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 è un livello open source di governance a runtime per agenti AI. Intercetta le chiamate agli strumenti, le classifica in base al rischio e mette in pausa le azioni più rischiose per ottenere l’approvazione umana prima dell’esecuzione.
Cos'è 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.
Cosa può fare 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.
Casi d'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.
Domande frequenti
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.
Informazioni rapide
- 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
Analisi del traffico di Phinq
I dati sul traffico sono solo a scopo di riferimento.
- Domain Rating
- 0
Alternative a Phinq
Panguard AI
panguard.ai
Panguard AI è una piattaforma di sicurezza open source per agenti AI che analizza skill e server MCP prima dell’esecuzione e protegge le azioni degli agenti a runtime, offrendo controlli self-hosted e prove di conformità firmate a sviluppatori, fornitori AI e team soggetti a regolamentazione.
Kastra
kastra.ai
Kastra è un’infrastruttura di autorizzazione per sistemi di IA che verifica prompt, chiamate agli strumenti, comandi shell, richieste API e azioni del browser prima dell’esecuzione. Aiuta i team ad applicare le policy, mantenere audit trail firmati e governare i workflow di IA locali ed enterprise.
Agentinel
agentinel.habitwala.in
Agentinel è un livello di sicurezza locale per agenti di coding autonomi: verifica le richieste di installazione prima dell’esecuzione e blocca i pacchetti npm sospetti usando un database OSV offline ed euristiche, senza chiamate al cloud.
Arcade
arcade.dev
Arcade è un runtime MCP per agenti AI in produzione che combina autorizzazione degli agenti, strumenti affidabili e governance. Aiuta i team a collegare gli agenti ai sistemi reali, con opzioni di deployment flessibili e piani tariffari dal gratuito all’enterprise.
Sim
sim.ai
Sim è uno spazio di lavoro AI open source per creare, distribuire e gestire agenti AI, con flussi visivi, Chat, accesso API, integrazioni e strumenti di collaborazione.
Sparkco
sparkco.ai
Sparkco: infrastruttura open source per agenti AI, strumenti terminal-first, workflow per mercati predittivi e piani per agenti vocali a consumo con credito iniziale, SMS, trascrizioni e integrazioni.