Research-backed TODO
Agent runs produce more than chat text: files, patches, logs, screenshots, reports, and package artifacts. CodexClaw should collect these as inspectable local artifacts.
Acceptance criteria
Public research basis
- Open WebUI documents persistent artifact storage for session-related outputs.
- Continue produces PR-check output and suggested diffs as inspectable artifacts.
- CodexClaw release work already produces tarballs and SHA256SUMS assets that fit this pattern.
Non-goals
- No binary preview engine beyond common text/images in the first pass.
- No cloud artifact storage.
Source set
- OpenAI Codex CLI - local terminal coding agent, installer paths, IDE/desktop context.
- OpenHands - local GUI with REST API + SPA, CLI, cloud collaboration/integrations.
- Aider - repo maps, git integration, image/web context, lint/test loops.
- Continue - source-controlled AI checks as markdown agents in CI.
- Open SWE - isolated sandboxes, AGENTS.md context, curated tools, subagents, Slack/Linear handoff.
- Model Context Protocol servers - tool/server registry pattern, filesystem/git/memory/fetch examples, security warnings.
- Open WebUI - responsive/PWA UI, RAG/web browsing, artifact storage, permissions.
- OpenCode - coding-agent modes, plan/build separation, subagent pattern.
- Cline - autonomous coding agent as SDK, IDE extension, and CLI assistant.
- Roo Code - agent-oriented coding workflow inside the editor.
Research-backed TODO
Agent runs produce more than chat text: files, patches, logs, screenshots, reports, and package artifacts. CodexClaw should collect these as inspectable local artifacts.
Acceptance criteria
Public research basis
Non-goals
Source set