GitHub agents

LLM Sentinel Red Teaming Platform is an enterprise-grade framework for automated security testing of Large Language Models, detecting vulnerabilities such as jailbreaks, prompt injection, and system prompt leakage across multiple providers, with structured attack orchestration, risk scoring, and security reporting to harden models before production

This repository contains code examples of langchain

Trilith v0.1 beta — context engineering for agents (budgeted memory, 3 tiers, audit trail). Core is Python; use via REST or adapters (LangGraph / OpenAI Agents / Claude / TS). Needs trilith serve locally. No API key for Trilith itself. Not prod-hardened. Clone → pip install -e ".[server]" → try docs/adapters.md → open issues.

A Repository for Intelligent Agents Integrated with Retrieval-Augmented Generation for Querying Automotive Manuals.

Autonomous Multi-Agent Environmental Command & Spatial Attribution Engine for 277 Municipal Corporations across India. Features real-time CAAQMS IoT streams, ESA Sentinel-5P satellite plume overlays, ML forecasting models, and automated compliance dispatch notices.

A governance framework for multi-agent AI systems. Structure, lifecycle, and quality controls for AI agent orchestration.

Assemble your AI team — a multi-agent product management framework for Claude Code

Autonomous delivery skills for Claude Code — pitch an idea, get an MVP. CEO/PO/DEV/Reviewer agent team with contracts, gates, and evidence rules.

Version control for many hands moving at once — intent leases, stitches, green-by-construction fabric above git

The battle-tested Claude Code kit behind HasBrainsAI — agent skills, subagents & slash commands for production multi-agent systems. Install in one command.

The first Russian-language based course on multi-agent orchestration in Claude Code: workflow tools, pipelines, adversarial verification, and budget loops. 15 chapters + 14 labs.

Neutral control plane for coding-agent fleets: claims, roles, mailbox reliability, receipts, audit, federation, dead-letter visibility, sandbox receipts, and cross-agent coordination. This is still pre-1.0.0 - Software works however you might need help from your local agents to set it up.

ae — agentic engineering: run multiple AI coding agents side-by-side in tmux focus on simplicity

A deterministic, budget-aware control plane for Codex custom agents and Skills.

Autonomous open-source contribution agent for Claude Code & Codex. A multi-agent harness that picks an issue, writes the fix, scores its own pull request on a 10-dimension merge-probability rubric, and iterates until a maintainer would merge it — a closed-loop, self-improving AI coding agent.

Auditable local control plane connecting ChatGPT Apps and GPT Actions to authorized workspaces

Automatic risk-based task routing and multi-agent orchestration for Codex using Sol, Terra, and Luna.

🤖 Enhance coding with Claude and Codex, a library for duo peer programming that combines AI strengths for superior code generation and reviews.

Your AI on rails, on your terms — an open-source Claude Code plugin that enforces every process as it happens, so your AI can't fake the work. Free, on the subscriptions you already pay for.

A macOS IDE for tmux-based multi-agent work with the smux skill.

多智能体群聊工作台：本地圆桌 Agent 用于方案讨论，战略分析、风险复盘。自定义名人角色进行群聊争论出最佳方案

Competition-oriented brain + multi-worker penetration runtime built with LangGraph and OpenCode

AI-powered Board of Directors for multi-perspective strategic decisions. 10 director archetypes (Musk, Altman, Hassabis, Li, Nadella, Huang, Pichai, Hoffman, Ng, Jobs) + 7 shared methodology skills.

Cybersecurity command center with AI-powered threat detection and response | 🤝 Looking for contributors!

Kubernetes operator for deploying and managing AI agents

Multi-agent orchestration for coding CLIs — dispatch tasks to Claude Code, Codex, Kimi, OpenCode, or Gemini workers and block until they actually report back.

Open-source desktop control center for running many Claude Code sessions in one tiling workspace — across all your machines, with live status, diffs & usage stats, and AI that can operate AI.

A股热门板块多智能体量化分析系统 | 基于FinGenius架构 | ETF50+60只个股扫描 | AkShare数据源免费

323個の即戦力AI専門エージェント — Claude Code/Cursor/Copilot等に対応。SIer/受託開発/SaaS/製造DX/公共分野など日本市場向け114個のオリジナルを含む、agency-agents日本語コミュニティ版

AIgazing. Like stargazing, but for local LLMs.

Agent-native RPC for the multi-agent era — write a Java interface, get gRPC + HTTP/MCP gateway and generated TS/Dart/Python/Rust clients, no protobuf. 智能体时代的契约先行 RPC：接口即 API，天然带 MCP 网关

Evidence-based adaptive scaling and governance for homogeneous Codex agents.

