GitHub agents

OpenBrowser is free local AI coding agent — use your ChatGPT, Claude, or Gemini browser subscription. No API keys. CLI + Chrome extension bridge.

从零构建的 LLM Agent Harness 实践项目——Agent Loop、Tool Use、Context Engineering、Memory

Skill для Hermes / Claude Code / Codex-агентов: автоматический выбор и настройка LLM inference engine под железо, модель и workload — MLX, llama.cpp, ExLlama, vLLM, SGLang, TensorRT-LLM.

Stop trusting 'done'. Make AI coding agents prove their work — frozen specs, tamper-detected tests, an independent blind verifier, hard-blocking gates. Fails loudly instead of pretending. For Claude Code, Codex, OpenCode & any Agent Skills runtime. No unverified work passes.

Enterprise AI OS reference architecture — the moat is memory and governance, not the model. One architecture, three scales (personal / startup / enterprise), derived bottom-up from a working n=1 system.

Local-first AI interactive fiction app — a self-hosted narrative engine with an async multi-agent brain that keeps story state in plain files.

Open source, self-hosted, multi-agent fraud detection. Real-time XGBoost decisions, drift-aware retraining, plain-language LLM investigations.

Reverse-engineer the RL reward an LLM was trained on — from black-box agentic coding behavior alone. Tested on Opus 4.8, Fable 5, GPT-5.5.

Agent-ready knowledge architecture, run daily in Claude Code: turn a coding agent into a system you can hand work to and trust while you're away. Roles library, typed memory, hooks, scheduled agents, delegation queue, self-audits, token budgeting, measurement-gated self-improvement. Interactive tour, fork-ready samples.

Human controlled project context

Teach an LLM to talk like a person — It teaches a language model how to talk like a person. Not how to sound like one — that part's easy, and it's what most failures already do

The prettiest statusline for Claude Code — pure bash, never blocks your prompt. Usage quota, context window, git status & more.

Turn your Claude Code subscription into a REST API. Access Claude Code from anywhere with a single command.

Minimal, type-led HTML/CSS/React design system for slide decks and data-driven presentations. 极简演示文稿设计系统，含7种幻灯片模板与React组件。

A team of specialized AI agents covering the complete software development flow — from requirements discovery to deploy. One responsibility per agent, specs as source of truth, no shortcuts.

File-first, human-gated delivery bus for solo builders orchestrating multiple AI coding sessions.

oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.

A minimal AI agent that gives an LLM a handful of tools, then gets out of the way.

Open-source agent OS for Claude Code that puts you in Builder Mode — and keeps you there for the whole life of a product. Claude Code setup that builds, launches, and learns. Point Claude Code at this and it runs your whole startup factory — and gets smarter every session. Works with Cursor, Codex & Windsurf too.

Agentic Content Creator to increase views & followers across different social media: Youtube, Tiktok, Instagram

Self-contained agentic development harness for Claude Code — one command runs the full feature pipeline (plan → execute → double review) with security gates baked in.

AgentScope.Go 是一个全面自进化的工业级 Agent 框架!

Wisp - A hotkey-driven AI overlay for your desktop. Press a key, pick an intent, and Wisp reads the right context, then streams an answer without making you leave what you're doing. Local-first, voice in/out, bring your own model provider.

Gemini in Chrome 一键启用与修复工具｜Cross-platform toolkit to enable/fix Gemini AI in Chrome on Windows/macOS/Linux. Fixes Gemini button missing, --disable-actor-safety-checks warning, Roxy fingerprint browser pollution, Chrome Sync contamination.

Desktop R&D AI-agent

Learn Nanobot with a beginner-friendly guide to AI Agent basics, interview prep, and core concepts for job seekers

🏢 Watch your AI coding agents live their office life — Claude Code, Codex & Gemini show up as tiny pixel coworkers who type, take coffee breaks, get blocked, and ship. Real-time, cozy, runs right in your browser 👀✨

AI job-search agent in Telegram — scrapes 25+ job boards, scores every posting against your CV with Claude, pushes real matches to your chat. Self-host free or use the hosted bot.

