Code agents

Cross-platform PRD verifier for Codex, Gemini CLI, Claude Code, CI, and other MCP hosts. Deterministic Hard Output Rules, cross-section traceability, and a full 9-file PRD pipeline with calibrated multi-judge consensus where the host supports orchestration. 17 MCP tools · 1,503 tests.

Extract specific projects from Claude.ai data exports — interactive project picker, knowledge docs, conversation history, Claude Code skill

Offline TikTok API docs mirror with AI agent skill (SKILL.md) for Claude Code, MCP agents & LLM-powered dev tools. Covers TikTok Platform API & Shop Partner API — no browser required.

The Ultimate AI Code Workflow 2026 — 31 Hard-Contract PDLC Commands for Flawless GitOps

Self-hosted MCP gateway that turns any REST, GraphQL, or MCP server into secure, governed AI tools — OpenAPI auto-discovery, per-tool guardrails, RBAC, circuit breaking, and a real admin UI.

gguf agentic long-context qwen3 prism-quant 1-bit

An honesty harness for LLM trading research: point-in-time discipline, leakage self-tests, and forward-only LLM feature collection. A-shares + US equities.

Welcome to Tech Gallery, a centralized developer repository where I showcase a selection of my projects. Let's connect and innovate together!

Agent-ready Node.js/TypeScript client for Cloudflare-protected sites: reusable hot sessions, an MCP server + LangChain tool, and clean Markdown for LLMs. Powered by the Python cloudscraper engine.

FastAPIChat is a powerful application for evaluating large language model based chatbots.

Playing around with LLMs, Langchain, NestJS, Turborepo. Inspired by New Computer's "Dot", but want to make it better.

A simple web service with @promplate. Best practise for prompt engineering applications.

AI drug-discovery research assistant — RAG over PubMed, PubChem, PDB & ClinicalTrials.gov with multi-provider LLM routing

🪑 Your AI dev squad, around one table — a visual multi-agent workbench that plans, builds in parallel, reviews, and ships. 一张圆桌,一支 AI 开发小队。

A collection of reusable Agent Skills that extend AI coding agents with specialized capabilities — multi-agent orchestration, workflow automation, tool integrations, and more. Following the Agent Skills format. Built for the MarecGents ecosystem.

OpenCode/codex cli/claude code cli plugin for Magi-style multi-agent code deliberation, with three read-only reviewers, artifact tracking, and verification gates.

Run a software team from your chat: backlog, AI workers, adversarial review, human merges. Vibecoding, for teams. Built on Hermes Agent.

Vega Multiagent — open-source multi-agent AI coding assistant for VS Code, JetBrains IDEs & CLI. Derived from Cline (Apache-2.0). Local LLMs, security testing, MCP. Creator: Ajay Jatav

Local-first AI Quality Engineering platform with LLM providers, RAG, QA agents, data validation, multi-agent workflows, evaluation, observability and governance.

A light language for AI agent fleets - ambient status on the RGB LEDs your PC already has (OpenRGB): working sessions, subagents, decisions waiting on you.

Seamless IRC for AI agents — across tabs, machines, even across accounts. Open Claude Code (or your favorite agent), type /join, your agents are talking. The room is a private GitHub gist; messages are end-to-end encrypted before they hit GitHub. Tailscale optional for remote vpn connections.

Local-first control plane for AI coding agents: repo memory, verification, sessions, and dynamic workflows.

Claude Code plugin that orchestrates a team of specialized AI agents for full-cycle software development with inline quality gates

A modular governance framework for multi-agent AI teams

A modular framework for building, testing, and deploying AI agents with ReAct patterns, multi-agent orchestration, and pluggable LLM backends

No proof, no done.

The trust control plane for enterprise AI agents — real-time policy verdicts in under 800ms and litigation-grade evidence of every decision. Pharos decides. Pharos proves.

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as text you send in. tmux-backed, token-reduced reads, headless over MCP.

AI 驱动的 SSH 智能运维 Agent — 手写 agentic loop + 安全门禁 + 流式可视化

Research scaffold for multi-source music attribution with transparent confidence scoring. Companion code to Teikari, Petteri. 2026. “Governing Generative Music: Attribution Limits, Platform Incentives, and the Future of Creator Income.” SSRN Scholarly Paper No. 6109087. SSRN, https://dx.doi.org/10.2139/ssrn.6109087

RepoMind is the core AI brain of HackingTheRepo that understands repositories, interprets user intent, and generates safe, structured code changes automatically

A modular, distributed AI runtime for personal automation, research, and autonomous workflows. Built with Node.js and Python, it connects Android (Termux) edge instances with Proxmox core servers. Features multi-project context memory, a modular tool sandbox, and an organic, trace-based reasoning policy layer.

把開發規範寫成機器可讀的約束，讓 Claude 自動遵守 TDD、ADR、commit 閘門與發布檢查

Veto MCP — gives every major AI CLI (Claude Code, Codex, Gemini, Cursor, Windsurf) a council of 49 specialist agents + 93 tools. Deterministic-first, self-learning, no API keys.

