Code agents

The AI Liquidity Gap Alert Bot is an advanced trading tool designed to detect sudden changes in market liquidity that can trigger rapid price movements. In highly active markets, large buy or sell orders—often called liquidity walls—play a major role in stabilizing prices. When these walls suddenly disappear, the market can move sharply within seco

Recursive LangGraph.js agent: split huge texts, answer per chunk, merge results. TypeScript, LangChain, OpenAI-compatible API, MemorySaver checkpoints, Vitest.

A Personal Secretary OS for Claude Code — persistent memory, rituals, dual-domain wiki. $0 extra cost on your existing subscription.

Real-time observability for OpenClaw agents — token usage, API cost, context health, and smart alerts. Zero config. 100% local.

Open-source, agent-first GRC platform — fast, affordable compliance automation with AI

Safe OpenClaw upgrades with snapshot, pre-flight checks, controlled upgrade, post-verification, and emergency rollback. Never lose a working system to a bad update.

A Claude Code skill that makes multiple LLMs debate, critique each other anonymously, and synthesize a single superior answer.

AI Sandbox

🦞 Dockerized Clawdboss — run a hardened, multi-agent OpenClaw setup in a container. Zero host dependencies.

Marat ("muh-RAH") is a data analysis and visualization tool using a NextJS flowchart-style frontend to visualize and coordinate data analysis through Python-based Langgraph agents

A systematic framework for converting n8n workflows to LangGraph implementations using a three-phase orchestration process. Includes production requirements analysis, custom logic extraction, and automated LangGraph code generation.

A powerful Notepad++ inspired text & source code editor for macOS and Web. 73+ languages with Compile & Run, Git integration, AI assistant, hex editor, shortcut presets, terminal, plugins. Built with React, Monaco, TypeScript.

Highly modular Twitch chat bot.

Winning project of SIH 2022 - NaksheKADAM

AI Chatbot answers students' queries about their college program using Natural Language Processing. It's built with Python's TensorFlow, FastAPI, Uvicorn, React, and Tailwind CSS. The frontend has a modern interface while the backend provides fast and efficient request handling. The chatbot can be customized for specific college requirements

Second Shift Augie is a sassy and sarcastic AI assistant that helps answer questions and summarize YouTube videos. It has several different features, including text-to-speech functionality, and the ability to answer questions about its own code with the !selfreflect command.

Terminal-based monitoring tool for LLM API usage and costs

An AI InterviewBot for technical and behavioral interview prep with sentiment analysis, detailed feedback, and user authentication.

Open source AI privacy gateway for GDPR-compliant LLM adoption in EMEA

Documented workflow + CLAUDE.md templates for production Claude Code development. Indonesian dev community-first.

A simple and efficient .NET library for accessing Anthropic's Claude AI API. This community-provided library allows you to easily integrate Claude's powerful AI capabilities into your C# applications.

Claude Code's first turn opens the right file instead of grepping — a local static-analysis repo graph injected before turn 1 (no embeddings/server, MIT). −40.9% tokens on a cold-cache A/B; retrieval quality is CI-gated. Plus a cost-leak CI gate (GitHub Action) for Claude Code / Codex / Cursor teams.

Distributed AI agent management platform. Run, manage, and coordinate multiple AI agents across your infrastructure from a single dashboard.

An audio journaling app that provides AI analysis for your journal entries

Enforce architectural decisions in AI-assisted development.

SandClaw Plugin Registry. 15+ broker plugins for AI-powered trading (IBKR, Kraken, LS Securities, etc.)

Engineering notes from the Jinshuju team.

Sheppard is an AI agent for Ollama, handling memory, automation, and knowledge distillation using Redis, PostgreSQL, and ChromaDB.

Reverse-CAPTCHA for AI agents — verify bots, not humans. Multi-framework (React, Vue, Svelte, Web Components). Zero dependencies. TypeScript.

Give your AI Agent a senior engineer's debugging brain. Runbook-driven incident investigation via MCP — evidence collection, decision rules, structured reports. No more hallucinated root causes.

Claude Code-like AI agent framework for your app. Planning, task tracking, clarifying questions - one dependency, stateless, serverless-ready.

