| What it does | An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
| Production control plane for AI agents with model gateway, stateful runtime, and observability
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Paid
|
|---|
| Pricing | Prototype: free during beta, then from December 16, 2026 it costs $1 per 1,000 agent calls after 1,000 monthly included calls. Production: $20 a month with 20,000 agent calls included, then $1 per 1,000 calls after that. Top-ups: $1 per 1,000 calls, from $10 to $500 at a time, never expiring.
| Relay: usage by model through API. Loop: base + usage for agent runtime capacity and managed runs. Lens: base + usage for observability retention and recorded events. Build Agent Service: custom scoped professional service. WebSearch API: $0.01 per successful simple/reader request, $0.08 per success
|
|---|
| Key features | - Prompt rebuilt from journal under token cap at each step to keep it bounded as history grows
- Spending limits checked before each model call at token prices you declare
- Resume after crash without repeating finished actions
- Tool calls returned as actions for your code to carry out
- Proof of what ran: check prompts, re-run engine, download hash-chained journal
- Integrations with Vercel AI SDK, OpenAI Agents SDK, LangGraph, Mastra, Pydantic AI
- MCP server for Claude Code, Claude Projects and Codex
- Works with any model via bring-your-own-key
- TypeScript and Python clients for HTTP API access
| - Model protocol translation for OpenAI, Anthropic, and Gemini SDKs
- Policy routing and approval gates for model calls
- Stateful agent runtime with session management
- Managed tool attachment and control
- Decision replay and audit trails
- WebSearch API with multiple query types
- Full request traceability from model to outcome
- SDK compatibility without code changes
|
|---|
| What makes it different | - Bounded prompt under a fixed cap while history grows, so costs per call stop climbing on long sessions
- Every run recorded with cryptographic proof: rebuilable prompts, hash-chained journal, re-runnable engine
- Resumes from crash without repeating finished actions using stable idempotency keys
- Budget enforcement before each model call, not reactive overage billing
- No model key storage or logging; your provider bills you directly
| - Three coordinated products (Relay, Loop, Lens) in one control plane versus stitching together separate tools
- SDK-compatible: change the base URL, not your code
- Decisions remain observable, replayable, and auditable without page turns
- Full evidence bundle exports with every decision
- Unified LLM gateway eliminates key sprawl and model switching without code changes
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 18 ● no change since last check |
| Trust Flow (Majestic) | 0 | 3 |
| Citation Flow (Majestic) | 9 | 20 |
| Referring domains (Majestic) | 4 | 33 |