Intercepts tool calls at the boundary
Phinq observes agent tool calls before execution rather than relying on prompts or instructions the agent could ignore.
Phinq
Freemium
Phinq es una capa de gobernanza en tiempo de ejecución de código abierto para agentes de IA. Intercepta sus llamadas a herramientas, clasifica el riesgo y pausa las acciones de mayor riesgo para obtener aprobación humana antes de ejecutarlas.
¿Qué es Phinq?
Phinq is an open source runtime governance layer for AI agents. It sits between an agent’s proposed tool call and the execution boundary, classifies the request by risk, and either allows it to pass or holds it for approval.
The product is meant to reduce damage from irreversible agent actions such as deletes, credential reads, payments, or external messages. It records each decision in an append-only, hash-chained audit log so teams can review what the agent attempted and how the request was resolved.
¿Qué puede hacer Phinq?
Classifies requests by risk
The system evaluates the proposed action using the tool name, arguments, and session velocity, then returns an allow or hold decision.
Holds irreversible actions for approval
Higher-risk actions are paused instead of forwarded until a human approves them through the configured channel.
Fails closed on unanswered holds
If a held action is denied or times out, the action is blocked and never reaches the tool.
Records a tamper-evident audit chain
Every decision is written to an append-only JSONL log with SHA-256 chaining so later edits, reordering, or deletion can be detected.
Runs in multiple integration modes
Phinq can run as a proxy, an in-process SDK, or a plain HTTP gate, and the docs list compatibility with OpenAI-style, Anthropic Messages, Gemini, and MCP-based clients.
Casos de uso
“Approve dangerous agent actions before they execute”
Use Phinq when an assistant may need to delete records, read credentials, send payments, or dispatch messages, but you want a human decision point before the action reaches the tool.
“Add governance to existing agent stacks”
Teams can place Phinq at the proxy, SDK, or HTTP boundary instead of rewriting the agent workflow, which makes it suitable for systems already using compatible clients or MCP.
“Keep an audit trail of agent decisions”
Phinq is useful when you need to review what an agent attempted, how it was classified, and whether it passed, held, approved, denied, or timed out.
“Start in observe-only mode before enforcement”
The docs say the proxy starts in shadow mode by default, which lets teams classify and log traffic before enforcing holds in production.
Preguntas frecuentes
What does Phinq do?
Phinq is a runtime governance layer for AI agents that intercepts tool calls, classifies them by risk, and holds higher-risk actions for human approval before execution.
How does Phinq decide whether to allow an action?
The docs say it evaluates the proposed tool call using the tool name, arguments, and session velocity, then returns allow or hold.
Does Phinq enforce decisions by default?
No. The documentation says the proxy starts in shadow mode by default, meaning it classifies and logs traffic first and only enforces HOLD decisions when enforcement is enabled.
What happens when a risky action is held?
The action becomes a pending approval instead of being forwarded. It can then be resolved through the configured channel; denied or timed-out holds are blocked.
Is the audit log tamper-evident?
Yes. The audit log is append-only JSONL and each entry is chained with SHA-256, so changing, reordering, or deleting entries breaks verification.
Datos rápidos
- Category
- Developer Tool
- Product type
- Open source runtime governance layer
- Primary function
- Classifies AI agent tool calls and pauses risky actions for approval
- Deployment modes
- Proxy, TypeScript SDK, plain HTTP gate
- Documentation domain
- phinq.co
- License
- MIT
Análisis de tráfico de Phinq
Los datos de tráfico son solo como referencia.
- Valoración del dominio
- 0
Alternativas a Phinq
Panguard AI
panguard.ai
Plataforma de seguridad de código abierto para agentes de IA que analiza habilidades y servidores MCP antes de ejecutarlos y protege sus acciones en tiempo de ejecución.
Privent
www.privent.ai
Capa de seguridad en tiempo de ejecución para agentes de IA que protege datos sensibles en flujos de n8n y supervisa el uso de herramientas de IA en toda la organización.
Browser Use
browser-use.com
Plataforma de automatización de navegadores para agentes de IA, con herramientas de código abierto y servicios en la nube para navegar con discreción, ejecutar tareas y extraer datos estructurados a escala.
MindsHub
mindsdb.com
Plataforma de agentes de IA de código abierto para delegar tareas completas, conectar datos y herramientas, elegir modelos y crear artefactos compartibles sin configurar claves de API de cada proveedor.
Dagworks
dagworks.io
DAGWorks ofrece herramientas de código abierto y alojadas para crear flujos de trabajo de IA fiables, con Apache Hamilton para canalizaciones de datos, ML y LLM, y Apache Burr para aplicaciones y agentes con estado.
Sparkco
sparkco.ai
Proyecto de investigación de código abierto para infraestructura de agentes de IA, herramientas centradas en la terminal y flujos de trabajo orientados a mercados de predicción.