Tavis

Tadata is an AI employee for Slack that handles research and repetitive sales and go-to-market operations work. It can prepare call briefings, research prospects and companies, draft outreach and follow-up emails, fill CRM fields, monitor relevant LinkedIn activity, and suggest recurring automations. It connects to tools such as HubSpot, Attio, Notion, Linear, GitHub, Google Sheets, Gmail, and Google Calendar, as well as external web sources and MCP or API integrations. Tadata runs pre-built agents or builds an agent from a described process. It observes repeated work, learns team preferences, and requests approval before automating tasks or sending messages; connected-tool access is scoped to the user's authorization. The service is presented as model-agnostic, with portable automations, preferences, exceptions, and agent behaviors that can be exported and versioned.

Griffin is Tavus's first Human Interaction Model (HIM), a real-time, full-duplex video-to-video system for face-to-face conversation. It continuously processes incoming audio and video, models conversational state, and decides when and how to respond, including turn-taking, interruptions, backchannels, expressions, gestures, and responses to visual context and pauses. Its architecture combines a Continuous Conversational Modeling engine with streaming speech and video generation. The conversational engine operates at regular sub-second intervals, while the audiovisual generation system converts its speech and nonverbal control signals into streaming audio and video; every frame is generated in real time from a reference image, including the surrounding scene. Griffin-Lite is described as a research preview available to a select group of early testers, with a broader release planned.

Tavily is a search and content-extraction API for AI agents, providing real-time web access through search, extraction, crawling, and research endpoints. It retrieves live web data, extracts relevant content, and returns structured, chunked results for use as model context; the videos also use it through MCP to capture search trajectories for synthetic agent-training data. The service includes caching, indexing, and security, privacy, and content-validation layers that the site says can block personally identifiable information, prompt injection, and malicious sources.

Tommo is an AI agent app with an interest-groups feature. It groups users around shared goals, such as LSAT study, and lets their agents connect them in group chats.

Tucano is an open-source desktop application for coordinating teams of AI agents on macOS, Windows, and Linux. Agents work in chat-like channels, have roles, tools, memory, and token limits, and can hand work to one another for tasks such as investigation, coding, and review. It uses existing harnesses and sign-ins, including Claude Code, Codex, Cursor CLI, Grok, OpenCode, and Pi, rather than requiring a Tucano API key or per-token billing. Each agent runs in an isolated harness session with context assembled from its workspace, instructions, memories, skills, and recent conversation. Tucano exposes tools through a local MCP gateway that gives each turn only that agent's permitted tools; sensitive calls become approvals showing the exact action and arguments. It supports MCP connectors, scheduled routines, agent computers in Docker, browser sessions, and optional control of local desktop applications through Vercel Labs' agent-desktop. The application stores conversations, memory, logins, files, and configuration locally, using the operating system's keychain or keyring for connector credentials. It is distributed for macOS, Linux, and Windows and can also run experimentally without a window on a server. The repository is licensed under Apache-2.0.