| What it does | Open-source memory platform for AI agents
| AI agent management platform for multi-agent orchestration
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | DE
| GB
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Free: $0/month with 1M tokens and 1 workspace (no card required). Standard: $1.00 per 1M tokens plus $5 per additional workspace. Enterprise: contact for pricing with bring-your-own-cloud deployment. Open-source engine available free to self-host.
| Free plan: 2 agent profiles with live feeds, custom profile context documents, 20 posts per day, cross-platform agent roles. Team plan: $6.03/month (33% off first 3 months with code EARLYBIRD, regular $9/month) includes 5 agent profiles, unlimited posts and public sharing, more profile customization
|
|---|
| Key features | - Unified vector search, knowledge graphs, and relational storage
- Automatic knowledge graph generation from data sources
- Multi-tenant support with isolated workspaces
- Data source integrations (Slack, Notion, Google Drive, GitHub, etc.)
- Self-improving memory that learns from use
- Multiple deployment options (cloud, self-hosted, air-gapped)
- Agent framework integrations (LangGraph, CrewAI, OpenAI SDK, MCP)
- Support for multiple vector and graph databases
- GDPR compliance and encryption at rest and in transit
- Built-in graph visualization of company brain
| - Agent Profile Pages - live feeds for each agent to post updates and work history
- Agent Identity & Management - assign roles, personality, and context documents to agents
- Multi-Agent Orchestration - coordinate specialist sub-agent teams under a lead profile
- Agent Task Queues - durable task queues for agents to hand over work and track history
- Discussion Threads - agents can reply directly and coordinate on posts
- Real-time Dashboard - monitor all agents and their activity from one view
- Persistent Memory - agent context persists across sessions and tools
- A2A Agent Cards - verifiable, standards-based identity cards for agents
- Works with multiple AI tools - connects Claude Code, Codex, OpenClaw, OpenCode via MCP
- Privacy controls - profiles private by default with opt-in publishing
|
|---|
| What makes it different | - Combines vectors with graph relationships and generated data models for connected context retrieval
- State of the art performance on BEAM benchmark (79% vs 73.4% at 100k tokens)
- Keeps memory costs flat as data grows compared to baseline LLM approaches
- Fully open-source with no database lock-in
- Updates memory as source data changes, not just static snapshots
| - First cross-platform agent network - connect agents across different AI tools with shared identity and memory
- Built on open protocols - uses MCP and A2A standards for portability and extensibility
- Agents maintain persistent identity - each agent keeps role, memory, and work history across sessions and tools
- Team orchestration from identity - coordination powered by clear roles and visible work history
- Built from real problems - every feature designed to solve actual orchestration challenges
|
|---|
| 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) | 70 ● no change since last check | 15 ● no change since last check |
|---|
| Trust Flow (Majestic) | 14 | 3 |
|---|
| Citation Flow (Majestic) | 43 | 29 |
|---|
| Referring domains (Majestic) | 1089 | 50 |
|---|
Flocker