Giving AI coding agents LSP-powered code intelligence.

ldm_AstrBot — AstrBot 二次修改/优化发行版（AGPL-3.0）

A cache doctor for Claude Code: find the money your prompt cache is leaking.

Streamlit chat client for Gemini - multi-session SQLite history, PDF and image input, runtime model fallback

Slides do curso de Agentes de Inteligência Artificial

// your AI took the IQ pill, personal AI OS, €0/message, self-hosted

a tool that reduces token usage and request waste in coding-agent workflows by selecting, compressing, caching, and budgeting repository context

Verification-native coding agent harness in Rust: isolated edits, evidence receipts, durable traces, and model portability.

A tool-first AI agent harness for durable repository work across terminal, browser, ACP, LSP, and CI.

An AI agent that grows your LinkedIn authority by drafting expertise-signaling comments. Built in public, one layer at a time — #PromptToArchitecture.

织镜是一个面向服饰电商场景的AI Agent产品，输入自然语言描述，Agent自动完成意图识别、DAG任务拆解、多源搜索、LLM分析、报告生成、质量审查的全流程

A Full-Stack Open-Source Academic Research Assistant Platform Powered by Agentic AI and Deeply-Engineered Multi-Paradigm RAG.

8 production-tested database ops skills + a reference MCP server for OpenOcta. Turn a 20-min DBA diagnosis into an 8-second AI analysis.

An autonomous AI agent built in typescript that combines social media management with blockchain capabilities. Features Claude AI integration for intelligent interactions, Solana token creation/management, and automated Twitter engagement. Perfect for DeFi projects looking to automate community management and token operations.

A cache-optimized AI memory and context management framework for long-running LLM agents, featuring tiered context storage, token budgeting, memory compaction, sub-agent delegation, and structured web intelligence.

Tested Azure cloud and Microsoft AI engineering scenarios: deployable architectures, runnable demos, benchmarks, and evidence-backed investigations.

The provenance-first personal graph engine behind Wend. A typed graph of people, organizations and events where every fact carries a source, every AI write is a human-confirmed proposal, and any MCP-capable agent can plug in.

The proxy your local agent calls out through. Local freedom, policy-gated egress, one-keystroke approval. — https://trollbridge.dev

Route bulk implementation to cheap executor LLMs (opencode/antigravity/cursor) with Claude as architect + judge - committed failing tests are the merge gate

Agentic Ai, multi vendor ecommerce store, featuring a hybrid RAG architecture, agentic tool calling, and Google Gemini Vision for zero input product uploads. Built with FastAPI and Next.js.

Modern crypto market data platform built with Hono.js and Next.js. Provides real-time price, volume, and volatility data through an intuitive UI and RESTful API endpoints optimized for blockchain integration.

One session picker for Codex CLI, Claude Code and OpenCode.

AI-powered crypto trading MCP server with technical analysis, sentiment, and execution tools

Highly opinionated AI software company you drop into any repo.

Autonomous session orchestrator for Claude Code — run sessions back-to-back with creative/refine improvement modes

Collaborative development environment and project repository for the Coddiom agency. Featuring AI-driven workflows, product scaling experiments, and automated content generation pipelines.

One .stdai/ source of truth, fanned out to 22 AI coding tools: Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf/Devin, Amp, Warp and more. Native formats, Agent Skills, MCP, context budgets, drift detection.

Smarter AI Development Workflows

Give your agent an Office engine — an AI-native CLI + MCP server that creates, edits, renders & validates real .docx / .xlsx / .pptx. One self-contained C#/.NET binary, no Microsoft Office.

Pipeline SDLC agentique déterministe (DISCOVER→DELIVER) : agents spécialisés, reviewers adversariaux, skills Outside-In TDD/Clean Architecture et garde-fous hooks portés sur Claude Code, Copilot & Cursor.

An AI-automated tool designed to help Threat Intelligence (CTI) Analysts process the overwhelming volume of daily cybersecurity news and vendor reports.

Compiler truth in, AI context out. Open semantic glue between language intelligence and AI tools.

Give your AI coding agent a voice. Speak to it, hear it back, fully on-device.

Bring your Diagrams to Life

AI powered whiteboards for AI-native companies

An unofficial, third-party desktop client for the Venice API. Not endorsed by, sponsored by, or affiliated with Venice.ai, Inc.

