Open-source AI agents

paradigmxyz

evmbench

★ 470

Collab with OpenAI. A benchmark and harness for finding and exploiting smart contract bugs

xuzhougeng

wispterm

★ 470

A cross-platform terminal workspace for remote development and AI agent workflows, powered by libghostty-vt

aiming-lab

AutoHarness

★ 469

AutoHarness: Automated Harness Engineering for AI Agents

S1N6H

pentest-harness

★ 469

Pentest Harness — Heaven for Hackers. A self-hosted AI agent harness for authorized pentests, bug bounty, security labs, and CTFs. Bring your own AI model API; sessions stay local.

xpert-ai

xpert

★ 469

XpertAI is an open-source platform for building, running, and evolving ai agents, providing extensible capabilities and infrastructure for diverse AI systems.

0ca

BoxPwnr

★ 468

A modular framework for benchmarking LLMs and agentic strategies on security challenges across HackTheBox, TryHackMe, PortSwigger Labs, Cybench, picoCTF and more.

FloWritesCode

fwc-swiftui-skills

★ 468

Coding Agent Skills for modern SwiftUI development

inkboard

system-atlas

★ 468

An agent skill that turns an architecture discussion into an explorable isometric atlas: one data file, an interactive map and a generated SYSTEM.md

NevaMind-AI

memUBot

★ 468

The Enterprise-Ready OpenClaw. Your Proactive AI Assistant That Remembers Everything

RickyTong1

audit-harness

★ 468

Three-layer audit enforcement framework for AI agents — hooks, skills, context recovery, and audit-driven daily reports

coderzc

open-xiaoai-bridge

★ 467

A bridge between the Xiaomi Xiao AI speaker and external AI services such as OpenClaw and XiaoZhi AI.

PleasePrompto

ductor

★ 467

Control Claude Code, Codex CLI and Gemini CLI from Telegram. Live streaming, persistent memory, cron jobs, webhooks, Docker sandboxing.

dlants

magenta.nvim

★ 466

A tool-use-focused LLM plugin for neovim.

pacifio

cersei

★ 466

The Rust SDK for building coding agents. Tools, streaming, graph, sub-agent orchestration, MCP — as composable functions

understudy-ai

understudy

★ 466

An understudy watches. Then performs.

alexisfox7

PRO-LONG

★ 465

Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)

CuriousLearnerDev

CipherBridge

★ 465

A visual decryption framework for reverse engineering and penetration testing of app and web encryption.

Dicklesworthstone

cass_memory_system

★ 465

Procedural memory for AI coding agents: transforms scattered session history into persistent, cross-agent memory so every agent learns from every other

iamzulx

crypto-rag

★ 465

Asisten crypto berbahasa Indonesia: RAG pengetahuan 267 topik + data pasar realtime (6 bursa, WebSocket, derivatif, on-chain, TVL, DeFi) + tool-calling agent + LLM synthesis

run-llama

llama-agents

★ 465

Llama Agents + Workflows are an event-driven, async-first, step-based way to control the execution flow of AI applications like agents.

alchaincyf

huashu-excel

★ 464

A data-analysis and Excel workflow skill: audit messy spreadsheets, clean data, align requirements, analyze, reconcile, and deliver, so AI-computed numbers hold up under scrutiny. Works across agents and depends only on openpyxl.

ApodexAI

AgentHarness

★ 464

Evaluation harness for Apodex-1.0 on public deep-research benchmarks.

Dicklesworthstone

ntm

★ 464

Named Tmux Manager: spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Gemini) across tmux panes with a TUI command palette

Gabson0x

bountyforge

★ 464

All-round bug bounty skill for Claude Code parallelized agents for smart contract audits (EVM, Move, Solana, TRON), web/API security, and submission-ready reports for HackerOne, Bugcrowd, Intigriti & Immunefi.