Native macOS counterpart to the web Omega agent, connecting directly
to the OpenAI API and TPMJS tool registry (1M+ AI-ready tools).
- SwiftUI app targeting macOS 15+ with dark theme
- Full agentic loop: auto-discover tools via BM25, stream OpenAI
responses, execute tools via remote sandbox, loop up to 10x
- SwiftData persistence for conversations, messages, tool runs
- Keychain storage for API keys and environment variables
- SSE streaming via URLSession.bytes with custom parser
- Actor-based services (OpenAIService, TPMJSRegistryService)
- NavigationSplitView layout with sidebar + chat detail
- MarkdownUI for rendering assistant responses
- Settings: API key, model picker, env vars, custom system prompt
- Keyboard shortcuts: Cmd+N new chat, Cmd+, settings, Enter send
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add @tpmjs/tools-slack (10 tools) and @tpmjs/tools-discord (15 tools)
with full API coverage, typed outputs, and domain-validated blocks.
Add 7 missing business categories (finance, legal, hr, marketing, cx,
edu, sales) to TPMJS_CATEGORIES so 50 previously skipped packages
can sync to tpmjs.com.
Fix lefthook secrets hook to skip gracefully when git-secrets is not
installed.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add @tpmjs/tools-resend with email API tools and blocks.yml entries
- Add MCP route for collection skill discovery
- Add InstallationSection component for collections
- Refactor collection pages to use shared components and simplify layouts
- Update skills questions API, rate limiting, and API key handling
- Add tpmjs-tool-creator skill for Claude
- Update video feature scenes and fix lint issues
- Update .gitignore with IDE and temp file exclusions
Implements batched generation to avoid Vercel 120s timeout for collections
with 60+ tools. Uses per-tool caching and recursive serverless invocations.
- Add ToolSkillsCache and SkillsGenerationJob models to schema
- Create tool-skills-generator.ts for per-tool markdown generation
- Create skills-summary-generator.ts for final pass summary/intro
- Update route handler with chunked generation logic
- Small collections (<20 tools) use original monolithic approach
- Large collections use 10-tool batches with progress tracking