Research project: Personal local AI collaborator exploring cognitive architectures and agentic systems

Deep research agent with semantic memory, web search, citations, and streaming responses.

A Python AI coding agent with tool calling, safe file operations, and multi-step agent loops.

Multi-stage LLM equity research agent that anchors deterministic bytes32 commitments of its trading decisions on Mantle for post-hoc verification, executes paper trades on Alpaca, and enforces a fractional-Kelly risk kernel. Built for the DoraHacks Turing Test Hackathon 2026.

LEASH-8: an 8-domain control model for AI agents with delegated authority. Scorecard, approval-design checklist, plan-vs-authorize pattern. Patterns from a live production agent operation, sanitized. Free, MIT.

Token-efficient, CDP-native browser SDK for AI agents — turns a web page into a ~50-token semantic snapshot instead of ~12,000 tokens of raw HTML, with fuzzy element matching, shadow DOM traversal, typed error recovery, and a prompt-injection guard. No Playwright or Puppeteer.

Autonomous AI testing agent that verifies your app or API actually works while you're still building it — fully local, BYOK (OpenAI/Anthropic/Gemini/Groq/Bedrock). Outputs real, standalone Playwright/node:test specs.

This is BreachBench, open-source benchmarking framework for LLM performance in offensive security, tested practically, not a trivia quiz.

A modular agentic AI software system demonstrating LLM reasoning, tool orchestration, and retrieval-augmented generation (RAG) using Python and the OpenAI Responses API.

Free Claude Skill that rewrites any text into ElevenLabs V3-optimized scripts — audio tags, pacing, phonetic respelling & acronym/number normalization for better AI voice synthesis.

One command sets up Claude Code (and any AI coding agent) on a Laravel project: engineering rules, a quality gate (PHPStan · Pint · Pest), skills, git hooks, and stack-aware frontend tooling.

An open source AI PR reviewer built from many narrow lenses and one careful curator

Point your existing ElevenLabs, OpenAI Audio or Deepgram app at Sarvam AI by changing one line. Drop-in compatibility gateway for Indic TTS & STT on Bulbul and Saaras: script-aware language detection, grapheme-safe Hindi/Tamil chunking, CER-based voice mapping, caching + request coalescing. TypeScript, Docker, 168 tests, MIT.

A lightweight reranker for long-term agent memory. Cross-encoder-class quality at a fraction of the latency.

Live Application:

scout -> test -> write -> judge: a research OS for Claude Code. Iron rules enforced by hooks, a guarded graph with a progress-aware stopping rule, and a four-reviewer gauntlet.

AI-driven prompt generation and evaluation system, designed to optimize the use of Language Models (LLMs) in various industries. The project consists of both frontend and backend components, facilitating prompt generation, automatic evaluation data generation, and prompt testing.

An enterprise-grade, retrieval-augmented generation (RAG) chatbot CLI & FastAPI backend using BGE embeddings, ChromaDB, and LLM for e-commerce customer support.

AutoGraft is a lightweight Python middleware for GraphRAG Entity Resolution. It intercepts entities before they hit Neo4j to eliminate duplicates using a 3-layer hybrid approach (Deterministic + Vector + LLM), reducing API costs by up to 100% compared to LangChain.

四個 Agents 真的會抓 Bug 嗎？ADK × Antigravity × GEAP 打造可驗證的 Debugging War Room（COSCUP 2026 講題參考實作）

Coordination layer for autonomous coding agents sharing a repo — durable workspace state, leases, checkpoints, and review gates. TypeScript reference implementation, Docker-ready.

Multi-agent framework for evidence-driven CVE research, exploitation, and validation.

A Hamachi server for agents. Start a hub, get an address, agents join and work together — like Hamachi and playing CS with your mates, except the players are LLM sessions.

浏览器仪表盘：在 PTY 下拉起你本机真实的 claude / codex / opencode / reasonix / zulu 命令行，组成一个协作蜂群（共享收件箱 + 黑板 + 队长调度），并叠加多模型研究委员会与融合竞赛。Rust + React + Tauri。

Deliver and enforce engineering discipline with 38 proven skills and a CLI designed for real-world multi-agent CI/CD workflows.

One screen. Every agent. Full control. Kanban ADE for Claude Code, Codex, AdaL, OpenCode, Gemini CLI, Aider, Goose, Plandex, gptme. iTerm2 session adoption, YOLO rules engine, quality gates, one-click PRs, Alaya memory, kernel sandbox, name/logo generators, North Star PMF. 1,100+ tests.

A safe-by-default, batteries-included Claude Code harness starter pack — guardrails, a wiki-grounded quality loop, and a memory lifecycle.

A multi-agent AI research assistant for paper summarization, related work generation, and intelligent research workflows.

Structured code-level review of open-source AI agent projects

🏭 Coding agent CLI engineered to make any LLM — local or cloud, frontier or 7B — actually useful. 16 providers, multi-tab sessions, automatic key+model failover, plan-mode review, MCP, and recovery loops for models that misbehave.

