Async Agents

Autonomous & Async Agents

Agents that operate independently on tasks, often outside your local editor.

13 tools · 13 with full reviews · 6 free or open source · Updated Aug 14, 2026

Google Jules is an autonomous, asynchronous AI coding agent designed to handle software development tasks like bug fixes, dependency updates, and feature implementation by creating pull requests on GitHub. It operates in an isolated virtual machine, allowing it to plan, code, and test independently while you focus on other work.

OpenHands Freemium

All Hands OpenHands is an open-source autonomous AI coding agent platform that performs end-to-end software engineering tasks like writing code, running terminal commands, browsing the web, and opening pull requests. It provides a flexible, model-agnostic architecture supported by a Python SDK, CLI, and web GUI, enabling developers to automate complex workflows while maintaining full ownership of their data.

SWE-agent Open Source

Princeton NLP SWE-agent is a research-grade framework that enables language models to autonomously fix issues in GitHub repositories by utilizing a specialized Agent-Computer Interface. It is designed to navigate codebases, execute commands, and run tests to resolve software engineering tasks without human intervention.

Sweep Sweep operates as both an AI-powered coding assistant plugin for JetBrains IDEs and an enterprise-grade agentic platform for managing system metadata across platforms like Salesforce and Snowflake. The coding assistant provides context-aware autocomplete and agentic refactoring, while the enterprise platform offers cross-system dependency mapping and governed automation.

Ellipsis Freemium

Ellipsis Ellipsis is a cloud-based platform for managing and deploying autonomous coding agents as infrastructure. Agents are defined via YAML files within your repository, allowing for version-controlled, triggered, and governed automated workflows like code reviews and bug fixes.

Cosine Genie AI is a legal-focused AI platform that automates the drafting, review, and negotiation of complex business contracts. It utilizes a multi-agent system with a specialized evidence layer to ensure legal accuracy and prevent hallucinations by validating outputs against document clauses and rules.

Open-yak OpenYak is a local-first desktop AI agent designed for document processing, file management, and long-running automation workflows. It allows users to maintain full privacy by keeping all files, conversation memory, and workflow states on their local machine while offering the flexibility to connect local or cloud-based LLMs.

DeepAgents JS Open Source

LangChain DeepAgents JS is an opinionated, production-ready agent harness built on LangGraph that provides out-of-the-box support for complex, multi-step tasks. It includes built-in capabilities like persistent filesystem access, delegated subagents, context summarization, and human-in-the-loop controls.

Orkas-AI Orkas is an open-source, local-first AI agent workforce that allows you to direct a team of specialist agents through chat to handle complex, multi-step workflows. It prioritizes data privacy by keeping files and configurations on your local machine, while supporting both Orkas-managed models and bring-your-own-provider configurations.

Kody Open Source

Kent C. Dodds Kody is an MCP (Model Context Protocol) server designed to act as a home for an AI agent's memory, authentication keys, code, and automations. It allows agents to interact securely with your personal services and accounts across various host applications.

Omnigent Open Source

Omnigent Omnigent is an open-source meta-harness that provides a unified orchestration layer for AI agents, including Claude Code, Codex, and custom agents. It enables real-time collaboration, stateful contextual security policies, and consistent session management across terminal, desktop, and web interfaces.

Monica Manus is an autonomous, general-purpose AI agent that plans and executes complex multi-step tasks in a cloud-based virtual computer, including web browsing, code writing and execution, data analysis, and producing finished deliverables like reports, spreadsheets, slides, and web apps.

LoopTroop Open Source

LoopTroop AI LoopTroop is a local, open-source GUI orchestrator that automates complex AI coding tasks from ticket to pull request. It uses LLM councils for planning, atomic 'beads' in isolated git worktrees for execution, and Ralph-style retry loops for self-correction, with human approval gates at key boundaries.

FAQ

What are the best Async Agents tools?

The most complete Async Agents listings on ai.dosa.dev include Jules, OpenHands, SWE-agent. Every tool has a detail page with pricing, key features, and a verdict - see the full list of 13 tools below.

Are Async Agents tools free?

6 of the 13 Async Agents tools listed here are free or open source. Others offer freemium or paid plans - check each tool's detail page for current pricing.

How is this list curated?

ai.dosa.dev is manually curated from community submissions and editorial review. Entries are enriched with pricing, features, and reviewer notes, and the directory is updated continuously.