Phinq
Open source runtime governance layer intercepting AI agent tool calls to enforce risk policies and record tamper-evident audit logs.
Open productWhat it does
About Phinq
Phinq is an open source runtime governance layer built for AI agents. Deployed as a proxy, in-process SDK, or HTTP gate, Phinq intercepts agent tool calls directly at the API or execution boundary to enforce structural risk rules rather than relying on advisory prompts. Safe actions pass automatically, while sensitive operations like deletions, credential reads, payments, or bulk sends are held for human approval. If an action is denied or times out, Phinq fails closed to block execution. Every decision is recorded in an append-only, hash-chained audit log for verification.
- Availability:
- launched
- Access:
- free
- Format:
- software
- Platform:
- api
Pricing at launch: Open source software distributed under the MIT license.
Core capabilities
Boundary Interception and Risk Classification
Intercepts tool execution requests at the API boundary, classifying risk levels to let safe calls pass while holding sensitive actions for authorization.
Fail-Closed Policy Enforcement
Keep discovering
Related debuts
Continue with products that solve a similar problem or serve the same kind of maker.
