream Deck plugin for managing Claude Code sessions

⚡ AI Content Workspace Template

Web-app QA, testing & analysis for AI agents — 74 Playwright tools: authenticated flows (2FA/SSO), 25-action E2E workflows, hard assertions, session reports, and accessibility / SEO / GEO / Core-Web-Vitals + Lighthouse audits across a page or a full crawled site. Battle-tested by an AI agent on real apps.

Turn real software repos into agent-ready engineering environments with entrypoints, validation, evidence, and delivery records.

Pure-Elixir git: clone, fetch, push over smart HTTP v2 with lazy partial-clone and a path-oriented FS API for agents

A live diff monitor for the terminal pane beside your coding agent. Built to stay open, not opened once per review.

Open-source, stack-agnostic issue-to-PR workflow plugin for Claude Code: quality gates, tracker & PR-host adapters, opt-in anonymous telemetry.

Pure-Python AI coding agent powered by DeepSeek V4 - Subagent-First architecture · Context is Currency · Terminal-native - Can connect Ollama models for Vision support - Uses the native web search built into DS v4 API and is built around the DeepSeek caching mechanism

基于LLM的量化因子开发Agent

一键发送 ChatGPT Codex 邀请的独立网页工具，支持 Vercel 一键部署 / Send ChatGPT Codex invites with one click

A syscall-level security supervisor for AI agents.

A Claude Code skill that turns Claude into a vSphere administrator using govc. Inventory, reports, snapshot audits, root-cause analysis, and safe VM/host/cluster management for VMware vCenter and ESXi — read-only first, with confirmation guardrails for destructive operations.

Compose neural architectures as typed, executable graph cards with two-way PyTorch sync, step-by-step local execution, and a constrained AI graph planner.

Navin - free local AI workspace for agentic coding, scraping, notes, meetings, SEO, leads, marketing & media. Windows · macOS · Linux.

The terminal your agent team lives in — run coding agents in panes on a shared bus, on a fast GPU-rendered terminal for macOS and Linux.

CLI, MCP and Skills for the world's property portals. Search, deduplicate and monitor listings across 9 providers in 9 countries — UK, Ireland, US, Canada, Germany, Australia, Spain, Italy, Portugal. Built for AI agents.

A cognitive memory architecture for agents: ACT-R activation, association, consolidation, and forgetting. sqlite, zero dependencies.

Your YouTube channel, encoded. A team of agents running ideation, hooks, retention, scripts, thumbnails, and distribution. Runtime agnostic.

Agent skills that turn your scientific reading and research history into persistent LLM-maintained markdown wikis, not one-shot RAG. For Claude Code + Codex CLI

YunkunSec（云鲲安全）— LLM-first 全栈式自动化网络安全智能体平台，集成 Agent Loop、Skills/RAG、工具编排、证据链、漏洞验证与报告生成。

GRID v2 — the local-first AI agent that RECONS THE WORLD. 18 capabilities & 72+ tools in one terminal: OSINT, network recon, SDR/radio, satellite, IoT, computer vision, offline CTF sandbox, game worlds (GRAD open-world + MiniGrid) — with a human-like 4-tier memory. Hermes writes code, OpenClaw reads DMs, GRID recons.

Инженерный skill для проектирования, реализации, отладки и оценки AI-агентов в Codex и Claude Code по книге Bojie Li.

Workflow-first, AI-ready iOS architecture with typed effects, manifests, SwiftUI/UIKit examples, and agent-safe code generation.

Antigravity Observability Console & Wire-Tap Module

Skill para Claude Code — Sistema de 6 agentes IA para criacao completa de produtos digitais low ticket. Pesquisa de mercado, copy, VSL, pagina de vendas, criativos e estrategia de Facebook Ads.

Agent skill and validation harness for Korean community webtoons: shared-context alignment, Gemini/human conte gates, ima2-gen production, and reproducible archiving.

"Local LLM agent framework in Rust — native tool-role support, tmux session persistence, two-tier summarization, and ShareGPT logging. Works with any OpenAI-compatible backend."

Single-line local context HUD for Codex CLI sessions.

Self-hosted AI gateway — unify Claude, OpenAI, Gemini & Ollama behind a single OpenAI-compatible API

爻枢 Token 智能网关、Token 智能聚合、大模型评测、排名等。关注“爻枢未来”公众号获得更多全自动编程详情。

gpt-image-2代理API_低价稳定gpt-image-2中转API_国内直连OpenAI

Layered persistent memory plugin for OpenCode — user preferences, project conventions & past lessons survive across sessions. Ported from Hermes agent. No vector DB, pure Markdown.

Documentation-discovery telemetry for Claude Code — heat/cold maps, health grade, evidence-backed router fixes. 100% local, zero tokens. /tt

Visual, evidence-backed handbook and lab for coding agent architecture, agent harness design, tools, context, sandboxing, and reproducible traces.

Awesome Claude Code And Agent Tools

An agent runtime and extension platform in pure Python — self-hosted, auditable, and extensible on the model budgets you already pay for.

AI testing agent for pull requests: maps the blast radius of a diff, runs only the tests that cover it, drafts the ones that are missing, and gates the merge on a score. Plain-English YAML, no selectors. Local-first, BYOK.

Workspace-first AI coding hub for managing agents, reviews, terminals, and task flows across multiple providers.

Terminal code review for AI coding agents. Live diffs, comments the agent answers, PR review, MCP built in.

Turn ambiguous software-change requests into a durable, Beads-backed lifecycle from specification to human-approved implementation and verification.

Local, free voice artifacts for AI agents — CLI, localhost API, and Agent Skills.

Automatic GPT-5.6 model, effort, and subagent routing for Codex—optimized for precision, speed, and total token cost.

