| What it does | AI agent management platform for multi-agent orchestration
| Serverless sandboxes that bill only for the seconds your agent's code runs
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | GB
| MX
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | 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
| Shark Pro $5/month includes $5 of usage; Shark Studio $25/month includes $25; Shark Scale $100/month includes $100. Commands run at $0.12 per compute-hour, billed per second only while running. Services: 2 vCPU / 2 GiB at $0.03/h; 4 vCPU / 4 GiB at $0.06/h. Storage $0.08/GiB-month with first 5 GiB f
|
|---|
| Key features | - 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
| - Persistent Space for agent files and databases
- Pay only for compute time while command runs, not idle or thinking time
- HTTP API with Python and TypeScript SDKs
- CLI for devbox with Claude Code and Codex support
- Sleeping services that wake in milliseconds
- Fork Spaces fast without booting VM
- API key isolation outside VM with egress proxy
- Fast file search with sharkfn 300–600× faster than ripgrep
- Integration with LangChain, LangGraph, smolagents, and Prefect
|
|---|
| What makes it different | - 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
| - Billing only for seconds code actually runs, not idle or thinking time
- Lowest cost compared to alternatives for agent infrastructure
- Persistent Storage with fast Space fork and file access without VM boot
- No GPU required, works with unmodified existing agent harnesses
- Sleeping services wake in milliseconds with zero idle billing
|
|---|
| 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) | 15 ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 3 | 0 |
| Citation Flow (Majestic) | 29 | 0 |
| Referring domains (Majestic) | 50 | 0 |