The Workbench · 10 product cards
Pick the harness, not the hype.
Models, chat apps, and agents are different layers. The workbench — the harness around a model — decides what it can see, touch, remember, and verify. Each product now has a stable detail page with its documented behavior, editorial limitations, and checked sources.
The comparison model
Six layers around the model.
The model is the engine. The harness is the cockpit. The workbench decides what the AI can see, touch, remember, and verify.
Model
The reasoning engine
GPT · Claude · Gemini · Llama · Qwen · DeepSeek · Hermes
Context
What it can read
Files · repo index · long context · RAG · web search · MCP · screenshots
Actions
What it can call or change
Shell · browser · git · APIs · databases · messaging · project systems
Execution
Where work runs
Local terminal · IDE · cloud sandbox · Docker · SSH · CI
Rules & memory
What persists and steers it
Project instructions · saved context · session history · external state
Control
How actions are bounded and checked
Permissions · approvals · sandboxes · tests · diffs · logs · rollback
The products
Compare by working style.
Filters change only this list. Open a card for the full context, permission, verification, and source record.
Aider
A Git-centered terminal coding assistant that builds a concise repository map, edits selected files, commits changes, and can automatically lint and test them.
Verified July 13, 2026 · Open card →Multi-surface coding agentClaude Code
An Anthropic coding agent that works from the terminal and connected development surfaces, with shell, file, Git, MCP, and configurable permission workflows.
Verified July 13, 2026 · Open card →Coding agent across CLI, IDE, app, and cloudOpenAI Codex
OpenAI's connected coding-agent family for local collaboration and cloud delegation, with sandboxing, approvals, repository instructions, and evidence from files and command output.
Verified July 13, 2026 · Open card →IDE-native agent harnessCursor
An AI code editor centered on interactive repository search, multi-file edits, terminal tools, checkpoints, reusable rules, and in-editor diff review.
Verified July 13, 2026 · Open card →Google terminal and IDE coding agentsGemini CLI / Code Assist
Google's open-source Gemini CLI and Code Assist agent mode share file, shell, search, MCP, planning, and approval patterns across terminal and supported IDEs.
Verified July 13, 2026 · Open card →Open-source personal and multi-channel agentHermes Agent
A Nous Research agent runtime with a terminal UI, messaging gateway, tools, skills, memory files, model-provider choice, scheduling, and configurable approvals.
Verified July 13, 2026 · Open card →A category of models and inference runtimesOpen-weight / local models
A do-it-yourself stack in which model weights and a chosen runtime—such as llama.cpp, Ollama, or LM Studio—run on hardware you control; capabilities depend on every component.
Verified July 13, 2026 · Open card →Self-hosted personal-agent gatewayOpenClaw
An open-source gateway that connects messaging channels to an always-available agent with sessions, tools, memory, plugins, and multi-agent routing.
Verified July 13, 2026 · Open card →Open-source software-development agent platformOpenHands
A developer-agent platform with SDK and application surfaces, isolated runtimes, workspace abstractions, command and file tools, and local or remote deployment options.
Verified July 13, 2026 · Open card →Research, search, and grounded-answer layerPerplexity
A research product and developer platform built around current web search, extracted source material, citations, and generated synthesis rather than repository execution.
Verified July 13, 2026 · Open card →Decision guide
Start from the work.
I want to actively code in an editor.
IDE agent
Cursor, Windsurf, and similar IDE-native harnesses.
I want a terminal agent to inspect, edit, and run my repo.
Terminal coding agent
Claude Code, Codex CLI, Aider.
I want to delegate a task and review a PR later.
Cloud / delegated coding agent
Codex web/cloud, Claude Code background modes, OpenHands cloud or self-hosted.
I want current research with citations.
Research / search
Perplexity, Gemini search-grounded workflows, ChatGPT Deep Research.
I want a personal assistant across messaging apps.
Personal agent gateway
Hermes Agent, OpenClaw.
I want self-hosted agent infrastructure.
Self-hosted control plane
OpenHands, OpenClaw.
I want lightweight terminal pair programming.
Terminal coding agent
Aider, Codex CLI.
I want local, private, or open-weight model control.
Local model stack
Ollama, LM Studio, llama.cpp, vLLM, SGLang.