Multi-agent RL solution for scheduling work within a graph-based digital twin of a residential complex

AI founder co-pilot that validates startup ideas through a 7-stage journey — autonomous competitor watchers, signal-to-knowledge graph, approve-first agent actions, real-time market research. OpenClaw-inspired multi-agent architecture on Next.js + PostgreSQL + Claude.

From raw idea to shipped MVP with a team of specialist AI agents inside Claude Code. Zero install, just Markdown.

Production-ready skills for Claude Code and multi-agent systems

Multi-agent HVAC operations co-pilot (dispatch, inventory, AR, risk). Phase 1 Streamlit demo with synthetic fallback + optional Mongo. Human-in-the-loop.

SAGE (Session Awareness & Guidance Engine) - a passive, read-only judge for fleets of parallel AI coding sessions. It watches and answers; it never edits, spawns, or blocks.

Autonomous coin launcher for Robinhood Chain — concept → 3D logo → deploy on NOXA or Uniswap v3 → announce. CLI, HTTP API, and an autonomous agent.

A coding agent for your terminal that runs fully offline on your own machine via Ollama — or on hosted frontier models when you want them. Open-source, one account with Aether AI.

Sovereign AI Initiative for Open Autonomous Cognitive Companion

The React framework for building agents into real apps — one definition serves humans (streamed HTML, zero client JS) and agents (markdown, JSON, MCP), nothing duplicated. Web-standards core, deploys to Cloudflare Workers.

Jupyter notebooks, made agent-ready. 8+ formats · MCP server · async execution · token budgeting.

Demonstrate best practices for coding with Claude through clear examples and organized workflows to improve skill and efficiency.

Scoop Skills: A specialized skill for the AI Agent agent to manage Windows packages using the Scoop command-line installer

app for coding agents

🤖 AI Voice Assistant with Memory, Wake Word & Smart Device Control

Autonomous content-publishing pipeline that learns from its own audience and rewrites its own prompts (agentic, self-improving)

Self-hosted runtime for AI coding agents. Real Linux containers, your hardware, your keys, your data.

Own Your Diff is a local human review gate for AI-assisted code changes. It generates grounded multiple choice questions before agents can push or open pull requests.

A full Google Cloud delivery team for your coding agent — vendor-objective solution designer, GCP + agentic architects, security, SRE, and QA — wired into a design-first, security-first delivery gate. Installable on Claude Code, Antigravity, Codex, and Kimi.

Fail-closed authorization gateway for agentic RAG — capability-label pushdown, deny-aware barriers, per-turn agent-context revalidation.

DataClawEval: A Benchmark for Engineering Data Agents in Real Industrial Harness

Codex-native operating layer for repeatable AI workflows with AGENTS autoload, project-isolated memory, plugin skills, and a thin ro CLI for terminal + VS Code chat.

The open standard for AI agent integrity. Evaluate, enforce, and prove that autonomous agents are adversarially coherent, environmentally portable, and verifiably assured.

Free, local-first, chapter-wise curriculum for LLMs, Vector DBs, RAG & Agents — from zero to your first AI agent.

Stacking Agent Development Environment (ADE) for the busy dev

Production-grade Agentic AI platform on Kubernetes — KEDA autoscaling, Kyverno governance, token budgets, OTel observability. Demo for CNCF Meetup talk "Agentic AI Without Chaos"

A tiny raccoon skill that rescues todos, ideas, plans and drafts from your AI chats into local markdown.

A science inference cluster — every model, from protein folding to LLMs, behind one OpenAI/Anthropic-compatible endpoint and a single key. Built to run beside HPC so agentic AI researchers can drive simulations and model inference together. Self-deploying on RKE2 with KServe/Knative + HAMi GPU.

Eticas AI Risk Taxonomy: Open, machine-readable AI risk taxonomy mapped to the EU AI Act, NIST AI RMF, ISO/IEC 42001, and 15+ other frameworks.

OpenTelemetry + Wireshark + Cloudflare for AI Agents. Monitor, inspect, secure, replay, and optimize all traffic between Users, AI Agents, LLMs, and MCP Servers.

A private, offline AI assistant running entirely on your local machine.

Render agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.

FastMCP 3.2 server plus Webapp for Yahboom Raspbot v2 robot car, ros2, raspberry pi

Security boundary CLI proxy between AI coding agents and your shell — redacts secrets, neutralizes prompt injection, wraps untrusted terminal output, and audits every command. Single Rust binary.

Shared, versioned memory for AI coding agents — MCP server with git-style history (log/diff/blame) for Claude Code, Cursor & Claude Desktop

AI가 발전하는 시대 흐름에 맞춰 국산(주통기) 체크리스트 기반 모의해킹 자동화 Agent를 만들어보려고 합니다.

