Build autonomous multi-agent systems¶
JarvisCore is a Python framework for production multi-agent AI. Peer-to-peer coordination, composable memory, 46 service integrations, and full observability — from a single agent to a fleet.
46 Service Integrations
237+ Prebuilt Actions
4-tier Agent Memory
P2P Agent Mesh
What JarvisCore provides¶
Agent Profiles
Two execution models¶
AutoAgent runs a full OODA loop internally — observe, orient, decide, act. CustomAgent exposes the execution loop directly for deterministic control. Both share the same infrastructure.
Memory
Four-tier memory¶
Working scratchpad → episodic ledger → LLM-compressed long-term summaries → optional cross-session semantic memory via Athena MemOS. Context that survives restarts, scales across steps.
Communication
Peer-to-peer mesh¶
Agents discover and message each other via a PeerClient API. Routing, request-response, and broadcast work identically on a single process or across distributed machines.
Integrations
46 service integrations¶
Slack, GitHub, Zoom, SAP, NetSuite, MS Graph, Salesforce, and 40 more. 237+ prebuilt actions your agents can call directly — no glue code, no auth wiring.
Auth
Nexus credential layer¶
Agents call third-party APIs without ever touching raw credentials. OAuth2, API keys, and basic auth — all managed by Nexus and kept out of agent reasoning.
Observability
Full-stack tracing¶
Every agent turn, tool call, and LLM request is traced automatically. Redis PubSub for live streams, JSONL for compliance, Prometheus for operational dashboards.
Control
Human-in-the-loop¶
HITLQueue intercepts decisions that exceed confidence thresholds, routes them to a review inbox, and resumes execution once a human responds. First-class, not an afterthought.
Quickstart¶
pip install jarviscore-framework
jarviscore init
cp .env.example .env # add your LLM key
jarviscore check # verify dependencies
import asyncio
from jarviscore import Mesh, AutoAgent
class ResearcherAgent(AutoAgent):
name = "Researcher"
role = "researcher"
system_prompt = "You are a rigorous research analyst."
async def main():
mesh = Mesh()
mesh.add(ResearcherAgent)
await mesh.start()
result = await mesh.run_task(
agent="researcher",
task="What are the key architectural trade-offs in multi-agent systems?",
)
print(result)
asyncio.run(main())
Where to start¶
If you are new to JarvisCore, read in this order:
- Getting Started — install, configure, and run your first agent
- Architecture Overview — the mental model for how the framework fits together
- Agents — what an agent is, its identity and lifecycle
- Language Models — how JarvisCore uses multiple LLMs simultaneously
- Memory — how agents maintain and recover context
- Agent Personas — how profiles shape autonomous behaviour
If you are evaluating for a specific use case:
- AutoAgent Guide — autonomous reasoning agents
- CustomAgent Guide — deterministic worker agents
- System Bundles & Integrations — the full atom catalog
- Configuration Reference — all environment variables
- JarvisCore Enterprise — managed deployment and SLAs
Explore the ecosystem¶
| Reference | Full API surface, configuration keys, and CLI flags — view reference |
| Source | Browse the code, open issues, and submit PRs — GitHub |
| Community | Questions, showcases, and early feature previews — Discord |
| Blog | Engineering deep-dives and architecture walkthroughs — read the blog |