Custom agents

AI-powered financial news summarizer for traders and investors. Aggregates news from Polygon, Finviz, and TradingView, then generates smart daily summaries using Google Gemini. Built with Flask, fully free to run.

Lightweight inter-agent trust, coordinatination and shared state server for AI agent swarms

Single, consistent interface to run code, manage files, and control isolated environments across sandbox providers

POPUP STUDIO의 AI Agent를 활용한 업무 프로세스 개선 프로젝트입니다.

A structural X-ray for the codebases AI agents are writing.

Track what your AI agents cost including files, commits, tokens, budgets. CLI , Dashboard+ API. Works with OpenClaw, Claude Code, and any agent framework.

The predictable, observable agent harness.

Runs AI coding agents inside isolated Docker containers

AgentTrace is an open-source, local-first step debugger for AI agents. It provides a Python SDK for tracing your agent runs and a web UI to inspect spans, tool calls, prompts, and responses as an interactive tree.

Local-first, AI-native LinkedIn messenger CLI. Sync your inbox to plain JSONL files in a git repo, pipe to agents, send from the command line.

A set of tools to use while coding using the Claude code cli. "smartgrep" is a grep-like tool that uses a semantic index of the codebase to provide Claudes with information tailored for how they think. Claudes love it! A "codebase-curator" Claude to assist the "developer" Claude in his coding tasks, together they implement fully integrated code.

pytest plugin for deterministic testing of AI agents. Assert agent actions, not vibes.

A growing collection of Claude Code skills, distilled from real engineering work.

The Requesty integration package for the Vercel AI SDK.

Skill that teaches AI agents how to build Agent Skills for Claude Code, Codex, Amp, and OpenCode. Production patterns from gno, sheets-cli, raindrop, outlookctl, and flow.

API documentation for Xquik - all-in-one X automation with 120 REST API operations, 2 MCP tools, 23 extraction types, HMAC webhooks, and SDK guides.

AI-powered LinkedIn job application automation tool using Selenium, featuring session persistence, clean browser profile handling, and stability-focused debugging for reliable job applying workflows.

Automated TikTok-style video review of every PR.

Orchestrate parallel AI coding into reviewable PRs.

Detect AI agent runtimes so CLIs can choose agent-friendly output

AI Technical Interviewer with Google ADK, Gemini and A2UI. Multi-agent system for adaptive interviews, guided learning, and code analysis with beautiful web UI.

Portable MCP plugin marketplace for Claude Code, Codex, Gemini, OpenCode, and Cursor.

Open sourced repo so anyone can build AI agent powered financial analysis platform

AI-powered deep research agent running locally via Ollama. Multi-agent pipeline with persistent memory, RAG, and GraalVM native image support.

A python library built to execute tasks with natural language

From breakpoints to test cases — AI-powered test generation straight from your debugger.

The work visa for AI agents. A high-performance Rust sidecar that deterministicly blocks unauthorized actions before execution.

Tool Confirmation Lock with Bayesian Regret

A forensic analysis of how local AI IDEs and wrappers secretly inject 'CHECKPOINT' mechanisms and override prompts to lobotomize your LLMs (Claude/Gemini) for token-saving. It's not the model degrading; it's the infrastructure hijacking your context.

A persistent Rails server for AI agents (no MCP needed). Avoids boot overhead for repeated queries via fast command-line access.

ClaudeClaw multi-agent Telegram starter kit: 5 specialist agents around Claude Code for self-hosted operator workflows.

This Project is for HackSecure Hackathon. This is a n8n based Data Leak Prevention AI Agent Project. This scans files from Discord, Slack, GitHub and Drive and checks for Data Leaks.

SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios

A team of Claude Code sub-agents that enforce security across the full SDLC, from ASVS requirements and threat modelling to SAST triage, IaC review, compliance attestation and release sign-off. Drop into any project. No security team required.

The terminal workspace for AI coding agents. Run dozens of Claude Code sessions on a 2D canvas. macOS.

This project use the power of LLM Agents to Refactor Legacy code.

Timestamped web intelligence for AI agents. MCP server with guaranteed freshness envelopes.

The coordination protocol for autonomous AI agents across networks. Summoner lets you compose, run, and coordinate agents over a WAN with a Python SDK and Rust server.

A Python and Temporal based implementation of OpenClaw.

Managed MCP server for Bybit perpetual futures trading

[DEPRECATED] Moved to microsoft/agent-governance-toolkit

A high-performance microservice for source code analysis, generating Abstract Syntax Trees (ASTs) and relationship maps from codebases.

The trust layer for agent-to-agent commerce — cryptographic identity, enforced transaction rules, verifiable reputation. Connect via MCP.

🐚 Hi Shell: An intelligent terminal assistant that translates your natural language descriptions into executable bash commands.

Here we will keep track of the latest AI Engineer Development Tools! 🔥

A dashboard that lets you query the Gapminder dataset using natural language. Powered by Gemini 2.5 Flash.

🦀 Complete OpenClaw documentation as a skill for AI Coding Agents. 333 pages of verbatim official docs. Works with Claude Code, Cursor, Codex, and OpenCode.

AI skills and workflow templates for Claude Code, Copilot, Gemini, any AI tool that will ingest skills files.

A hyper-optimized MCP server that supercharges AI coding agents. Outperforms built-in IDE tools with AST-based precision editing and native OS control, drastically reducing LLM token consumption.

A session trace format for capturing human-AI coding interactions across frameworks.

TUI for managing a fleet of opencode agents in git worktrees

An AI Project Manager that Creates and Manages Linear Projects

Right-hand Agent for your majesty;

Run Claude Code, Codex, and Gemini CLI from Telegram, WhatsApp, or Slack - single Rust binary, no server required.