Igris Guardian — a capability-bounded prompt-injection firewall (verdict-only, self-protecting, universally deployable)

Companion code project for the ebook Vector Database Engineering for AI — Building High-Performance Retrieval Systems for LLMs, RAG, and Agentic AI.

Drop-in Claude Code skill bundle for AI-resistant SEO article generation — research → write → E-E-A-T audit, configurable for any site or language.

Browse open-source tools for automating scientific research, from literature review and experiments to writing and peer review

AI-native QA patterns for governed automation, RCA triage, agentic workflows, and deterministic Quality Gates.

A portfolio site, showcasing my blogs, repos, sites and applications. Built with Python backend and React/Vite frontend. Includes chatbot built using Gemini and Google ADK. Uses Gemini AI for content summarisation and metadata extract. Hosted on Google Cloud Run and Google Firestore.

Starter Kit for AI Native Applications - Vite Plus (Vite+) TanStack Start monorepo with Paraglide.js (i18n), drizzle-orm, better-auth, Feature-Sliced Design (FSD)

AgentVoir is an open-source enterprise AI agent registry, LLM gateway, model proxy, semantic cache, and governance control plane for agentic AI systems.

Post to Tiktok, Instagram, Facebook, Linkedin using API

Deterministic governance for Claude and MCP tool calls. Pin approved capabilities, detect drift, and refuse unsafe or unapproved actions before execution. No model in the decision path.

A self-installing working memory system for Claude Cowork. Builds on Andrej Karpathy's LLM Wiki pattern. Markdown-based, no vector DBs, self-improving.

Local viewer for VS Code GitHub Copilot Chat sessions. Reads transcript & debug JSONL files locally and shows session metadata, turns, models, tools, agents, token usage and estimated AI costs. No data leaves your machine.

Agentic Component Manifest (ACM) — universal, schema-first manifest format describing UI components from any framework for AI agents and tooling. Canonical JSON interchange, token-frugal Agent View, executable conformance suite.

Google Antigravity workshop using the TripLens demo app

Because your AI shouldn't lose its memory every time you switch models.

10 copy-paste superprompts + 100 agent-ready goals for ChatGPT connectors (Gmail, Drive, Calendar), Claude Code, Codex, and MCP agents. Authored with Claude Fable 5, executed by GPT-5.5 xhigh or cheaper models. Includes LOOPS.md-inspired agent-loop templates.

Agentic RAG system with LangGraph, hybrid BM25+FAISS retrieval, cross-encoder reranking, Corrective RAG, FastAPI, RAGAs evaluation, and Docker deployment

Case study resources from PepsiCo's agentic AI modernization — data foundations with Azure SQL, Cosmos DB, PostgreSQL, and Databricks for agentic RAG architecture. From Microsoft Build 2026.

Agentic synthetic-data generation framework inspired by Meta FAIR's Autodata / Agentic Self-Instruct.

An efficient open Mixture-of-Experts (MoE) agent that runs on a single 24 GB GPU. Agent-first design: coding, terminal, computer-use, tool-use. v0.1.0 documentation preview — weights/code follow staged open release.

🧠 Build a cutting-edge AI agent with Project Synapse that enables strategic thought and multi-turn collaborative dialogue for innovation and discovery.

Full-stack apps built by a local LLM coding agent (ollama-local-coding-agent · glm-4.7-flash · Ollama). No cloud, no API keys.

remembr.ai is an AI-powered memory aid platform designed to support individuals living with dementia. It helps patients recall personal memories, recognize familiar faces, and manage daily routines through the use of Agentic Artificial Intelligence and adaptive memory interaction.

Offline Agentic AI Compliance Platform for RBI, SEBI & IRDAI Regulatory Analysis using Ollama + Qwen2.5:3B

an automated benchmark farm for agent memory frameworks.

Uses beads, souffle, z3 and mcps to give first-order logic powers to your thinking agents

Phased planning and execution for Claude Code. Roadmap, plans, and progress live in files that survive a /clear.

A guard-railed, closed-loop workflow for AI coding agents: live state bus + execution-level hard intercepts for Claude Code and Codex (GitHub PR / GitLab MR). From step-level to requirement-level; eval-driven, spec-driven, human-in-the-loop.

One objective in, a verified result out. An agent skill that runs a full, gated dev process with expert subagents and refuses to declare done until a machine-checkable gate passes. Bilingual (EN/한국어) onboarding & live walkthrough

Research on why autonomous AI agents don't know when to stop, and three engineered fixes.

Detect and redact sensitive data in LLM requests — before they leave your machine.