Add complete support for Kimi Code CLI agent format.
- Add convert_kimi() function to generate YAML agent specs
- Add install_kimi() function to install agents to ~/.config/kimi/agents/
- Add Kimi to tool detection and installer UI
- Add integrations/kimi/ directory (generated files gitignored)
- Update integrations/README.md with Kimi documentation
- Add generated agent directories to .gitignore
Users can generate agents with: ./scripts/convert.sh --tool kimi
Generic memory integration pattern using any MCP-compatible memory
server. Replaces vendor-specific PR #57 based on maintainer feedback.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reflect the switch to agents/ (plural), hex color codes, mode: subagent,
and @agent-name invocation in both the OpenCode integration README and the
main README's OpenCode section.
The 250+ generated files in integrations/ were adding repo bloat and would
cause merge conflicts when agents change. Run scripts/convert.sh to
regenerate them locally.
What's committed:
- scripts/convert.sh and scripts/install.sh (the actual value)
- integrations/*/README.md (docs for each tool)
- integrations/README.md (overview)
- .gitignore updated to exclude all generated output dirs
What's excluded (add to .gitignore):
- integrations/antigravity/agency-*/
- integrations/gemini-cli/skills/ + gemini-extension.json
- integrations/opencode/agent/
- integrations/cursor/rules/
- integrations/aider/CONVENTIONS.md
- integrations/windsurf/.windsurfrules
