No description
eb52b6b699
* Fix OpenRouter support by using laravel/ai default provider config. PR #216 patched Lab::OpenRouter into every agent match, but laravel/ai already resolves config('ai.default') — including openrouter — when agents omit provider(). Those matches also forced unknown providers to Gemini and BrandAnalyzerRunner checked a non-existent services.openrouter key. Remove the duplicated provider() overrides, gate availability on ai.providers.*.key, and document OPENROUTER_API_KEY. Co-authored-by: Paulo Castellano <hello@paulocastellano.com> * chore(deps): bump laravel/ai to v0.10.3 for native OpenRouter support v0.5.1's OpenRouter driver only covered text/embeddings via the legacy Prism gateway. v0.10.3 ships a native OpenRouter gateway with image, audio (TTS/STT), and web search support, and drops prism-php/prism as a dependency. ai-sdk-development skill docs refreshed via boost:update to match the installed version. * fix: honor AI_IMAGE_PROVIDER instead of hardcoding OpenAI's gpt-image-2 AiImageClient always passed model: 'gpt-image-2' to Image::of()->generate(), so AI_IMAGE_PROVIDER silently did nothing for any provider other than OpenAI — gemini/xai/openrouter would fail against an OpenAI-only model id and quietly fall back to a stock photo. Usage recording was hardcoded to provider 'openai' too, so credits were billed against the wrong model whenever a different provider actually ran. Drop the hardcoded model so generation falls through to the SDK's own config('ai.default_for_images') + per-provider default model, and read the actual provider/model back off the response's meta for usage recording and source_meta instead of assuming OpenAI. * refactor: extract AiImageClient into single-purpose steps, fix uncaught exception generate() built the prompt, called the SDK, and unpacked the response all in one block, with bytes extraction happening after the try/catch — so a response with an empty images collection threw an uncaught RuntimeException from ImageResponse::firstImage() instead of returning null as documented. Split into cleanKeywords(), buildPrompt(), resolveBrandContext(), and toResult(), and moved response unpacking inside the try block so any malformed response is treated as a failure like everything else. Added a regression test with an empty-images fake response. * fix: drop hardcoded default_text_model, resolve model per provider default_text_model was the only per-modality model override in ai.php — image, audio, transcription, embeddings, and reranking all just pick a provider and let it use its own default model. Text had a config-pinned model on top, forced into every agent's model() and into every usage log's model field regardless of which provider actually ran. Switching AI_TEXT_PROVIDER (e.g. to openrouter) kept sending OpenAI's model id to whichever provider ended up handling the request. Removed model() from all six agents so laravel/ai resolves the model from the active provider's own default (OpenAI's default is already 'gpt-5.4', so no behavior change there). Usage-recording call sites now read the actual provider/model back off the response's meta instead of assuming config('ai.default')/default_text_model. StreamPostContent needed the then() callback since broadcast()'s StreamableAgentResponse doesn't expose meta directly. * refactor: drop AiConfiguration wrapper, use data_get() for array reads AiConfiguration was a one-line static helper used by only two call sites, with no laravel/ai equivalent to lean on (confirmed AiManager and the Provider base class expose no isConfigured()/hasKey() check — the package's model is try-then-catch, not pre-flight checks). Inlined the filled(config(...)) check directly into HandleInertiaRequests and BrandAnalyzerRunner instead of keeping a class around one line of logic. Also swapped direct array-key reads for data_get() per project convention across every file touched by the recent AI provider/model fixes (agents' budget arrays, RunGenerateNode/StreamPostCreation's humanizer merge, RegeneratePostMediaImage's baseContext/copy/rendered access). Write/assignment sites (`$x['key'] = ...`) are left as-is — data_get() only reads. * feat: enhance AI configuration with new providers and options Added strict types declaration and updated Azure OpenAI API version. Introduced new 'bedrock' provider configuration with AWS credentials and role assumptions. Enhanced existing providers with additional options, including image deployment for Azure and OpenAI, and updated URLs for Gemini and Ollama. Added support for an 'openai-compatible' driver to broaden integration capabilities. * fix: remove trailing newline in AI configuration file * feat: add support for OpenRouter and ElevenLabs API keys in configuration Updated the production Docker Compose file and example environment file to include commented-out entries for OPENROUTER_API_KEY and ELEVENLABS_API_KEY. This enhances the configuration options for AI providers, allowing for easier integration of additional services. * feat: allow per-provider model overrides for every AI modality Adds a `models` array to each provider block, wired to env vars, so self-hosted operators can pin a specific text/image/audio/transcription/ embeddings/reranking model instead of relying on the package's built-in default for that provider. Only added for the modalities each provider actually implements (verified against laravel/ai's Provider classes). Azure is left untouched — it resolves models via deployment names (AZURE_OPENAI_DEPLOYMENT etc.), not raw model strings, which was already wired before this change. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> |
