| What it does | The open-source database and workspace for AI agents
| An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Free: $0 (1 space, 3 seats, 5,000 records, 1 GB storage). Plus: $10/seat/month ($120/year, 2 months free) for 3 spaces, 10 seats, 20 GB storage. Pro: $20/seat/month ($240/year, 2 months free) for unlimited spaces, unlimited seats, 100 GB storage.
| 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.
|
|---|
| Key features | - Open source MIT license - run locally, self-host on server, or use cloud
- Support for multiple agents via REST API, MCP, Agent Skills, and OpenAPI
- Human review and approval workflow for agent changes
- Structured data tables with fixed columns for agents and people to share
- Docs and knowledge base with verified sources
- Reusable agent skills and playbooks
- Apps and views built on shared data structures
- Role-based permissions and access controls
- Offline support on desktop with no usage tracking
| - 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
|
|---|
| What makes it different | - Only AI agent workspace that keeps complete history and requires human approval before changes enter canonical data
- Unified workspace where agents and people access the same data, avoiding scattered chat logs
- Completely self-hosted and private on your own hardware with full control over data
- Works with any agent that calls REST API - no lock-in to specific model or platform
- Rejects never enter canonical data - all decisions remain attached for auditability
| - 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
|
|---|
| 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) | 17 ▼ −1 (down) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 6 | 0 |
|---|
| Citation Flow (Majestic) | 32 | 9 |
|---|
| Referring domains (Majestic) | 143 | 4 |
|---|
Busabase
Argentic