Phinq logo

Phinq

Freemium
Visitar

Phinq é uma camada open source de governança em tempo de execução para agentes de IA. Ela intercepta chamadas de ferramentas, classifica o risco e pausa ações de maior risco para obter aprovação humana antes da execução.

O que é 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.

O que Phinq pode fazer?

Intercepts tool calls at the boundary

Phinq observes agent tool calls before execution rather than relying on prompts or instructions the agent could ignore.

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.

Perguntas frequentes

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.

Informações rápidas

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

Análise de tráfego de Phinq

Os dados de tráfego são apenas para referência.

Classificação do domínio
0

Alternativas ao Phinq

Privent logo

Privent

www.privent.ai

Privent é uma camada de segurança em tempo de execução para IA agêntica, especialmente para fluxos de trabalho n8n. Mascara dados sensíveis antes que cheguem a modelos externos, mantém um registro das decisões de risco e monitora o uso organizacional de ChatGPT, Claude e Gemini.

Agentinel logo

Agentinel

agentinel.habitwala.in

Agentinel é uma camada de segurança local para agentes autônomos de programação: verifica solicitações de instalação antes da execução e bloqueia pacotes npm suspeitos usando um banco de dados OSV offline e heurísticas, sem chamadas à nuvem.

Sparkco logo

Sparkco

sparkco.ai

Sparkco: infraestrutura open source para agentes de IA, ferramentas focadas no terminal, fluxos para mercados de previsão e planos de agentes de voz por uso com crédito inicial, SMS, transcrições e integrações.

Kortix logo

Kortix

kortix.com

Kortix é um centro de comando de IA open source para empresas criarem, executarem e governarem agentes de IA em um só lugar. Oferece opções gratuita, para equipes e enterprise, com controles de governança, escolha de modelos e implantação flexível.

AgentConnect logo

AgentConnect

www.agentconnect.md

AgentConnect permite que as equipes integrem agentes ACP como Claude Code, Codex e Gemini CLI ao Slack, Telegram, Discord e GitHub, para que eles possam assumir tarefas nos mesmos canais em que as equipes já colaboram. É open source e pode ser hospedado por conta própria, com funções, ferramentas, memória e gatilhos configuráveis para fluxos de trabalho com agentes.

Kastra logo

Kastra

kastra.ai

Kastra é uma infraestrutura de autorização para sistemas de IA que verifica prompts, chamadas de ferramentas, comandos shell, solicitações de API e ações no navegador antes da execução. Ajuda as equipes a aplicar políticas, manter trilhas de auditoria assinadas e governar fluxos de trabalho de IA locais e empresariais.