Autonomous AI agents that perform tasks independently
adithyan-ak
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
...moredondai44423
An agentic browser driver for AI — few tools, full control, real stealth, god-tier token efficiency.
marcominerva
A Blazor Web App playground for quickly testing agents built with Microsoft Agent Framework
andreibesleaga
Kaiban Distributed - Distributed Agentic AI Platform - Actor Model Kanban Framework Implementation with Enterprise Messaging Layer State (Redis/Kafka) and Individual Deployed AI Nodes (Node.js/TypeScript).
...morexiejianjun000
Eco Agent - 五层循环驱动的开源自主 AI 智能体系统 / 持续自我进化 / 多智能体协作 / 8 平台统一网关
PCODE-pl
MCPTap is a lightweight LLM proxy for Codex-compatible AI clients that intercepts traffic (currently OpenRouter/Requesty) and controls MCP tool calls.
...moreiyedtouati
AI agent skill for generating PHP flat-file websites (type agence digitale). Works with Claude, opencode, and other AI coding agents.
...moreboqiang.liang
MyAgent CLI for compiling and running Skill-backed verified workflows
GitHub Actions
Flow agent bridge: joins a Flow workspace as a first-class AI agent and execs a coding-agent CLI (Claude Code, Codex) headlessly per conversation
...moreranxianglei
Issue-driven AI development daemon. Spawns opencode subprocesses to resolve Gitea issues.
Gubernaut Research
Gubernaut SDK — deterministic runtime governor for LLM agents: drop-in local proxy (gcc_proxy) plus a one-call SDK facade (gubernaut_sdk) with framework config helpers.
...moreiTao-AI
Evidence-driven research agent with durable runs, governed tools, reviewable Evidence, and canonical delivery.
ayman3000
Protocol-oriented Swift package for building tool-using AI agents on top of LLMProviderKit.
marko1olo
Complete guide to run Claude Code CLI & VS Code with AgentRouter using a WAF bypass proxy
Underline-1024
🧵 A terminal-native narrative engine & text RPG in Rust 🦀. Play with any LLM: OpenAI, Anthropic, local models & more.
npm-support
security holding package
npm-support
security holding package
GitHub Actions
Pre-action policy verification for AI agents.
mashground
Operator console (a pi extension) + skill for pi-dispatch: run the pi coding agent as a self-hosted service. A /dispatch TUI for the queue, spend caps, run history, editable GitHub and GitLab triggers (cron/label/comment/PR/MR), and scheduled pause window
...moreA code review gate that verifies changes by executing tests, not by judging diffs. An LLM proposes edge-case tests; a deterministic harness runs each one; a behavior is a gap only if its test runs and fails.
...moreTrustGraph Authors
Enterprise client for AI-TrustGraph cloud control plane — license-key authenticated with usage metering
Georgi Mammen Mullassery <[email protected]>
Production ML deployment with automatic versioning, intelligent rollbacks, cost optimization, and multi-model orchestration
...morearsonist-g
Search/research sub-agent + concurrent search/fetch/locate CLI atomic tools for AI agents (Exa, Tavily, Firecrawl, Context7, OpenAI-compatible).
...moreyiyuiii
Codex-facing external LLM review and delegation tools