The Short Answer
A source-code study of eleven coding agents found they share seven subsystems and the same retrieval approach, so the agent loop is no longer the differentiator. Enterprise teams should evaluate permissions, sandboxing and portable skills instead. With ibl.ai you own all the code and the data, and our coding-agent skills are plain Markdown.
The study is Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents, an 83-page source-code study of eleven systems submitted to arXiv on 15 July 2026.
Its authors are Paul Barbaste, Tristan Darrigol, Germain Vu and Tom Wiltberger of Wavestone AI Lab. Barbaste is also with Inclusive Brains.
What did the Wavestone AI Lab study of coding agents actually examine?
The Wavestone AI Lab team read the source of eleven production coding harnesses, roughly four million lines of Python, TypeScript and Rust. A twelfth system, a meta-harness called Omnigent, served as a contrast point.
The eleven are Claude Code, Codex CLI, Gemini CLI, Mistral Vibe, OpenHands, Aider, Mini-SWE-Agent, Hermes, Pi, OpenCode and OpenClaw. The paper reports 13 cross-cutting observations, a catalogue of 29 design patterns and 18 design recommendations.
Its working definition is the useful part for buyers: an agent is a model plus a harness, the runtime that connects the model to tools, context, safety controls, orchestration and extensions.
Do all coding agents use the same architecture?
The eleven coding agents converge on seven canonical subsystems, which the paper's first table names as follows. Convergence is not sameness, though: the same subsystem is built very differently from one agent to the next.
| Subsystem | What it does |
|---|---|
| Agent loop | Runs the cycle of prompt, model response, tool call and result |
| LLM integration | Connects to one or more model providers |
| Tools and actions | Reads and edits files, runs commands, calls services |
| Memory and context | Decides what stays in the context window and what is compacted |
| Safety and permissions | Decides what the agent may do without asking |
| Orchestration | Coordinates subagents and multi-step work |
| Extensibility | Skills, hooks, plugins and MCP servers |
The authors also observe that convergence is turning into imitation. Codex adopts Claude Code's hook vocabulary verbatim and ships an importer for its sessions and settings.
Do coding agents use vector databases to search code?
None of the eleven coding agents retrieves code with vector embeddings. The paper describes retrieval as deterministic: ripgrep, tree-sitter, glob, and Markdown context files the agent discovers automatically. Aider adds a ranked repository map.
The second absence is just as plain. No agent runtime in the corpus imports a general-purpose agentic framework. Each team wrote its own loop, and the two absences held when the authors tripled the size of the corpus.
For a team weighing a code-search index or an agent framework as the foundation of its developer tooling, the production evidence points the other way.
Where do coding agents actually differ?
Coding agents differ most in safety and permissions. The paper finds Claude Code uses three permission layers, Codex a four-layer stack with native sandboxing and an approval reviewer, and Gemini CLI four approval modes plus a sandbox.
At the other end, Aider and Mini-SWE-Agent carry minimal safety, the paper's sandbox table lists none for Aider, Pi, OpenCode or OpenClaw, and OpenCode is permissive by default. Pi argues that a documented absence of sandboxing is itself a security position.
Context handling varies as much. The paper counts seven systems that compact at a threshold, each in its own way, while Mini-SWE-Agent keeps an unbounded linear history.
So two agents with the same seven boxes on a diagram can carry very different risk once they reach a real repository and a real terminal.
What should enterprise teams evaluate in a coding agent instead?
With the loop shared across eleven coding agents, evaluate what is not shared. Four questions do most of the work:
- What can the agent reach? Test the default network, filesystem and credential exposure, not the configuration you hope people set.
- Who sets the policy? Behavioural policy is moving from prompt text into configuration, the paper finds. Ask whether an administrator can set it centrally.
- Do your skills travel? Skills ship in 9 of 11 agents and MCP in 8, so knowledge written as SKILL.md files survives a change of tool.
- Is there a record? Ask for the log of what the agent ran, not only what it said.
The paper's conclusion is that in the first half of 2026 the coding harness turned from a tool into a platform. Platforms are where lock-in lives, which makes the fourth question about ownership.
How does ibl.ai fit the harness picture for coding agents?
ibl.ai works with the harness your developers already run rather than replacing it. Agentic Vibe is an MIT-licensed set of more than 150 skills that installs into Claude Code, Codex, Cursor, OpenCode or GitHub Copilot with one command.
Three of those five, Claude Code, Codex and OpenCode, are in the Wavestone corpus. The skills are Markdown, so they follow the convergence the paper documents instead of a format only we read.
Inside the platform, Agent Skills are written playbooks an agent loads when relevant.
The Sandbox panel gives an agent a Linux virtual machine that starts with no network at all. An administrator opens it per agent to package registries, the public internet, or a custom allowlist of named hosts.
The same panel can connect an agent to a registered OpenClaw instance, one of the eleven harnesses the study read. Since the paper lists no sandbox of OpenClaw's own, that is where the platform's controls earn their keep. Transcripts and Audit keep the record.
Who should own the harness that runs your coding agents?
If the harness is now a platform, owning it matters more than which model sits inside it. With ibl.ai you own all the code and the data, model-agnostic across any LLM, with no per-seat pricing.
You can deploy anywhere: your own cloud, on-premise, GovCloud or a fully air-gapped network. Syracuse University runs ibl.ai this way, among 1.6M+ users across 400+ organizations.
ibl.ai is family-owned and operated from New York, NY. Start from the Agentic Vibe page, or book a pilot.
Source: Barbaste, Darrigol, Vu and Wiltberger, Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents, arXiv:2609.00006, July 2026. Figures on subsystems, retrieval, adoption and permissions are the paper's own; we did not re-run its analysis. Product facts are from our documentation, linked above.