Autonomous AI agents that perform tasks independently
Jeremy-Gitau
A small Kotlin/JVM workshop project for learning how to build: MCP servers over stdio an MCP client that launches and connects to a local server process an agent loop that lets Gemini discover MCP tools and call them dynamically simple data integrations against football and cryptocurrency APIs The repository is structured as an educational sample
...moreguanhan01
手机上的 AI Agent：自然语言驱动 103 个内置工具直接操作本机——文件、应用、抓包、APK 反编译、Linux 环境、界面自动化。内置 MCP 客户端与 MCP Server。
AaronWong1999
Put a personal agent inside your product, at 1/1000 the cost. Personal agent infra that runs VM-less personal agents on Cloudflare: Agent Mail, WeChat, Telegram, cloud browser, long-term memory.
...moreaLIZELI
Provenance-retaining cross-session context merge for DeepSeek Harness — a confluence theorem with a counterexample, and a benchmark for it.
...moreContext compaction for RAG and agents: relevance-score every chunk with a local System 1 decision model and cut tokens before they reach the LLM
...morehammrouni
Add AI agents to your PHP app in an afternoon - local-first, no Python sidecar, no framework to learn.
antalez
MCP-сервер для hh.ru: поиск, резюме, отклики, переписка с работодателями и скрытая аналитика по одному аккаунту соискателя через собственный JSON сайта (без официального API). Исходники открыты, некоммерческая лицензия.
...moresuperintelligenceco contributors
Evals as code for LLM apps and agents. Write tasks and graders in YAML, run them in CI, fail the build on regressions.
A local-first, multi-agent writing assistant with project knowledge tools
Reusable LLM security scanning library — language-agnostic guardrails for AI agents
Immune contributors
A general immune system for LLM applications: two lines, every call, reflexes at every boundary.
centerforagenticai-dev
Run headless pi agent sessions in-process with local socket clients, durable replay, live streaming, and explicit driver arbitration.
...moreDeepMind
A suite of test scenarios for multi-agent reinforcement learning.
Measure whether your coding agent actually follows the rules in AGENTS.md / CLAUDE.md.
shengkuan06
Automated research loop that drives WorldQuant BRAIN alphas to all 8 submission gates. Generate, guard, simulate, evaluate, refine — never submits.
...moreDiego Margoni
Tool search for LLM agents, ranked by System-1 decision models, with a benchmark that measures prompt caching.
Magnus Gille
Local, private token and cost atlas for AI coding agents (Claude Code, Codex, OpenCode, Pi)
oneopcai
AgentSchool CLI —— 让 AI Agent 一行命令接入 AgentSchool：抖音解析 / 语音转写 / 文件平台 / 公众号创作（as / agentschool 双入口，Agent Skill 公开仓分发）
GitHub Actions
Local cockpit for running and tracking AI agent tasks in any project folder, with the Claude Code, Codex, OpenCode or pi CLI you already use — zero config, zero database.
...moremetaphorli
PingCode CLI and Codex skill, written in Node.js.
moadrbt
Browser client for Eclatira realtime voice, camera and screen-share sessions.
onehumanai
Access control for the AI agents your customers log in with (Claude in Chrome, ChatGPT agent, Codex, Comet): hide private data from them, ask the account owner's passkey before anything risky, sign every decision on your own server. Node.js middleware + b
...moreGitHub Actions
Provider-agnostic AI agent framework with skill-based architecture
orbit-intelligence
orbit — a premium pure-TypeScript coding agent for Termux and desktop terminals, powered by Orbit X.