Havuz

Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip instal

Automated auditing pipeline for LLM and agent benchmarks — surfaces task ambiguity, environment conflicts, and evaluation bugs.

AI-first open source operating system for various devices, based on the Android.

Self-host your own AI app builder: FOSS v0/Lovable like.

The framework for building stateful agents. Your agent is a folder of state, served over MCP, used from any runtime.

Bash interpreter with git-like memory and fine grained access control.

基于 B 站博主 黑鸦（Heya）视频标题的深度分析，让 AI 学会黑鸦的标志性风格：长标题、情绪炸弹、多事件合并。

Open Source Agentic Security Scanner

Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work wi

agent tui in a web gui

A lightweight toolkit for building secure AI systems with built-in middleware, protected memory, and AI safety models that mitigate prompt i

Agents Anywhere, Codex, Claude Code ve DeepSeek Harness oturumlarını masaüstü, mobil ve Web istemcilerinden uzaktan yönetmeye yarayan, self-host edilebilen bir Agent çalışma alanıdır.

Neden yükseliyor · Kesin nedeni mevcut verilerden belirlenemiyor. 135 günde 1.400 yıldız ve son 28 günde 647 commit ilgi ve yoğun geliştirme gösteriyor; ancak aynı dönemde yalnızca 3 farklı yazar olması katkıların dar bir ekipte toplandığına işaret ediyor.

Control your Pi coding agent from your phone. Pair with a one-time QR code and chat with your local agent, even when you're away from your c

Open-source TypeScript framework for building operational software used by humans and AI agents.

Agent Reliability Analyzer: deterministic scanner that finds and fixes AI agent reliability failures

Deterministic agent reliability detection rules for the Trustabl Analyzer

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

Public home for Atlassian Teamwork Graph CLI users, release notes, issue tracking, agent skills, and marketplace plugin integration notes.

Local agent infrastructure in one stdlib-only Go binary

The daily arena where AI agents clash to rank tomorrow’s S&P 500 winners and losers. Their only judge is the future — the one truth that sim

Live-proven Cloudflare Project Think contracts — each example deploys to a real Worker, proves its claim against live state, and tears itsel

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

One Layer, All Seekable

A local-first control layer for AI agents

Universal OpenCode TUI sidebar for browsing provider agents and subagents

The open-source skills that turn your agent into a full PR team.

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in

Hands-on Microsoft Foundry hackathon labs to build, monitor, evaluate, and deploy agentic AI workflows.

Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.

一款专注于慢性病管理的AI平台，通过多Agent协作问答、干预效果仿真预测、认知评估与训练、亲情账号关怀等核心技术，为慢病患者提供专业、个性化的健康管理服务

Embedded long-term memory database for AI agents & LLM apps. Six-layer cognitive architecture, knowledge graph, hybrid BM25 + vector search,

CLI tool surface for Telegram channel agents

My notes and insights on designing self-evolving LLM agents.

Template organization overlay for extending Centaur with tools, workflows, skills, and sandbox guidance.

Behavior guidelines that stop your AI coding agent from overengineering, hallucinating, and breaking things

🐾 A desktop pet that reacts in real time to your AI agents — Claude Code, Codex, Antigravity, OpenCode, Cursor, Copilot, Gemini.

The factory for custom internal software, purpose-built for human2agent work.

Apple Silicon mlx with Zero Dependency Java

Official Repo for Spreadsheet-RL

Teaching people about WebMCP

Humanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it

多功能 AI 编程助手 支持web/本地应用/bot接入 等

Event-sourced graph runtime for durable and stateful agents

A menu bar app that can become anything you ask it to be.

One command to cut token usage by up to 50%+

The Hale programming language: general-purpose, native and memory-safe, from a five-line script to a dynamic distributed system. Less langua

A modern, hands-on, self-paced course that takes you from your first line of Python to shipping a real AI-powered automation.

Full stack agent runtime and orchestration framework built in typescript.

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code,

[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted A