Voted! Thanks for your input.
Hermes-OpenClaw Directory

Hermes-OpenClaw - The Open Agentic Coding Directory

Every tool that lets an AI actually do the work rather than just suggest it. Terminal agents, AI IDEs, editor plugins, autonomous software engineers, the frameworks that orchestrate them and the sandboxes they run inside. Vendor neutral, community voted, updated continuously.

47 Tools Listed 7 Categories Community Voted Updated July 2026

What is Hermes-OpenClaw?

Hermes and OpenClaw are two open-source agentic coding projects, both listed below. We borrowed their names for this directory because between them they defined the shape everything else converged on: an agent with a plan, a shell, a set of tools and a way to check its own work, running on weights you choose rather than a service you rent.

That shape now spans official vendor CLIs, community forks, research agents, orchestration libraries and sandbox providers. They compete hard on the surface and quietly converge underneath, mostly around MCP for tools, container isolation for execution and some notion of subagents for parallel work. This directory tracks all of it in one place so you can compare like for like instead of reading twenty landing pages.

Model portable

You choose the model. No tool in this directory locks you to a single provider without an escape hatch.

Agent shaped

The tool plans, acts and checks its own work. Autocomplete-only products live in the coding assistants directory instead.

Inspectable

Open source, an open protocol, or at minimum a documented tool surface you can audit and extend.

AI IDEs & Editors
Most Installed

Cursor

AI-first code editor built on VS Code. Understands your codebase, writes code, fixes bugs and now runs background agents in parallel.

VS Code fork Background agents Codebase search
Editor Plugins
Most Installed

GitHub Copilot

GitHub AI assistant. Completion, chat, PR summaries, code review and a coding agent that opens pull requests from issues.

GitHub Coding agent Enterprise All editors
Terminal Agents
Most Popular

Claude Code

Anthropic official agentic coding CLI. Reads whole codebases, runs tests, commits changes and drives subagents, all from the terminal. Also ships as a desktop app and IDE extension.

Official Agentic Subagents Terminal MCP
Terminal Agents
Namesake

OpenClaw

Open-source agentic coding tool, and the project this directory takes half its name from. Provider agnostic, runs locally, and built around an agent loop you can read rather than a hosted service you rent.

Open source Namesake Provider agnostic Local Agentic
Terminal Agents
Official

Codex CLI

OpenAI terminal agent for long autonomous coding sessions. Sandboxed by default, with cloud handoff for tasks that outlast your laptop.

Official Sandboxed Cloud handoff Terminal
Editor Plugins
Editor's Choice

Cline

Autonomous coding agent for VS Code. Plans and executes complex tasks across files, runs terminal commands and drives a browser. Fully open source.

VS Code Autonomous Terminal access Open source
Terminal Agents
Namesake

Hermes

Open-source agent that grew up alongside OpenClaw and shares much of its tooling surface. Aimed at long-running autonomous work, with message passing between the agent and its tools.

Open source Namesake Long-running Composable
AI IDEs & Editors

Windsurf

AI-native IDE with the Cascade agent for autonomous multi-file editing and deep codebase understanding. Now part of Cognition.

AI IDE Cascade Multi-file Cognition
Orchestration Frameworks
Official SDK

Claude Agent SDK

Anthropic official SDK for building agents on the same harness Claude Code uses. Subagents, hooks, skills, MCP and permission control.

Official Subagents Python TypeScript MCP
Editor Plugins
Best Plugin

Continue

Open-source AI code assistant for VS Code and JetBrains. Bring any model, local or hosted, and build custom assistants from config.

VS Code JetBrains Multi-LLM Open source
Terminal Agents

Aider

AI pair programming in your terminal. Git-native, edits multiple files with clean commits and works with essentially any model you can point it at.

Git native Multi-LLM Python Open source
Orchestration Frameworks
Best Orchestration

LangGraph

Graph-based orchestration for stateful, long-running agents. Durable execution, checkpointing and human-in-the-loop interrupts.

Graphs Durable state Checkpoints Python
Terminal Agents
Best Free Tier

Gemini CLI

Google open-source terminal agent with a generous free tier and a very large context window. Strong at reading big repositories in one pass.

Open source Free tier Long context Google
Autonomous SWE Agents
Open Source

OpenHands

Open-source autonomous software engineer. Runs in a container, browses, writes code and iterates against tests until the task passes.

Open source Containerised SWE-bench Autonomous
Web & No-Code Builders

Bolt.new

Browser-based full-stack AI development environment. Prompt to running app to deploy without installing anything.

Browser Full stack Deploy No install
Orchestration Frameworks

OpenAI Agents SDK

OpenAI lightweight framework for multi-agent workflows with handoffs, guardrails and built-in tracing.

Official Handoffs Guardrails Tracing
Editor Plugins
Rising Fast

Roo Code

Community fork of Cline with custom agent modes, per-mode model routing and a large prompt-customisation surface.

VS Code Custom modes Model routing Open source
Web & No-Code Builders
Best UI Gen

v0

Vercel AI UI generator. Natural language to React components, then copy the code or deploy it straight away.

Vercel React UI generation Deploy
AI IDEs & Editors
Fastest

Zed

High-performance collaborative editor written in Rust, with a built-in agent panel and first-class support for external agent protocols.

Performance Multiplayer Rust Agent panel
Orchestration Frameworks

CrewAI

Role-based multi-agent framework. Define crews with goals and backstories, wire them to tools and let them delegate between each other.

Multi-agent Role based Python Delegation
Web & No-Code Builders

Replit Agent

Agent built into the Replit workspace. Plans, writes and deploys an app inside a hosted environment with no local setup.

Hosted Deploy Beginner friendly Full stack
AI IDEs & Editors
Open Source

Void

Open-source Cursor alternative. Run local models or cloud APIs with no telemetry. Full VS Code fork with complete privacy.

Open source Local models Privacy VS Code fork
Web & No-Code Builders

Lovable

Prompt-to-product builder that wires a database, auth and deployment behind the generated front end.

Full stack Auth Database Deploy
Orchestration Frameworks

AutoGen

Microsoft framework for conversational multi-agent systems, with an event-driven core and a visual builder for prototyping.

Microsoft Multi-agent Event driven Open source
Autonomous SWE Agents

Devin

Cognition hosted autonomous engineer with its own workspace, browser and shell. Aimed at delegated tickets rather than pair programming.

Hosted Autonomous Cognition Ticket delegation
Terminal Agents
Open Source

opencode

Open-source terminal coding agent with a provider-agnostic core, a TUI, and a server mode you can drive from anything.

Open source Provider agnostic TUI Lightweight
Sandboxes & Runtimes
Best Sandbox

E2B

Cloud sandboxes purpose-built for AI agents. Sub-second Firecracker microVM starts, filesystem and network isolation, SDKs in Python and TypeScript.

Sandbox Firecracker Isolation SDK
Terminal Agents

Warp

Agentic terminal that turns the shell itself into the surface for AI work, with multi-agent panes and shared session context.

Terminal Multi-agent Rust Shell
Sandboxes & Runtimes

Modal

Serverless compute with a sandbox primitive that agents can call directly. Useful when the agent needs GPUs, not just a shell.

Serverless GPU Sandbox Python
Autonomous SWE Agents
Research Standard

SWE-agent

Princeton research agent that turns any language model into a software engineer through a purpose-built agent-computer interface. The reference implementation for SWE-bench work.

Research Open source SWE-bench Reproducible
Orchestration Frameworks

Pydantic AI

Type-safe agent framework from the Pydantic team. Structured output validation is the core primitive rather than an afterthought.

Python Type safe Structured output Validation
Terminal Agents

Goose

Open-source developer agent from Block. Extensible through MCP servers, runs fully locally and handles long multi-step tasks.

