AgentOracle
Pre-action verification for AI agents. When signing succeeds, /evaluate and /v1/verify-facts return signed receipts whose signatures can be checked offline with the published public keys; retired keys stay published.
AgentOracle at a Glance
- How you use it
- API or local MCP server
- Who it's for
- Agent platform builders, compliance and audit teams, and regulated operators
- Works with
- Cursor Claude Desktop Codex
AgentOracle Key Features
- MCP receipt verification
- Offline receipt verification
- Pre-action claim checks
- Signed verification receipts
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
AgentOracle Alternatives
Guardrails AI
The AI Reliability Platform
Highflame
Highflame is the AI agent security platform: a verifiable identity for every agent and an authorization decision for every action, enforced inline across LLM and MCP traffic.
agentsystems
Open-source infrastructure for AI sovereignty and governance.
TapVow
TapVow is a local gateway that checks signed mandates and estimated reservations for supported AI API calls, with virtual keys and verifiable signed receipts.
attestix
Verifiable agent identity, signed credentials, delegation and portable governance evidence. Open source under Apache 2.0.
VulnClaw
基于 AI Agent + MCP 工具链 + 渗透 Skill 编排， 配合大语言模型， 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。 - Netw0rkNoob/VulnClaw