A Claude Code skill (standard Skill format) for generating AI images via the Evolink Z-Image-Turbo API. Cross-platform, zero dependencies.

Soul Protocol: An open standard for portable AI identity, memory, and emotion. Like HTTP, but for AI companions.

Open-source, self-hostable runtime for managed AI agents. Apache-2.0.

로컬 LLM을 이용한 로컬 AI 커뮤니티 웹보드 서버입니다.

Apple-native execution layer for AI coding agents: compile, validate, repair, and prove Swift surfaces.

Business-Native AI Agent Collaboration Platform.

A text editor designed for AI agents.

Two lines of code to give your LLM eyes. One attribute.

RepoBird CLI is a powerful command-line interface and terminal UI for RepoBird.ai - the One-shot agentic coding platform

Persistent memory for AI agents. Single Rust CLI, hybrid Gemini + FTS5 + RRF retrieval. R@5 = 0.99 on LongMemEval S (beats MemPalace). Agent-native: no MCP, no server, just shell out.

Open-source MCP Server for web search, content extraction, library docs & multimodal analysis.

ITQA (Intelligent Traffic Question-Answering) 是一款专为交通法规咨询与智能出行规划打造的Agentic_RAG 平台。

Deep learning models implemented as web services for integration in Rhino Grasshopper

The AI collaboration framework that prevents echo chambers - Real-time multi-agent coordination with enforced diversity and anti-groupthink protection

The open, vendor-neutral protocol for governing the lifecycle of AI agent systems. Standardizes planning, coordination, execution, confirmation, and traceability across multi-agent runtimes and tools — enabling interoperable, observable, production-grade agent systems.

This repository demonstrates how to build a Decoder-Only Transformer with Multi-Query Attention in JAX.

Robotics demos: ROS, SLAM, robust control, mobile robotics.

ProductionOS v1.0 — Claude Code plugin with 76 agents, 39 commands, and 12 hooks. Deploys specialized agents that review, score, and improve your entire codebase. Smart routing, recursive convergence, self-evaluation.

This module implements a post-training mechanism that allows a language model to explore various reasoning branches (chain-of-thoughts) using a Monte Carlo Tree Search (MCTS) framework. It selects the branch with the best answer using a cosine similarity evaluator that compares the candidate answer to a known correct answer.

Repository containing the code and explanation of a solution to the Flatland Challenge problem.

Atlaso — desktop app + Python SDK for confidence-flagging AI agent memory. Apache-2.0.

Fabricatio is a Python library designed for building applications that leverage Large Language Models (LLMs) using an event-based agent structure. It utilizes Handlebars for templating and provides a robust framework for managing tasks, workflows, and toolboxes, enabling developers to create intelligent and efficient applications.

Autonomous trading research factory and flagship reference app for Meerkat + Goldfish

Local-first AI agent gateway — multi-agent, multi-channel, multi-provider. Open-source OpenClaw alternative.

A template repo for development with the AEA framework

"Open-source toolkit (Python Library, Registry API, CLI) for secure, decentralized AI agent interoperability using A2A/MCP."

A Model Context Protocol (MCP) server for Discord-based AI agent-user communication. Enables AI agents to communicate with users through Discord instead of IDE chat interfaces.

Lets Threat Model is an AI-driven tool that helps teams identify and manage threats early in the development lifecycle. Built with extensibility and automation in mind, it brings security into agile workflows by generating actionable threat models.

CoAgent - Control software to log, test, and monitor generative ai applications and agents.

AniBaba is an AI-powered anime recommendation system that provides personalized suggestions based on natural language queries. Leveraging Retrieval-Augmented Generation (RAG), it understands user preferences and retrieves relevant anime from a semantic knowledge base to offer a conversational and discovery-rich experience.

Teach your LLM to dynamically call your services in Kubernetes

VeoCrafter is an automated video generation pipeline that transforms simple text ideas into engaging short-form videos using Google's VEO-3 AI model.

A unified interface for discovering and accessing skill configuration paths for various AI coding agents.

A platform for AI builders to list, sell, and promote AI agents, while businesses can discover, purchase, and integrate these solutions—or hire builders for custom AI development

Context Engineering - The art of providing all the context for the task to be plausibly solvable by the LLM.

The Notion ReAct Planner Agent is an AI daily planning system using the ReAct (Reason + Act) architecture, integrated with Notion. It understands intent, breaks natural language into steps, and executes actions via Notion APIs and external tools to manage tasks, notes, and schedules.

Local-first AI extension that turns what you read into a searchable knowledge graph with hybrid search, temporal context, and proactive recall—fully private.

An autonomous research and synthesis agent powered by Google Gemini. Features intelligent deep research, query decomposition, and safe local system control via a native Python loop

🧠AI-powered CLI tool for automatic git commit message generation

Agentic Retrieval Augmented Generation App that uses CodeAgents

A multi-agent system specialized for healthcare-related domain

Code repository for examples of implementing quick machine learning solutions to real-world problems

Agentic TRACE is the implementation of the framework described in: https://appliedingenuity.substack.com/p/the-verifiable-orchestrator-a-new

A real-world library of 40+ browser automation prompts for Perplexity Comet. Instantly automate coding, productivity, job search, and more just copy, paste, and run!

This project guides you through end-to-end AI agent development using Google's Agent Development Kit (ADK). You'll learn to build agents, expose them via REST APIs, create a Streamlit frontend, and deploy them to Google Cloud Run, resulting in a fully functional and production-ready AI agent application.