Jev in production › SDKs and workflow integrations

JarvisCore (Prescott Data)

Python multi-agent framework that injects a Jev client as self.decisions for Choice, Score and Noul judgments, with opt-in Jev subagent routing, model-tier selection and RAG passage filtering. Three questions in one call: 434 ms median warm (company).

Open on GitHub ↗

434 ms median warmmeasured, as published by the source
Use
SDKs and workflow integrations
Industry
AI infrastructure
Form
Open-source tool
Stage
In production
Listed
2026-09-20
Found via
github
Repository
Prescott-Data/jarviscore-framework
Stars
125
Forks
17
Last push
2026-11-18
Language
Python
License
Apache-2.0
JarvisCore (Prescott Data) screenshot
jarviscore/docs/assets/readme/mesh-vs-orchestrator.png in the Prescott-Data/jarviscore-framework README, Apache-2.0; shown from GitHub.

The README opens with

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.

Most agent frameworks put one orchestrator in charge: it plans, routes every request and holds the state, so the system is only as available as that one process. On a JarvisCore mesh, every agent is a peer. Peers find each other by what they can do (SWIM gossip), take steps from a shared ledger (Redis) and record what they did there, so when one stops, another claims its step and the work goes on. None of them holds a credential: the Nexus broker places it at the call.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for sdks and workflow integrations