||
|---|---|---|
| .agents/skills | ||
| .claude | ||
| .codex | ||
| .cursor | ||
| .github | ||
| app | ||
| bootstrap | ||
| config | ||
| database | ||
| docker | ||
| lang | ||
| maizzle | ||
| public | ||
| releases | ||
| resources | ||
| routes | ||
| storage | ||
| stubs | ||
| templates | ||
| tests | ||
| .dockerignore | ||
| .editorconfig | ||
| .env.ci | ||
| .env.example | ||
| .env.testing | ||
| .gitattributes | ||
| .gitignore | ||
| .mcp.json | ||
| .prettierignore | ||
| .prettierrc | ||
| AGENTS.md | ||
| artisan | ||
| boost.json | ||
| Caddyfile | ||
| CLAUDE.md | ||
| components.json | ||
| compose.override.yaml.example | ||
| compose.prod.yaml | ||
| compose.yaml | ||
| composer.json | ||
| composer.lock | ||
| eslint.config.js | ||
| GEMINI.md | ||
| LICENSE.md | ||
| package-lock.json | ||
| package.json | ||
| phpunit.xml | ||
| pint.json | ||
| README.md | ||
| tsconfig.json | ||
| vite.config.ts | ||
Run your whole social presence from one calendar
An open-source social media scheduler with an AI copilot, native publishing to 12 networks,
and an MCP server so your AI assistant can post for you. Self-host it, or skip the setup on cloud.
Try on Cloud • Documentation • Community
What you get
| 📅 One calendar, every network | Plan a month at a glance, drag any post to a new slot, and publish natively to 12 platforms. No redirects, no "finish in the mobile app." |
| ✨ An AI copilot that knows your brand | Captions, hooks, full drafts, and multi-slide carousels in your tone, voice, and colors. It reads your brand profile on every generation. |
| 🤖 Built for AI agents | A first-class MCP server and REST API. Claude, Cursor, ChatGPT, or your own scripts can draft, schedule, and publish for you. |
| ⚙️ Automations that run themselves | A visual workflow builder: triggers, conditions, RSS, webhooks, and AI generation, all server-side. Set it once, let it post. |
| 🗂️ Made for many clients | Workspaces, roles, and approval flows so an agency or freelancer can run a roster of brands without the spreadsheets. |
Features
| Visual calendar | Month, week, and day views. Drag and drop to reschedule across networks. |
| Multi-platform composer | Write once, then tailor the preview per network in parallel. |
| AI generate & review | Draft from a prompt, get inline feedback before you publish. |
| AI carousel builder | Prompt to a multi-slide carousel with images, on-brand. |
| Brand profile | Tone, voice, language, and colors applied to every AI call. |
| Automations | Schedule / RSS triggers, conditions, publish steps, and webhooks. |
| Asset library | Reusable workspace media, plus Unsplash and Giphy search built in. |
| Signatures & labels | Reusable hashtag and CTA blocks, color-coded post tags. |
| Team collaboration | Owner / Admin / Member roles, comments with @mentions on drafts. |
| Workspaces | Isolate each brand, client, or project in its own space. |
| REST API + MCP | Full programmatic control; AI assistants integrate natively. |
| Native analytics | Per-account reach and engagement across every connected platform. |
| Multi-language | English, Ukrainian, Spanish, Portuguese, French, German, Italian, Dutch, Polish, Greek, Japanese, Korean, Chinese, Russian, Turkish, and Arabic. |
Supported platforms
Posts publish natively through each platform's official API.
 |
 |
 |
 X (Twitter) |
 TikTok |
 YouTube |
 |
 Threads |
 Bluesky |
 Mastodon |
 Telegram |
 Discord |
Get started
| ☁️ Cloud | The fastest way in. We host, update, and scale it for you. Start at trypost.it → |
| 🛠️ Self-host | Free forever, your servers, your data. Installation guide → |
| 🤖 Drive it with AI | Connect Claude, Cursor, or ChatGPT over MCP. MCP setup → |
Own your stack
TryPost is open source on purpose. Self-host it and your posts, drafts, and metrics stay on your infrastructure, under a license that is yours to keep. No seat tax, no feature gates, no vendor deciding when to lock you out. Read every line, fork it, and ship it. When you would rather not run servers, the same product is one click away on cloud.
Contributing
Contributions of any size are welcome. Pick an issue, say hi in Discussions, or open a PR with what you would like to see.
Short on time? A star is the most valuable thing you can give. It helps more people find the project.
License
GNU Affero General Public License v3.0. Use, modify, fork, self-host, and redistribute, including commercially. If you run a modified version as a network service, make your changes available to its users (AGPL §13).
Built in the open. Star TryPost on GitHub and tell a friend.