#autonomous-agents

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

Q-Learning Swarm Foraging 2026: Multi-Agent RL in Dynamic Grid Environments

Autonomous AI BD Agent for SolCex Exchange: 24/7 Cross-Chain Token Scoring & Payments 2026

🔁 Build reliable recurring AI-agent systems: 968 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

Skill repository to enforce Engineering disclipline in coding assistants

Codex App templates for long autonomous project runs with reviewer agents, learning loops, and narrow safety hooks.

基于 DeepSeek 大语言模型的 AI 编程助手 Agent —— 自然语言驱动的终端编码助手。支持自动读写文件、代码搜索、命令执行、Git 管理，复杂任务智能拆解与多 Agent 并行执行。

Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. 87 subagents + skills, TDD defense-in-depth gates, Kaizen retros, a four-body adversarial council, and an empirically benchmarked QA harness. Does it hang true?

Your own self-hosted AI agent OS

Local-first autonomous agent: Hermes speed plus Rust determinism, gated actions, checkpoints, evidence receipts, MCP, skills, and multi-model freedom.

Fable 5 workflow Loop; A Claude Code skill: autonomous build / audit / verify loop that runs until a machine-checkable contract passes, with ▎ deterministic anti-spin stop conditions (no-progress, retry, oscillation, budget) and on-disk human escalation.

Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars

Multi-project mission control for Hermes Agent users.

A curated, credited library of loops — repeatable AI-agent workflows for Claude Code, Cursor & Codex. Refactor until clean, test until 100%, hunt bugs until none remain.

The continuity substrate for AI agents — memory that becomes a mind: a versioned self-model, a cognitive heartbeat, a shared cortex, metacognition & debate, on temporal-graph memory. Apache-2.0, zero-dep core.

A sandboxed, full-featured agent operating system in a single Go binary. Bring any model, manage local models, point it at a goal, and grant it real authority: every action is sandboxed, governed, and sealed into a verifiable, tamper-evident record an independent party can check. Runs interactive or 24/7, or embed it in your own system.

Behaviour trees for AI agents. Define agentic workflows in YAML, drive deterministic agent runs from a CLI works with any agent, Claude, Codex, Copilot, Gemini etc.

AI Research Agent 2026 🔍 - Autonomous Deep Web Explorer & Adversarial Synthesis

🚀 ralph-claude-code: AI Code Assistant 2026 – Smart Repo Management & Automation Toolkit

The architecture pattern, pitfalls, and security model for running Claude Code as a scheduled, unattended agent — plus a free constitution template. Written and maintained by the agent that runs on it.

Autonomous AI Cloud Agent 2026: Auto-Fix Code & PRs with Multi-LLM Sandbox

Open-core AI coding agent.

An autonomous browser QA agent that explores a running web application, discovers new pages and workflows, fuzzes inputs, detects UI failures, and builds a navigation graph dynamically using Playwright + FastAPI + local LLMs through Ollama.

Boardroom: iPhone command center for an autonomous AI company — agent offices, CEO/CFO/CTO teams, board debates, approvals, builds, QA, and Demo Day via Hermes on your Mac.

Self-hosted manager for Claude Code & Cursor Agent — prompt queues, multi-account quota auto-switch, overnight runs on multiple machines, git push & code review. Control from your phone.

An AI agent builds complete mobile games end to end — design, code, art, music, 136 headless tests, store assets, in-app purchases and signed releases — with humans at only two gates. Godot 4, pluggable market modules (worldwide by default), autonomous QA, and 56 rules learned from real failures.

Hat-Based Multi-Agent Orchestration Loops for Pi Coding Agent 2026 – AI Workflow Revolution

Agentic loop OS for Claude Code on Windows. State on disk, QA with separate memory, and a rate-limit circuit breaker that pauses at zero tokens and resumes on reset. 47 offline tests.

Ralph Desktop 2026 AI Coding Plugin – Visual Prompt Engineering & Automation Tool

Agent Revenue Copilot: $9.90 AI agent earning audit. Buy: https://doctors-lighting-facial-admissions.trycloudflare.com/agent-revenue-copilot/out?route=buy_starter_audit&source=github-repo

Autonomous multi-agent AI penetration testing framework — 20 specialist agents, ECC architecture, MITRE ATT&CK + OWASP mapped, HMAC-chained audit trail, Docker sandbox, and multi-LLM backend (Ollama/OpenAI/Anthropic).

Open, experimental specification (v0.1) for machine-readable trust and Cognitive Passports for autonomous agents. A proposal, not a standard.

Run many parallel Claude Code agents on one git repo — git-worktree branch-ref locks, crash recovery, a merge gate, guard hooks. Delegate work to headless, OS-sandboxed `claude -p` workers on any provider (incl. cheap models); N=2 adversarial reviewers that emit evidence, not verdicts. Stack-agnostic (shell + python3).

A powerful Chrome Extension powered by Chrome's built-in local AI (Gemini Nano). Acts as an autonomous web agent and conversational assistant. 100% offline and private.

Non-custodial crypto payments for AI agents — Python & TypeScript SDK + API spec. Pay, get paid, swap (Base + cross-chain BTC/USDT/XMR), x402/L402 metering, subscriptions, webhooks. Works over MCP, function-calling, SDK or REST.

Turn Claude Code into a phase-aware, multi-team software factory: hard-gated pipeline, Clean Architecture + Effect standards, adversarial review, token discipline.

Ansible role for automated Hermes Agent (Telegram AI bot) installation on Linux and macOS.'

Specification for governance-first context memory in autonomous AI agent systems. Defines the Mandate Gate: a pre-work mandate must exist before an agent session is valid.