taracodlabs/aiden

Aiden — an autonomous AI agent and work engine built solo. It can operate your browser, terminal, files, apps, APIs, skills and tools, remember context, recover from failures, automate workflows, and verify the result. Open source · AGPL-3.0.

What it solves

Aiden is an autonomous AI engine designed to move beyond simple AI advice and perform real computer work. It solves the problem of fragmented, multi-step tasks that typically require dozens of prompts, allowing users to set a high-level goal and have the agent autonomously plan, execute, and verify the results across various system resources.

How it works

Aiden operates as a work engine that transforms a goal into a structured pipeline: Goal $\rightarrow$ Job $\rightarrow$ Plan $\rightarrow$ Attempt $\rightarrow$ Effect $\rightarrow$ Approval $\rightarrow$ Execution $\rightarrow$ Evidence $\rightarrow$ Verification $\rightarrow$ Verdict $\rightarrow$ Proof. Unlike tools that assume success based on a model's response, Aiden tracks these stages separately to ensure work can be recovered and reconciled. It utilizes a runtime that supports multiple LLM providers (including OpenAI, Anthropic, Google Gemini, and local models via Ollama) and integrates with files, terminals, browsers, APIs, and MCP servers.

Who it’s for

It is intended for developers and power users who need an autonomous agent to handle complex technical tasks such as codebase management, research, browser-based workflows, and background system automations.

Highlights

  • Codebase Mode: Snapshots repositories to make conflict-safe changes, run tests, and verify final states with durable evidence.
  • Multi-Tool Integration: Works across the terminal, browser (via Playwright/Chromium), files, and connected services like Discord, Slack, and Telegram.
  • Control Mechanisms: Implements risk-tiered approvals, budgets, and scoped permissions to keep the user in control of consequential actions.
  • Autonomous Triggers: An optional daemon mode allows Aiden to react to files, schedules, email, and webhooks.
  • Sub-agents: Ability to delegate specific parts of a larger job to isolated sub-agents and combine the results.

Related

  • Project
    Vasco0x4/AIDA

    AIDA is an open‑source autonomous pentesting platform that lets any LLM (Claude, Gemini, OpenAI, etc.) drive a Docker‑based security‑testing environment. The agent can run reconnaissance, scanning, custom Python exploits, and raw HTTP manipulations, logging every command and its output in a persistent notebook. Findings are auto‑scored with CVSS 4.0 and can be exported as PDF reports. The project includes a web dashboard, JWT authentication, notification hooks, and supports swapping the built‑in `aida-pentest` container for the larger Exegol image. Real CVEs discovered by AIDA are listed, showing practical impact. Licensed under AGPL‑v3.

  • Project
    pikpikcu/airecon

    An autonomous penetration testing agent that uses LLMs to drive a Kali Linux sandbox and Caido proxy to automate the RECON-ANALYSIS-EXPLOIT-REPORT pipeline.

  • Project
    getsentry/warden

    Warden is an open‑source Sentry project that runs AI‑powered code reviews using reusable “skills”. It can be invoked locally via a CLI or automatically on each PR through a GitHub Action, posting findings as inline comments and Checks. Supports OpenAI and Anthropic models and can auto‑apply simple fixes.

  • Project
    iOfficeAI/AionUi

    AionUi is a free, cross‑platform desktop app that turns LLM APIs into autonomous AI agents capable of reading/writing files, generating Office documents, browsing the web, and running scheduled tasks. It includes a built‑in agent engine, supports dozens of external CLI agents, offers a Team mode for coordinated multi‑agent work, and provides remote access via WebUI or chat‑platform bots.

  • Project
    luoguoxiong/aipack

    aipack is a TypeScript‑first, lightweight AI‑agent framework. It includes its own runtime, a Tapable‑based plugin system, and built‑in adapters for 13+ LLM providers. Features include streaming vs. batch execution, persistent session storage, permission‑based tool approval, hybrid BM25 + vector long‑term memory, five‑stage context compression, multi‑agent orchestration (graph, pipeline, router, debate, map‑reduce), two‑way MCP integration, full observability (metrics, dashboard), and an offline evaluation suite. The project ships a CLI assistant, a library for embedding in apps, and example apps demonstrating real‑world use cases.