GitHub
Inspect issues, open pull requests, summarize reviews, and track repository activity.
Integrations
Start with source control and channels, then expand into data, productivity, and infrastructure workflows.
Inspect issues, open pull requests, summarize reviews, and track repository activity.
Connect merge requests, CI status, and project boards to your assistant workspace.
Send scheduled summaries, alerts, and approval requests to paired Telegram chats. Bundled runtime with long polling, reconnect logic, and group support.
Receive task updates, approvals, and daily summaries in the channels your team already reads.
Run community workflows and support queues from a server-native assistant.
Deliver personal and team updates through configured WhatsApp conversations via the Cloud API.
Route status updates and team workflows into Microsoft Teams spaces via the Graph API.
Post summaries, task prompts, and notifications into Google Chat rooms.
Use Signal for private channel notifications and paired direct-message workflows.
Connect Friday to iMessage for macOS-native direct message delivery.
Use the open Matrix protocol for federated, decentralized team notifications.
Deliver updates into self-hosted or cloud Mattermost workspaces.
Send messages and workflow updates through the LINE Messaging API.
Integrate with Feishu and Lark via the open platform for enterprise messaging.
Connect to IRC networks using IRCv3 for lightweight, low-latency channel delivery.
Run live-stream workflows and bot interactions in Twitch chat.
Reach self-hosted Nextcloud Talk rooms and bots via the Talk API.
Post notifications and updates to Synology Chat via webhook or integration.
Publish encrypted direct messages over the decentralized Nostr protocol.
Build QQ bot workflows with the official QQ Bot platform API.
Deliver messages through Zalo Official Account for Vietnam-based audiences.
Connect to decentralized Tlon groups via Urbit for sovereign communication.
Integrate with ClickClack for specialized channel messaging workflows.
Live dictation and audio transcription powered by any configured STT provider — OpenAI Realtime, Deepgram, and more.
Synthesize spoken audio from assistant responses using ElevenLabs, Cartesia, Deepgram, or any TTS-capable provider.
Generate and edit images through Black Forest Labs, Stability AI, Ideogram, OpenAI, or any image-capable provider.
Create video with async generation jobs via Runway, Kling, Pika, Luma AI, or any video-capable provider.
Generate music and audio output through MiniMax, Stability AI, ElevenLabs, Google, or any sound-capable provider.
Extract text from images and documents through a configured OCR endpoint or provider.
Schedule recurring tasks, one-time runs, and interval jobs with missed-run handling and concurrency policies.
Run agent, image, video, sound, and OCR work concurrently with cancellation and lifecycle event tracking.
Query operational data through scoped credentials and auditable read-only workflows.
Coordinate deploy previews, DNS checks, queues, workers, and edge runtime tasks.
Chat, speech-to-text, text-to-speech, image, and video. GPT-5.5, GPT-5.4, and GPT-5.4 Mini with configurable reasoning effort.
Claude Opus, Sonnet, and Haiku models for chat and tool-use workflows.
Gemini 2.5 Pro, Flash, and Flash-Lite via the OpenAI-compatible Gemini API. Chat, speech, images, video, and music.
Grok 4.3, Grok 4.3 Fast, and Grok Code Fast for chat, realtime voice, image, and video.
Mistral Large, Medium, Small, and Ministral models for chat with configurable reasoning effort.
DeepSeek V4-Pro and V4-Flash via the OpenAI-compatible DeepSeek API.
Sonar Reasoning Pro, Sonar Pro, and Sonar Deep Research for web-grounded research chat.
Llama 4 Maverick, Llama 4 Scout, and Llama 3.3 70B for chat and video via the Llama developer portal.
Command A, Command A Reasoning, Command A Vision, and Aya Vision for chat and speech-to-text.
Qwen3-Max, Qwen3.5, Qwen3-Coder, and QwQ models via DashScope for chat, image, video, and omni tasks.
Kimi K2.6, K2.5, K2, and Kimi Latest for chat via the Moonshot AI platform.
GLM-5.1, GLM-5, GLM-4.6, GLM-4.5V, and GLM-Z1 via the BigModel API.
ERNIE 5.1, ERNIE 5.0, ERNIE X1.1, and ERNIE 4.5 via the Baidu Qianfan platform.
Hy3 Preview for chat, image, video, and 3D via Tencent Cloud API.
Seed2.0 Pro and Seed2.0 Code via BytePlus ModelArk for chat, image, video, and 3D.
MiniMax M2.7 for chat, text-to-speech, video, and music via the MiniMax API.
Reka Core, Reka Flash, and Reka Edge for chat via the OpenAI-compatible Reka API.
Jamba Large, Jamba Mini, and Jamba 1.5 models for chat via the AI21 Studio API.
Nemotron Ultra, Llama Nemotron Super and Nano, and Nemotron VL for chat via NVIDIA NIM.
Uni-1 for omni, image, video, and 3D generation via the Dream Machine API.
Speech-to-text, text-to-speech, audio, and music. Default TTS provider with Rachel multilingual voice.
Nova-3 and Nova-2 for speech-to-text and text-to-speech via the Deepgram API.
Sonic Multilingual and Sonic 2 for text-to-speech via the Cartesia API.
FLUX.1 Pro and FLUX.1 Dev for image generation via BFL API. Default image creator provider.
Stable Image Ultra and Stable Diffusion 3.5 for image, video, and audio generation.
Ideogram 3.0 and 2.0 for image generation with strong text rendering.
Gen-3 Alpha Turbo and Gen-4 for async video generation. Default video creator provider.
Kling 2.1 Master and Kling 2.0 for image, video, and audio generation via Kuaishou.
Pika 2.2 and 2.1 for video generation via the official Pika API through Fal.ai.
Firefly Image 4 and Video for image and video generation via Adobe Developer Console.
Run private workloads on local or self-hosted models for sensitive drafts and internal context.
Need a different system?
Use the JSON data model as a starter, then connect real providers as your product matures.