Platform capabilities

One platform. Every capability an agent needs.

From a browser-based coding agent to webhook automation and multi-tenant governance — accurate to what ships today, with beta work clearly marked.

Core agent engine

Shipped

ReAct agent runtime

Multi-step reasoning with streaming tool calls over WebSocket, with full event replay on reconnect.

Shipped

Human-in-the-loop

Agents request approval for risky tools, ask to clarify when unsure, and pause for your decision.

Shipped

Autonomous runner

Background execution for signals and schedules with planning, working memory, and budget guardrails.

Code intelligence & Let’s Code

Shipped

Let’s Code IDE

Clone a GitHub repo, browse files, and chat with an agent that proposes diffs you review and export as a PR.

Shipped

Reviewable diffs

Per-file and per-hunk accept/revert against a clone — focused verify runs before anything ships.

Beta

Graph-aware retrieval

Symbol and call-graph indexing (CRS) grounds edits in callers, callees, imports, and related tests.

Knowledge & RAG

Shipped

Document knowledge

Upload PDFs, text, and markdown — chunked and embedded for per-agent semantic retrieval.

Shipped

Website crawler

Index sites via sitemap or crawl, grouped as one source with live progress.

Shipped

Self-learning (Dream)

Agents distil knowledge cards from their own history and inject them into future runs.

Tools & integrations

Shipped

1,800+ tools

Builtin + MCP + OpenAPI/Postman services, lazily loaded and authorized per agent.

Shipped

Semantic tool discovery

Agents find the right tool via embedding search instead of a bloated prompt.

Shipped

MCP servers

Connect stdio/HTTP/SSE MCP servers with credential injection and circuit breakers.

Automation

Shipped

Signals (webhooks)

External systems fire agents with idempotency, HMAC auth, retries, and a dead-letter queue.

Shipped

Schedules (cron)

Run agents periodically with per-schedule budgets, max runs, and auto-pause on failure.

Beta

Workflow builder

Compose multi-step automations on a node canvas with retries, approvals, and sub-workflows.

Security, governance & cost

Shipped

Multi-tenancy

Organizations, workspaces, teams, and RBAC with workspace-scoped resources and audit trails.

Shipped

Encrypted credentials

Fernet-encrypted vaults and OAuth connections — secrets are never exposed to agents or logs.

Shipped

Cost observability

Every LLM call is logged with tokens, latency, and frozen cost — per user, agent, and source.

See it on your own repo

Start free, bring your own model keys, and self-host in minutes.