Assurance, research and network for autonomous AI agents
Open-source home for AI agents
Stage
Startup
Startup
Founded
Not given
2022
Based in
Not given
Not given
Pricing model
Not given
Freemium
Pricing
Not given
camelBot: free to start, no credit card required, credit packs from $4.99. camelRun: $0.01 per agent-hour of active run time, $0.10 per GB-month for storage, tokens free on your own provider keys or at provider's price on camelAI's keys with no markup. camelCode: free plan with your own model API ke
Key features
Test agent behavior against explicit authority boundaries
Preserve separate evidence of actor choice, authorization, containment and effect
Bounded adversarial behavioral testing
Repair and retest workflows with lineage
Public Observatory for longitudinal research
Provider-neutral and framework-compatible
Customer-controlled assurance runtime
Agent-to-agent collaboration and cross-agent encounters
Test financial authority and spending limits
Open integration surface with developer tooling
Define agent model, instructions, tools and channels
Open-source AI agent runtime with Docker and Postgres self-hosting
AI agent history and file storage
Connect tools with OpenAPI, MCP, or custom code
Deploy to Slack, Discord, Telegram, GitHub, or custom apps
Sandboxed code execution for agents
Support for multiple AI models from Anthropic, OpenAI, OpenRouter, Amazon Bedrock
Custom Discord bot building with testing before publishing
What makes it different
Separates evidence of agent behavior from infrastructure containment, so compliance is not mistaken for trustworthiness
Tests specific agents against explicit authority boundaries rather than universal safety claims
Preserves longitudinal behavioral history and repair lineage across retests
Works with multiple agent frameworks and supports customer-controlled environments
Enables evidence-backed behavioral testing without requiring production credentials
Thousands of agents at once without talking to sales
Open source agent runtime available for self-hosting
Agents survive crashes and deploys without losing history or pending work
camelAI