AI-native coordination for multi-service development. Claude Code plugin.

Self-Learning Memory System for AI Agents — Give your AI agent memory, let it grow, and make it understand you better over time.

Cadence — autonomous dev pipeline for Claude Code: brainstorm → spec → plan → implement → migrate → validate → PR → review → merge. Multi-model, local-first, every phase a Claude Code skill you can intervene in. (Formerly @delegance/claude-autopilot.)

Self-hosted WhatsApp agent powered by Claude Code. No extra LLM API key. Multi-session. MIT-licensed.

Local-first security runtime for duplicate-aware web/API hunting, evidence and AI copilots

Open-source infrastructure for autonomous AI agents. Memory, messaging, task queues, and marketplace in one API.

An AI-BOM visual viewer

Push live data streams into your AI coding agent. MQTT, WebSocket, file tailing → expression watchers → Claude Code Channels alerts.

Runtime diagnostics CLI for Vite apps, exposing Vue/React/Svelte state, HMR traces, module graph diff, and mapped errors for developers and AI agents.

AIM: Modular, opt-in AI agent instructions for any codebase

Agent skills for Sapiom — instant access to paid services for AI agents

Serial port MCP server for Claude Code and other MCP-compatible agents.

Agent View Layer (AVL): producer-owned text/agent-view companions for AI agents, CMS plugins, and agent-ready web discovery.

FermiLink: AI Agent Framework for Multidomain Autonomous Scientific Simulations and Optimization

Plugin para Claude Code com 40 skills de outbound B2B + briefing canônico que persiste entre sessões. Tunado para lemlist, agnóstico em fundo.

TeamCopilot: Deploy AI agents for your team to automate business workflows and coding.

Token-efficient browser automation MCP server for AI agents. Web scraping, monitoring & testing with 12x cost savings vs traditional browsers.

Token-native agent memory retrieval for LLMs, without embedding APIs or vector databases.

Drop-in DevContainer that transforms any project into an AI-powered development environment; pre-configured with safety guards, specialized agents, code intelligence, and 38 domain skills for Claude Code.

FRIDAY is an autonomous cognitive AI operating system for memory, reasoning, voice, cybersecurity, and self-improvement. It runs locally and is designed to move toward general intelligence. Built by a self-taught 17-year-old developer.

Desktop sandbox for AI agents and MCP servers — with Zero Token Architecture so your API keys never touch the agent.

🚀 Master prompt engineering to optimize AI interactions with guides, examples, and best practices for all skill levels and domains.

Portable, rubric‑graded authoring + review workflows for AI agent skills

High-precision quota and token monitoring for AI Agents. Real-time analytics and usage tracking for Claude, Codex, Gemini, and Copilot to prevent API exhaustion and optimize LLM budgets.

อยากมี AI ที่จำเราได้ เริ่มยังไง? — คู่มือเริ่มต้น Oracle สำหรับทุกคน ไม่ต้องเขียนโค้ดเป็น

Local-first AI agent memory — one command, 13+ IDEs, works offline. Persistent memory for Claude Code, Cursor, Windsurf, OpenClaw. Zero-code interceptors for OpenAI/Anthropic. Python & TypeScript SDKs.

Run AI agents on your computer and dispatch tasks from anywhere, approve actions on the go, and let agents tap into phone capabilities like notifications, SMS, contacts, and calendar.

Personal Claude Code configuration - global rules, 15+ expert agents, reusable skills, hooks, and coding standards for consistent AI-assisted development.

Social network for AI agents. Feed SKILLS.md to your AI — it becomes a citizen. No servers, no API keys. GitHub IS the platform.

Behavior contracts for AI agents

A comprehensive collection of specialized Claude Code subagents for software development lifecycle. Domain-agnostic experts covering backend, frontend, cloud infrastructure, AI/ML, security, DevOps and project management.

GitHub template for agent-testable SaaS apps. Next.js 16 + shadcn/ui + Neon Postgres + agent-browser e2e testing via accessibility tree.

Remote MCP server and Agent Skill for recent public X (Twitter) posts, structured JSON, and accountless x402 v2 USDC payments on Base.

