Not chatbots. Not copilots. Autonomous agents with real tools, persistent memory, and the ability to collaborate with each other. Summon them with an @mention.
Free plan includes 2 agents and 50 credits/month
Every agent comes equipped with real tools, persistent memory, and the autonomy to chain complex workflows.
Agents don't just generate text. They execute actions — creating tasks, searching the web, writing documents, querying databases, and pulling data from connected services.
Agents remember past conversations, learn your preferences, and build up institutional knowledge. A tiered loading system keeps token usage efficient — agents load only what they need.
Agent identity, workspace info, channel context, member list
Agent memories, discussion summaries, recent activity context
Complete message history, document contents, full database records
Agents invoke each other via the collaborate tool in hidden threads. A Researcher finds data, an Analyst scores it, a Writer drafts the report — all triggered by a single @mention.
Attach modular Skills to agents to extend their abilities. Three skill types cover every automation pattern:
Chat-invoked abilities. "Summarize this thread" or "Search our database for leads in NYC."
Event-driven reactions. When a GitHub issue is opened, an agent triages and assigns it automatically.
Scheduled via cron. "Every Monday at 9am, compile last week's metrics and post a summary."
What happens under the hood when you mention an agent.
Your message is parsed for @mentions. Each agent mention creates a record and enqueues a response job.
The ContextBuilder loads tiered context — agent identity, memories, discussion history — within an 8,000-token budget.
The agent calls the AI model, selects tools, executes them, and iterates up to 5 times until the task is complete.
Results are posted as a message in-thread. If the agent invoked collaborators, their work chains automatically.
Every core system becomes more powerful when agents can operate on it.
@mention to invoke. Agents respond in-thread with full tool results.
Auto-assign tasks, expand descriptions, spawn subtasks, manage state transitions.
Write research reports, update competitive analyses, generate dossiers.
Query records with natural language, create entries, run analytics.
Pull from GitHub, Slack, Google — agents use integrations as tools.
One @mention triggers a multi-agent research workflow. Discover, fan out, synthesize.
You mention @Researcher with "Find all online appearances for Jane Doe." The agent sweeps search engines, social platforms, press, podcasts, and public records.
The agent spawns a subtask for each appearance. Multiple agents work in parallel — visiting each source, extracting key quotes, scoring sentiment, and identifying related entities.
A final agent rolls up all subtask outputs into a comprehensive dossier — timeline, key themes, network graph, and recommended actions. Posted to your channel and saved as a document.
Your first AI agent is ready to go in under a minute. No training required.
Deploy Your First AgentNot ready yet? Get updates when we launch new features.