| What it does | One memory, every AI tool. Write once, recall anywhere.
| 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 | Freemium
| Freemium
|
|---|
| Pricing | Free: $0 with 1,000 queries/day, 10,000 atoms, 60 req/min. Pro: $29/mo with 50,000 queries/day, 500,000 atoms, 600 req/min. Team: $149/mo with 500,000 queries/day, 5,000,000 atoms, 3,000 req/min. Enterprise: Custom limits and 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.
|
|---|
| Key features | - Persistent cross-tool memory API working with Claude, Cursor, VS Code, ChatGPT, Python, and any HTTP client
- Hebbian associations that strengthen links between concepts recalled together
- Outcome feedback that re-ranks recall based on usefulness
- Automatic query expansion along learned associations
- Python SDK with typed errors for write, read, feedback, and stats
- REST API for any HTTP client
- Per-tenant org isolation and SHA-256 hashed API keys
| - 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 | - Learns from outcomes and improves over time, unlike vector databases that only perform similarity search
- Works across every AI tool with a single API key, not locked to one platform
- Complementary to RAG: remembers outcomes and lessons, not just document similarity
- Free tier with full API access and MCP server, no credit card required
| - 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) | 40 ▼ −1 (down) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 7 | 0 |
|---|
| Citation Flow (Majestic) | 37 | 9 |
|---|
| Referring domains (Majestic) | 200 | 4 |
|---|
Mnemoverse
Argentic