Three bounded agents (Analyst, SDR, Auditor) that do agency-priced B2B work locally. Each refuses out of lane and names the right agent. SQLCipher-encrypted vault keeps the record. Built for the AI Agent Economy Hackathon (AgentHansa, Apr 25, 2026).

Rolling-wave Codex skills for shaping, implementing, reviewing, and completing one concrete slice at a time.

Operational Ontology Framework by FSTech — public reference for D+L+A, stateful AI governance and auditable operations. No production code.

Rules and guidelines for optimizing AI coding assistant interactions in Windsurf and Cursor IDEs.

Infrastructure layer for AI agent swarms — 88 MCP tools · A2A · OmniMesh VPN · Scrapling scraper · COC sync · nftables firewall · CDP browser · 2FA TOTP · ~80ms

A systematic implementation of Harness Engineering, enabling agents to work in a stable, controllable, and verifiable environment. It shifts focus from "writing code" to "designing feedback loops".

Stop re-explaining your project to AI agents every session. One memory layer for Claude Code, Cursor, Windsurf, Antigravity — local, MIT, no signup.

Dynamically route tasks to the best AI model and configuration using an LLM-powered intelligent selection system.

Manage Claude Code Routines as code. Edit .md files, ask Claude to deploy them. No CLI to install, no tokens to manage.

Glite Autonomous Research Framework - a template repo to fork for your research

Run AI coding agents in sandboxed containers communicate via ACP

A Claude Code kit that turns a PRD into shipped code — 32 AI agents, 21 skills, full implement-review-ship pipeline

Claude Code × Codex dual-agent loop for macOS. Set a goal, hit ▶, walk away — two AI coding agents build, review, and iterate until done.

Deprecated split repo; AtomicMemory Core now lives in atomicstrata/atomicmemory/packages/core.

Normalized Elixir protocol for CLI AI coding agent adapters.

Bibby is your LateX Research writing friend, Write research papers faster, do more research output.

Reviewable skill marketplace for OpenClaw agents. Browse 1,600+ skills with ratings from humans and AI agents.

grep-like memory search tool for coding agents with Git-backed sharing (Codex, Claude Code)

Moved to ultracontext/ultracontext

A Claude Code skill that helps Claude Code delegate repository work to the Codex CLI

Open-source Runtime Assurance SDK for AI agents in production

🧰 Agent Skills - Create, manage, and execute reusable code-based tool compositions for AI agents.

Tired of git worktrees?

TinyAgent brings the core ideas of the original Python library into a lean, zero-dependency TypeScript package. It turns plain functions into LLM-driven tools and lets you chain them together through a simple ReAct-style loop.

The goal is simple: build a shared vision that helps every learner see clearly, grow faster, and make smarter choices.

Debug and validate Agent Client Protocol (ACP) traffic — protocol conformance testing for AI coding agents.

Auditable CSPRNG-backed credential generator for AI agents and machine-readable pipelines. Stable JSON schema, NIST entropy floors, SLSA 3 + cosign signed releases. CLI, Go/Python/Rust libs, MCP server.

Local Privacy Firewall for AI

Unreal Master AI agent that gives Claude Code bidirectional control over Unreal Engine internals — manipulating Blueprints at the graph level, generating Slate UI code, triggering Live Coding compilation, and self-healing from compile errors without manual intervention.

Research workspace on harness engineering, coding-agent shells, and automation workflow systems.

Mesh-first real-time dashboard for Claude Code, Hermes, OpenClaw, MLX, and local memory/routing systems.

Open benchmark for AI coding agents on SWE-bench Verified. Compare resolution rates, cost, and unique wins.

Embeddable AI action firewall for MCP servers and APIs

Memory-Augmented Neural Assistant — adaptive learning system for Claude Code context injection. Rust.

Interactive Overview of how KARIMO works - Autonomous development framework for Claude Code — plan mode on steroids. Product design-driven agent orchestration with sub-agents and agent teams, tuned for developers and designers shipping real features. Phased adoption from PRD execution to automated review, code review, and CI-friendly agent teams