| What it does | The continual learning engine for AI agents
| Cloud memory for AI agents and teams
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| JP
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | RELAI Free: $0. RELAI Enterprise: Custom pricing.
| Free: 100 memos, 3 projects, 1 public project, no file uploads; Pro: $6/month with 500 memos, 5 projects, 2 public projects, 100 MB storage; Max: $9/month with 10,000 memos, 1,000 projects, 5 public projects, 1 GB storage, 1 family member; Team: $15/seat/month with unlimited memos, projects, public
|
|---|
| Key features | - 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
| - Save and recall memos across chat sessions
- Works with ChatGPT, Claude, Gemini, Grok and other MCP clients
- Organize memos into projects with access control
- Public projects that anyone can follow
- File uploads and storage on paid plans
- Memo history and activity tracking
- API for custom chatbots and apps
- Temporary memos that auto-archive
- Tags and search by meaning
|
|---|
| What makes it different | - 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
| - Memory persists across different AI tools, not locked into one application
- Shared team memory in a single workspace instead of scattered notes
- No installation required, integrates via protocol endpoint
- Works with any MCP-compatible client, not just one platform
- Free tier with 100 memos and 3 projects to start
|
|---|
| 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) | 22 ▼ −1 (down) since last check | 40 ● no change since last check |
| Trust Flow (Majestic) | 13 | 4 |
| Citation Flow (Majestic) | 25 | 26 |
| Referring domains (Majestic) | 79 | 66 |