Open-Source AI Agents DirectoryOpen-Source AI Agents Directory

AdaExplore

[COLM-LLA 2026] The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation"

EpochGo

Autonomous, local-first multi-agent AutoML platform. Zero cloud costs, zero API keys, 100% private. Benchmarks 7 algorithms, tunes hyperparameters, and serves live in-browser predictions.

Browseruse Agent Bench

Real-world browser-agent benchmark: 210 tasks across 107 websites, multi-agent/multi-browser evaluation, reproducible leaderboard and result submissions.

Vion Protocol

Constitutional governance runtime for autonomous AI agents

ComProScanner

A python package for extracting composition-property data from scientific articles for building databases

Datarobot Agent Templates

DataRobot Agentic Workflow Templates

Shekel

LLM budget control and cost governance for AI agents. Python library for token budgets, usage limits and guardrails for OpenAI, Anthropic, LangChain, LangGraph and agentic systems.

Pixelpi

A minimal browser-agent harness - six tools, any model. pi for the browser.

Mycelium

🍄 The open-source internet for AI agents. pip install → discover → communicate → collaborate.

Browser Agent

Replayable Browser Agent

AgentHound

BloodHound-style risk analysis for multi-agent AI architectures. Parses CrewAI, Dify, LangGraph, or generic YAML into a typed capability graph and detects reachable attack paths from untrusted input to sensitive data or external action, with live control simulation.

AI Garage

Mini-Projects using Cutting-Edge AI Frameworks

Typed Evals

Fast, typed Python framework for Jev-as-a-Judge/Decision-model evaluation for LLMs, RAG, and AI agents along with human-label calibration.

GenAI GCP HF OpenAI Databricks

GenAI - Building AI Workflows | Agentic Appls | Working with LLMs | HuggingFace | OpenAI | Gemini

Crewai Go

Orchestration of autonomous, collaborative AI agents in Go — an idiomatic Go port of CrewAI.

Kakunin Samples

Runnable examples for AI agent identity & compliance — certificate issuance, scope enforcement, and integrations for LangChain, CrewAI, Next.js & more.

Summoner Core

Summoner's core SDK for building and deploying agents

Toolguard

The "Cloudflare for AI Agents". 7-layer security interceptor, real-time observability dashboard, and automated reliability testing for MCP and AI tool chains. Prevent hallucinations, prompt injection, and destructive tool calls.

Supervaizer

SUPERVAIZER is a toolkit built for the age of AI interoperability. At its core, it implements Google's Agent-to-Agent (A2A) protocol, enabling seamless discovery and interaction between agents across different systems and platforms.

Structsense

A multi-agent system for extracting structured information from unstructured text and documents. It orchestrates a configurable pipeline of AI agents — extractor → alignment → judge → human feedback — each driven by a single YAML config file.

Youtube Video Analyzer

YouTube Video Inspector is a multi-agent tool that analyzes YouTube videos by fetching metadata, analyzing comments, and generating performance reports, which can be exported as PDFs using CrewAI.

Paragent

Stateful execution layer for browser agents.

Multi Agent System Architecture For Federal Funds Target Rate Prediction

End-to-End Python implementation of "FedSight AI" multi-agent system for Federal Funds Target Rate prediction (NeurIPS 2025 Workshop). Simulates FOMC deliberations using LLMs with Chain-of-Draft reasoning and In-Context Learning. Integrates structured macro indicators with unstructured narratives (Beige Book, Dot Plots).

Dejevu

Jev? Déjà vu. Browser agents that run on instinct, no Jev needed. One look at the page, one call to any open model, one action. Faster than the Jev demo on Google Flights.