Skill library for Space Engineers plugin, mod and in-game script development. Usable with any "skills" compatible agentic coding harness.

A decentralized agent team with Discord as the interface.

Trust and verification for the skills your AI agent installs.

cubest

Agent-first CLI that runs Codex, Claude Code, and Grok as detached coding workers, while a stronger model keeps orchestration, steering, and review.

Persistent memory + security layer for Claude Code (MCP plugin). Agents remember your project across sessions (~87% fewer context tokens), every tool call lands in a tamper-evident HMAC audit chain, and skills are AST-scanned + HMAC-verified before they run. 100% local: PostgreSQL + Ollama, no cloud, MIT.

Fixes Codex registration failures by restoring OpenAI OAuth, workspace, and token flow in codex-manager-based tooling

The coordination layer for autonomous AI agents

One coding session. Two AI agents. Zero lost context. Run Claude Code and Codex CLI as a single paired session.

Local code navigation for coding agents: deterministic symbol graph, semantic search, compact briefings, and byte-exact real-grep passthrough. One native Rust binary.

Modular multi-model generator of controllable AI news stimuli for misinformation research - agent-based simulation seeding, red-teaming & human-perception studies. GPT-4/LLaMA/Mistral/DeepSeek, multilingual, full provenance. Stimuli are evaluated by human raters in JudgeGPT.

An LLM Multi-agent Environment in Romance of the Three Kingdoms

AI 기반 식재료 관리 서비스: 냉장고 재료 관리, 영수증 OCR, 레시피 추천, 장보기 목록, Google Calendar 알림 연동을 제공합니다.

🔍 Visualize any Claude Code agent harness — CLAUDE.md, subagents, skills, commands, hooks & MCP servers — as an interactive flow graph. Import from GitHub, ZIP, or local folder. 100% client-side.

an agentic harness system written in rust

Anchor — the production-grade AGENTS.md template for AI coding agents. 51 sections of battle-tested rules. Keep your agents grounded.

Shift-handover workflow for AI coding agents — capture ideas into an inbox, dispatch tasks to the cheapest capable executor (any CLI agent or subagent), and hand work down between sessions, agents, and tools. Composes with superpowers and OpenSpec.

Parallel Claude Code workers in isolated git worktrees — fire tasks, auto-land merges, deploy-safe push throttle

Evidence-preserving multimodal RAG for bilingual (Vietnamese/English) document Q&A — hybrid dense+sparse+graph retrieval, bounded agentic planning, verifiable citations. FastAPI · Qdrant · MongoDB.

Conversational AI Agent & Multi-Agent Workflow Orchestration Platform

Automated vulnerability triage and zero-day remediation of software at scale

Kling AI desktop build for ai tasks. Tuned for Windows 10 and 11 workstations.

Swift package as module for interfacing with SAP Conversational AI in native iOS apps.

The open-source benchmark for LLM memory decay. Measure how Naive, RAG, Chunked RAG, Cascading, and SummaryMemory degrade over 100 conversation turns. Ebbinghaus forgetting curves, 5-provider LLM eval, multi-seed CI. No API key needed.

Prompt, run, edit and download full-stack web applications

A chatbot for an SQL databases. An easy way to interact with your database using natural language

An AI-powered personal assistant that answers questions about you. Built with React, FastAPI & Google Gemini.

Choose your AI. Ask anything. Get answers that matter.

A timeline of ChatGPT: major events, milestones, controversies, etc.

Спроси данные на русском — получи ответ с графиками, инсайтами и публичной ссылкой на дашборд. 30 инструментов анализа, ML-прогнозы, подключение к prod БД. Работает на бюджетных LLM вроде Deepseek V4 Flash.

A interctive offline chatbot vault that stores your personal documents, notes, and files locally, no internet or servers required.

Your conversations with language models, as editable, forkable .chat files in VS Code. Docs: https://ice.leaforest.cc/

Dynamic workflow orchestration for Codex: parallel, resumable, journaled sub-agents for complex tasks.

Use the OpenAI TTS (text-to-speech) model to read any selected text on your Mac with a keyboard shortcut. Bring your own OpenAI API key.