Feature Overview
A complete summary of everything you can do with VectorChat.
This page provides a quick reference to every feature in VectorChat.
| Feature | Description | Learn More |
|---|
| Agents | Create AI agents with custom instructions, persona, constraints, and model selection. Agents can use tools, search knowledge bases, and remember users across conversations. | Agents |
| Conversations | Chat with your agents in real time. Agents respond using streaming and can call tools, ask clarifying questions, and search your knowledge bases. | Agents |
| Knowledge Bases | Upload documents, crawl websites, or add text content. Shared across multiple agents. Agents search automatically using document search. | Knowledge Bases |
| Skills | Reusable instruction sets you can attach to multiple agents. Generate skills from example questions or write them manually. | Agents |
| Scheduling | Run agents automatically on a schedule (hourly, daily, weekly, monthly). Includes approval workflows and prompt templates with date variables. | Scheduling |
| Organizations | Create team workspaces with role-based access (owner, admin, member, billing). Invite members, manage seats, and share agents across your team. | Settings |
| Embeddable Widget | Deploy agents as chat widgets on your website. Customize theme, initial messages, position, and branding. | Agents |
| API Access | Use OAuth client credentials to interact with agents programmatically. | Settings |
| Integration | Type | Capabilities |
|---|
| Gmail | OAuth | Read, search, send, archive, label, and delete emails |
| Slack | OAuth | Send, update, and delete messages. List channels, members, and users. Read message history. |
| Google Calendar | OAuth | Create, list, update events. Quick-add events. Invite attendees. Auto-generate Google Meet links. |
| Google Drive | OAuth | Search, read, create, and update files. List folder contents. |
| Email (IMAP/SMTP) | Credentials | Read, search, send, reply, move, and delete emails via any IMAP/SMTP provider. |
| Calendar (CalDAV) | Credentials | List calendars and events. Create, update, and delete events via any CalDAV-compatible calendar. |
| Web Search | Built-in | Search the public web for current information. |
| Web Fetch | Built-in | Fetch and read content from any public URL. |
| Tool | Description |
|---|
| Execute Code | Run sandboxed JavaScript/TypeScript functions with schema-validated inputs and outputs. Configure timeout, memory, and CPU limits. |
| Data Collection Query | Query structured data collections with exact-match filtering. |
| Conversation State | Store and retrieve JSON state snapshots per conversation. |
| Ask User Question | Present multiple-choice questions to users during a conversation. |
| Knowledge Base Search | Search shared knowledge bases and return relevant document chunks. |
| User Memory | Remember and recall information about users across conversations. |
| Setting | Description |
|---|
| Agent Mode | Multi-turn reasoning with tool calls, self-correction, and reflection. |
| Think Tool | Internal reasoning step the agent uses before responding. Can be made visible to users. |
| Autonomy Level | Controls when the agent asks for confirmation before taking actions. |
| Persistent Memory | Agent remembers facts, preferences, and decisions about users across conversations. |
| Context Retention | Configurable token budget for conversation history. Older messages are auto-summarized. |
| Setting | Description |
|---|
| Max Turns | Limit how many conversation turns the agent can take per session. |
| Max Tool Calls | Limit how many tool executions are allowed per session. |
| Token Budget per Turn | Maximum tokens the AI model can generate per request. |
| Request Timeout | Maximum time allowed for each AI model request. |
| Reflections per Turn | How many times the agent can self-correct within one turn. |
| Reflections per Session | Total self-correction budget across the entire conversation. |