| What it does | An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
| The continual learning engine for AI agents
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| 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.
| RELAI Free: $0. RELAI Enterprise: Custom pricing.
|
|---|
| 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
| - Capture signals from code, requirements, and production traces
- Build and maintain EvalsWiki as versioned behavioral knowledge
- Find missing eval coverage and unclear expectations
- Generate complete evals with scenarios, environments, and evaluators
- Optimize harness across prompts, tools, workflows, and code
- Multi-objective optimization for quality, cost, latency, and KPIs
- Model selection, migration, and routing with evaluation
- Regression-controlled improvement with evaluation evidence
- Versioned storage in repository with pull requests
|
|---|
| 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
| - Turns failures into replayable learning environments
- Prevents regressions by keeping previous evals in the loop
- Integrates with existing observability stacks and traces
- Preserves business intelligence versioned in repository
- Adapts harness to model changes without redefining use cases
|
|---|
| 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 | 23 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 13 |
|---|
| Citation Flow (Majestic) | 9 | 25 |
|---|
| Referring domains (Majestic) | 4 | 79 |
|---|
Argentic
RELAI