Open source MCP Local Extensible
Editor Plugins
Best Self-Hosted

Tabby

Self-hosted AI coding assistant. Runs entirely on your own hardware with no external calls, which makes it the default for air-gapped teams.

Self-hosted Air-gapped Open source Privacy
Editor Plugins

Kilo Code

Open-source VS Code agent that merges ideas from Cline and Roo, with built-in provider routing and no markup on model costs.

VS Code Open source Provider routing No markup
Editor Plugins

Supermaven

Very fast completion with a 1M token context window. Optimised purely for low-latency inline suggestions.

Fast 1M context Low latency VS Code
AI IDEs & Editors

JetBrains Junie

JetBrains own coding agent, wired into IntelliJ, PyCharm, GoLand and the rest of the suite with full IDE index access.

JetBrains IDE native Index aware Enterprise
Orchestration Frameworks
Best TypeScript

Mastra

TypeScript-first agent framework with workflows, evals, RAG primitives and deployment adapters for the usual edge platforms.

TypeScript Workflows Evals RAG
Editor Plugins

Augment Code

Context-engine-first assistant aimed at very large codebases. Indexes the whole repo and keeps that index warm across sessions.

Large codebases Context engine Enterprise
Terminal Agents

Amp

Sourcegraph agentic coding tool built around unconstrained token use and deep code search across very large monorepos.

Sourcegraph Monorepo Code search Agentic
Sandboxes & Runtimes

Daytona

Fast, stateful sandbox infrastructure for agent workloads, with snapshot and resume so a long task can survive a restart.

Sandbox Stateful Snapshots Open source
Editor Plugins

Amazon Q Developer

AWS coding assistant with deep AWS service knowledge, transformation jobs for legacy upgrades and a usable free tier.

AWS Free tier Migrations Enterprise
AI IDEs & Editors

Trae

Adaptive AI IDE with a builder mode that scaffolds whole projects from a spec, plus a generous free model allowance.

AI IDE Builder mode Free tier
Editor Plugins
Best QA

Qodo

Test and review focused assistant. Generates meaningful test suites and does structured PR review rather than free-form chat.

Testing PR review Quality CI
Terminal Agents

Plandex

Planning-first coding engine for large changes. Keeps work in a protected draft sandbox so you review before anything touches your branch.

Planning Sandbox Multi-file Terminal
Sandboxes & Runtimes

Dev Containers

The open spec most agent harnesses fall back on for reproducible local environments. Not glamorous, but it is the shared substrate.

Open spec Reproducible Local Docker
Autonomous SWE Agents

Refact.ai

Open-source autonomous agent with a self-hosted server option, strong on refactoring and repository-wide edits.

Open source Self-hosted Refactoring Agentic
AI IDEs & Editors

AIDE

AI-native IDE forked from VS Code with proactive suggestions, inline edits and automatic debugging loops.

VS Code fork Proactive Auto debug Free

How to Pick One

You live in the terminal

Start with a terminal agent. Claude Code and Codex CLI are the most capable, Aider is the most model-agnostic, opencode and Goose are the ones you can read end to end.

You want to stay in your editor

Editor plugins keep your existing setup. Cline and its forks give you the most control, Continue gives you the widest model choice, Copilot gives you the deepest GitHub integration.

You want to delegate whole tickets

Look at autonomous SWE agents. OpenHands if you want to self-host and inspect everything, Devin if you would rather buy the outcome than run the infrastructure.

You are building your own agent

Pick an orchestration framework by language and by how much state you need. LangGraph for durable long-running graphs, the Claude Agent SDK for the Claude Code harness, Mastra or Pydantic AI for typed stacks.

Your agent runs untrusted code

Do not skip the sandbox layer. E2B and Daytona give you microVM isolation with sub-second starts, Modal adds GPUs, dev containers cover the local case.

You cannot send code off-premises

Tabby self-hosts completely, Void and Continue run against local models, and most terminal agents will happily point at an Ollama or vLLM endpoint.