Model
Produces responses and tool-use decisions. Qwen and DeepSeek models are examples. Their speed and quality depend on the exact model, serving setup and task.
Inside the coding workflow
Inspect the run.
Decide what stays.
AX Code is an agent harness: it connects a model to project tools, session records and review workflows. The value is what you can inspect, verify and recover after an agent edits your code.
One bug, a reviewable change
This walkthrough uses an illustrative task. Commands below describe real AX Code interfaces; replace example session IDs with your own. No model is running in this page.
01 · Connect your model and set the boundaries +
Open AX Code in your repository and use /connect to choose a supported local runtime, cloud provider or coding CLI. Choose your sandbox and permission settings before granting access to unfamiliar code. Ordinary sessions do not automatically enforce your project’s test suite.
ax-code --sandbox read-only02 · Inspect the problem, then authorize the change +
Ask the agent to find where empty input is accepted and identify the relevant tests. Review its findings, enable the write scope you intend to allow, and request a focused fix. A reusable skill can supply your team’s investigation or review instructions.
Find why whitespace-only input is accepted. Show the relevant code and tests before making changes.
03 · Verify the change and inspect the execution +
Run the repository’s checks and inspect the diff. Use the session graph to see recorded steps and tool calls. A recorded check failure remains a failure; the agent’s completion message is not proof that a patch is correct.
git diff
ax-code graph <session-id>04 · Compare attempts or inspect recovery points +
Compare two sessions to review changes in execution and risk signals. List available rollback points before choosing a recovery step. Recovery depends on retained snapshots and cannot undo external side effects such as sent messages or remote deployments.
ax-code compare <session-a> <session-b>
ax-code rollback <session-id> --listYour coding CLI, inside AX Code
Keep the CLI you already use and bring it into AX Code as a provider. Supported adapters reuse the local CLI and its login/session, so you can evaluate your existing coding setup alongside local and hosted models.
| Coding CLI | Provider ID | Local command |
|---|---|---|
| Claude Code | claude-code | claude |
| Codex CLI | codex-cli | codex |
| Grok Build CLI | grok-build-cli | grok |
| Kimi Code CLI | kimi-cli | kimi |
Install and sign in to the vendor CLI first, then connect its provider. For example:
ax-code providers login codex-cliUse AX Code’s skills and repository checks to structure the task, then review the recorded session and resulting diff. Capabilities and visibility depend on the adapter and CLI; integration alone does not establish higher coding accuracy or make every nested action visible.
CLI provider setup and requirements ↗Beyond a single attempt
Arena implement mode runs candidate solutions in isolated Git worktrees and evaluates them against repository checks. Verified candidates rank ahead of candidates that fail verification. You review the evidence and choose what to keep; AX Code does not automatically merge a winner.
Read the documented execution and arena capabilities ↗Models, harnesses and skills
Agent harness
Connects the model to tools and manages the execution loop. AX Code, Codex, DeepSeek Harness and Hermes Agent belong in this comparison. DeepSeek Harness is a separate project from DeepSeek’s model API.
Skill
Reusable task instructions and optional supporting resources. Skills guide the agent; they do not replace the runtime or guarantee correct output. AX Code supports project skills using SKILL.md.
Compare the harness, not just the model
Evaluate tool boundaries, session evidence, recovery, customization and verification using the same task. Shared features such as skills or local models are not evidence that one tool is uniquely capable.