yagna-1/astragraph
Policy-enforced observability and fail-closed guardrails for MCP/A2A multi-agent systems.
AstraGraph helps AI application developers enforce safety and compliance in their multi-agent systems. It acts as a gateway, evaluating every agent action against predefined policies. It takes in agent actions and outputs real-time audit trails and a causal graph of interactions, which developers can query to understand and investigate system behavior.
Use this if you are building multi-agent AI applications and need to prevent unsafe actions, ensure policy compliance, and have a clear, real-time audit trail of all agent interactions.
Not ideal if you are working with single-agent systems or do not require strict policy enforcement and detailed observability for AI workflows.
Stars
24
Forks
2
Language
Rust
License
—
Category
Last pushed
Feb 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/yagna-1/astragraph"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GetBindu/Bindu
Bindu: Turn any AI agent into a living microservice - interoperable, observable, composable.
opena2a-org/agent-identity-management
AIM - The open-source NHI platform for AI agents. Cryptographic identity, governance, and access control.
kanoniv/agent-auth
Cryptographic identity and delegation for AI agents
peacprotocol/peac
PEAC Protocol: Verifiable interaction records for AI agents and automated systems
openwallet-foundation-labs/sd-jwt-dotnet
Selective Disclosure for JWTs (SD-JWT) .Net implement