The memory_search tool requires external API keys (OpenAI/Google/Voyage)
which are not configured. This documents that Nova should use the RAG
scripts directly via command line instead.
- Fixed README.md 'API key is pre-configured' claim
- Fixed scripts/MOLTBOOK_POST.md 'API key is already configured' claim
- Both files now clearly state user must configure their own API key
- Added note that Moltbook posting is optional, not required for core RAG
- Consistent with code fix in v1.0.5 removing hard-coded credential
- Removed embedded API key from scripts/moltbook_post.py
- Script now requires explicit user configuration (env var or credentials file)
- Updated SKILL.md to clarify API key must be configured
- Core RAG functionality unaffected - fully local, no dependencies
- Addresses ClawHub security scan finding about embedded credentials
- Replaced /home/william/.openclaw/workspace/rag with dynamic path
- Replaced /home/william/.local/bin/openclaw with PATH resolution
- Script now portable across different user environments
- Addresses security scan findings from clawhub.com
- Add moltbook_post.py script for posting to Moltbook
- Add MOLTBOOK_POST.md documentation
- Update SKILL.md with Moltbook section
- Update README.md with Moltbook integration
- Support posting from files or direct text
- Handle rate limits gracefully
- Replace all absolute paths with dynamic resolution
- Add path portability and network behavior documentation
- Verify no custom network calls in codebase
- Update version to 1.0.3
- Add MIT License
- Add package.json with OpenClaw skill metadata
- Explicitly declares NO required environment variables (fully local)
- Documents data storage path: ~/.openclaw/data/rag/
- Includes installation steps and available scripts
- Add CHANGELOG.md with version history (v1.0.0)
- Update README.md to:
- Clarify no API keys required (fully local system)
- Add documentation files section
- Reference CHANGELOG, LICENSE, package.json
- Addresses security scanner best practices for transparency
