Auditable Local-First Code Agent Baseline Model Card

这是可索引项目报告证据页：它保留 Auditable Local-First Code Agent Baseline Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。

Auditable Local-First Code Agent Baseline Model Card

1. Role in Self Evolve

DM-Code-Agent is a local-first and auditable Python code agent baseline with explicit planning, trace replay, optional reflexion modules, and benchmark-facing evaluation paths. It matters because self-evolving agents need explicit feedback loops, observable retention mechanisms, and auditable evaluation pressure before improvement claims become useful.

2. Working Principle

plan and replan -> call tools with JSONL trace capture -> enable optional reflexion or critic modules -> run maintenance benchmark harness -> replay and diff the trajectory

3. Evidence Path

web-observed GitHub page showed 138 stars, 12 forks, 78 commits, MIT license badge, a local-first auditable code-agent framing, JSONL trace replay, and SWE-bench Lite evaluation hooks. This iteration keeps freshness honest: the snapshot comes from the current public GitHub page, while shell GitHub API access remained blocked in this workspace.

4. Teaching Use

Use this card to explain Auditable Local-First Code Agent Baseline: it shows how coding-agent, self-rewarding, optimization, or graph-runtime layers convert agent behavior into a reproducible engineering story.

5. Limits

The repository was not cloned in this iteration; no benchmark run, workflow execution, or training experiment was executed. Counts and claims are visible public-page signals unless independently revalidated later.