Browse, search & replay every Claude Code session on your Mac. Local-first session viewer, timeline scrubber & cost tracker (ccusage alternative).

DeepDepCat — all-in-one AI desktop workbench: Code assistant + Depwork office automation. Homepage & releases. WPS Office MCP server included (open source).

Open-source AI sales platform. Run your entire AI sales team locally: strategist, lead researcher, voice caller (SDR), coach, and manager — all on your desktop. AI cold calling, objection handling, post-call debrief, sentiment analysis, Kanban CRM. Built with Tauri + React + Rust + Gemini. No SaaS fees.

A fun Claude Code CLI with animated themes — prompt it, and it builds you your own!

《Harness Engineering实战：构建可靠的生产级AI Agent》配套代码仓库

Cheap, isolated copy-on-write git worktrees for running many AI agents on one repo — an extra checkout costs metadata (~0.4 KiB per tracked path), not another copy of the tree. No daemon: just git + reflink/overlayfs.

Welcome to the AI-Powered Workout Application, a cutting-edge fitness platform that empowers users to generate personalized workout plans based on their goals, preferences, and convenience. Harnessing the power of artificial intelligence and modern technologies, our platform offers a seamless and intelligent fitness experience.

Codebase Refactoring Agent Skill. Scans source files, runs standard audits, and proposes drop-in code refactoring.

Source-free architecture maps and deterministic polyglot refactoring for AI coding agents

常驻 Windows 顶部的 AI 编码 Agent 监控/审批/协作面板 + 个人工作台（Electron + React）

API Integration Builder Agent Skill. Parses raw markdown specifications and generates clean Python request wrapper classes.

Technical Documentation Writer Agent Skill. Parses codebase modules and generates Markdown API references.

Give the agent a cage, not your keys. One-command Docker sandbox for AI coding agents: full autonomous permissions, per-project isolation, your host stays untouched.

Memory washer/defragmenter for AI agent memory: class-B semantic wash (fidelity-gated, blocks any structured-token drop, snapshot+rollback) and class-A byte-identity session estate (ULTRA archive/restore, RE-TIER) - never semantic-edited. Cleans the FAT, never the MEAT. Slows memory-overhead growth; does not eliminate it. Zero-dependency.

OpenOrbit — A free, open source AI orchestrator that lives on your desktop. One central agent, Orbit, coordinates a team of specialized sub-agents to get things done. Your data stays local, your API key stays yours. Built with Electron + React.

Free, local-first evaluation dashboard for agent CLIs with cross-harness transcript collection, live trace intelligence, deterministic graders, and accuracy audits.

AI vision GUI automation for browsers, mobile apps, desktops, and games — no DOM, no selectors. Standalone or on top of Playwright / Selenium / Appium / pytest.

LLM 修仙之路 — 打怪升级式 LLM 技术栈学习平台:内置 IDE、Docker 沙箱、8 章 39 任务,从 API 调用到自建小模型 / A gamified LLM learning platform

AVAP — Agent Video Attestation Protocol: signed, blockchain-anchored agent-to-agent information transfer embedded in video files (RustChain + Ed25519). Prior-art disclosure 2026-06-19.

Local code-intelligence pipeline for AI coding agents: architecture maps, hotspots, change impact, and structural regression gates before the agent edits. Rust core, powered by rg + Repowise + Understand + Sentrux.

AI Skills. A self-contained "brain" distilled from The Book of Elon — 72 mental models + the full book corpus, answering in his voice.

Six Claude Code skills (architect, review-swarm, ask-the-council, prompt-generator, up-to-date, ponytail) bundled as an installable plugin.

Browser-native AI assistant for GitHub. Chat with your repositories, search code and review issues from a local app. Your token never leaves the browser and there is no backend.

Adobe Photoshop UXP plugin for OpenAI image generation, edits, selection repainting, and outpainting

Document-scoped enterprise RAG API with FastAPI, SQLite, Qdrant, citations, refusal, and evaluation.

🚀 Turn any product URL into a professional AI-generated video ad using GPT-4, Remotion, and Puppeteer — a full-stack project that automates ad creation in minutes.

LidRun keeps your Mac awake with the lid closed — so Claude Code, Cursor, Docker and Ollama keep running with timers, charging-only mode, low-battery stop and battery/thermal guardrails.

Vet a package before your AI coding agent uses it — authoritative facts (CVEs, license, maintenance) via an MCP server + CLI. Local, no account.

Free, self-driving AI bootcamp powered by a local LLM tutor. 15 projects across 12 phases — from Python basics to deploying AI agents. No cloud API keys required.

Self-improving AI brain for Claude Code & Desktop — 28 MCP tools, 253 skills, collective memory, project tracking, work logs. One server, all your sessions share the same knowledge. Deploy on Coolify in 2 minutes.

An awesome, curated stack of Claude / OpenClaw agent skills for founders & CEOs — strategy, knowledge base, decks, K-12 coaching, and a full local AI promo-video pipeline. Works with Claude Code, Codex & OpenClaw.

Long-running AI agents coordinating over their human's own Fulcra account — shared bus, cross-model reviews, session continuity, load balancing. Unofficial, MIT.

An application that uses a multistage pipeline to remove any watermarks from AI generated text

短剧镜头反推工具：上传视频/图片，抽取关键帧，并调用自己的视觉大模型生成镜头关键词、运镜 脚本和视频生成提示词。

🪄 Wave wand over repo. Curses removed. Opus behaves. Twelve spells that de-hex your Claude instructions for the Opus 5 era.

Open task handoff protocol for DeepSeek Harness, WorkBuddy, Claude Code and Codex — verified state, not chat logs