CalibratedDecisions.

Repo · SDKs & integrations

JarvisCore

Python multi-agent runtime (peer-to-peer mesh, durable state, integration atoms) with a typesafe extra that injects a shared Jev client as…

Open github.com ↗

From the repository

JarvisCore is a runtime where AI agents operate as a fleet of equal peers. Agents discover one another by capability, execute tasks from a shared ledger, and authenticate to every external service through a zero-trust broker, never with their own keys.

agentsaiai-agentsaiagentframeworkllms

How builders describe it

Python multi-agent runtime (peer-to-peer mesh, durable state, integration atoms) with a typesafe extra that injects a shared Jev client as self.decisions and can route subagents, task complexity and RAG passages with Jev.
Python multi-agent runtime that ships Jev natively in an optional extras install: agents ask typed Choice, Score and Noul questions through a shared decision client, the Kernel can pick specialist subagents by Choice, and RAG passages with a prompt-injection Noul above 0.70 are withheld.
I maintain JarvisCore an open-source Python framework for multi-agent systems. When Jev launched I started poking at it, and ended up shipping native support in our 1.12 release today . It now drives four things, all opt-in: typed agent decisions, which specialist subagent takes a task, task…

The decision Jev makes

Any Jev question: yes or no, a choice, or a score, from your own stack.

Where it fits

Official and community SDKs, MCP servers and integrations for calling Jev from the languages and tools you already use. All 625 sdks & integrations projects →

Related projects