Connect your agent to 2,400+ tools through one MCP connection at provider prices
Open-source AI agent orchestration platform for incident response and automation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
FR
Not given
Pricing model
Not given
Open source
Pricing
Free tier with access to free tools and optional $5 promotional credit. Pay-as-you-go with no platform fee on first top-up of $10 or less; 5.5% platform fee (minimum $0.80) on larger first top-ups and subsequent top-ups. Tool calls charged at provider's price with 0% markup. Example prices: Google s
Not given
Key features
Access to 2,436 tools from 52 providers
Support for Claude, ChatGPT, Codex and Cursor
Price preview before tool execution
Per-call billing at provider prices with 0% markup
Spending caps per hour, day, lifetime and per tool
113 playbooks for common tasks
Tools across social media, ads, search and company data
Single prepaid balance across all providers
Incident response with agent investigation and pull request generation
Automated workflows triggered on schedules or webhooks
Agent summoning from GitHub, GitLab and Radicle with /ryph command
Semantic memory system for shared and persistent agent learning
Credentials kept behind gateways with no access in sandbox
Customized environments per repository with cached dependencies
Browser use for agent interactions with live watching
Artifacts and pages for reports and overviews
Deployment options from laptop to Kubernetes
Tool proxy with allowlisted MCP server integrations
What makes it different
One prepaid balance eliminates need for separate accounts with 25+ providers
0% markup on all tool calls - pay provider prices directly
Price transparency with cost shown before execution
Granular spending controls per key, hour, day and tool
Pre-built playbooks reduce setup time for common workflows
Agents work without holding real credentials or keys
Changes ship as patches that require review before merge
Runs on your own infrastructure from laptop to cloud
Semantic memory learns across runs with deduplication and contradiction handling
Built-in safety assuming agents can be manipulated or exploited
Agentik
Ryph