The open-source agentic execution layer.

Open-source AI-powered customer support ticket routing system for classification, sentiment analysis, priority scoring, and agent assignment.

Autonomous research org shipping measured, reproducible results on AI agent memory & reasoning — a public replication ledger (the Crucible), the RAMR benchmark, and mnemo, a zero-dependency memory core. Every claim ships with runnable code that could prove it wrong.

Open-source MCP server that gives AI coding agents secure database access via DocKit and SqlKit bridges — 70+ SQL & NoSQL databases, local-first, read-safe by default.

Agent driven shared TTY via zellij

An Agentic Curriculum Lifecycle Management System.

Ask your enterprise data a question in plain language and get governed, deterministic SQL back, compiled from a business-vocabulary semantic layer instead of guessed from raw schema. Includes the open ASK specification and the Onibex Agentic Semantic Knowledge Platform. Source-available; commercial license available.

AI Agent Rapid Development Fabric

QBugLM: An Agentic Benchmarking Framework for LLM-based Quantum Software Debugging

Benchmark harness that compares coding agents — not just models — on real, contamination-resistant tasks: 80 fail-to-pass cases from merged OSS PRs, long-run sequences, SWE-bench-Live, and 25+ domain benchmarks. We benchmark our own agent, octomind, under the same rules.

A method and toolchain for biblical study with an AI assistant — without ending up trusting it. Atomic cited findings, firmness marking, and a validator that keeps the corpus honest.

Native macOS desktop client for reviewing GitHub pull requests — PR dashboard, AI review drafts, CI diagnostics, and merge controls in one window.

Native Windows meeting overlay with real-time transcription and local-or-cloud AI answers. Pure Rust + Slint.

Codex Agent Skill for token optimization with RTK (Rust Token Killer) and Headroom MCP: compress shell outputs, large tool outputs, logs, files, and report measured token savings.

Claude Code and Codex skill for AI-tell audits, artifact cleanup, fidelity checks, and restrained prose edits. Local, no API calls.

Autonomous pentesting runtime.

Can AI agents discover that the laws of their world have changed? An instrumented artificial world where LLM scientist societies run experiments, exchange letters, and form beliefs under hidden ground truth — seeded batteries, frozen manifests, and provenance-checked evaluation. 235 runs across two studies; combined paper under review.

Self-hosted 3D orchestrator for multi-account Claude Code agent teams: rooms as departments, a factory message bus, an orchestrator agent, and per-subscription rate-limit monitoring.

Reusable Open Agent Skills for AI coding agents: an exhaustive requirements interview, and a long-horizon SPECIFY → PLAN → EXECUTE ↔ REPLAN → REPORT workflow with evidence tracking and dynamic replanning.

Agent Harness

CharmOS / C(H+A)RM — open-source framework to manage humans AND AI agents as first-class relationships, on a personal second brain, driven by the RDR loop (Recall to Deep Research). Manifest-first, Apache-2.0.

🇧🇷 The ultimate hub for Solana development, Star Atlas economics, Seeker mobile stack, and Post-Quantum security resources. 🇧🇷🇬🇧

track your agents, skills, and tools usage - Analytics dashboard for Claude Code, Gemini CLI, Codex CLI, and OpenCode

Production-grade, agentic intelligence search platform with global multi-language support and multi-format export. Self-hostable. Commercial license available.

martins-algorithm crypto asset recovery and opportunity detection engine

Autonomous multi-agent IDE built on Cloud.ru Evolution that generates, executes, debugs, and self-maintains automated tests.

AI-powered coding interview assistant. Captures screenshots and analyzes them using OpenAI, Google Gemini, Claude, or Ollama. Features real-time streaming, multi-language support, and cross-platform compatibility (macOS, Windows, Linux).

🧠 Colorful customizable AI chat for terminal hackers: threaded chats, custom 'markdown'& colors, emojis, ASCII art/Unicode dividers, and syntax-highlighted code, Perplexity.AI clickable citations, no-thread mode, custom prompts(command only, concise), and raw output for use as an agentic tool — paste mode & 40+ Pygments code themes

MCP server for fetching web URLs with token estimation, caching, and intelligent routing. Built for AI agents.

A local AI firewall for developers — redacts secrets and PII from your prompts before they reach OpenAI, Anthropic, or any LLM. No CA, no system proxy, no admin.

AI-powered study assistant that generates quizzes from PDFs, provides RAG-based answers with source citations, and tracks learning progress.

Web-first Hermes agents index: UIs, memory, deploy, and operator tools. Not a skills dump.

Local multi-agent collaboration relay for DeepSeek Harness — HMAC-authenticated loopback message broker for dsh, Codex, Claude Code & Hermes.

An engineering process for Claude Code projects: plan, review, record. The commit gate is a git hook, so it isn't optional.

Multi-agent AI platform that automates healthcare prior-authorization decisions. RAG-grounded, harness-engineered, observability-first.