omnirexflora-labs/omnicoreagent

Every action checked before it runs. Every run survives a crash without silently redoing anything. Every step on the record.
Docs ·
Quickstart ·
Cookbook ·
Proof ·
How it compares ·
For your coding agent ·
Known issues ·
Ask AI
A model is not an agent. The runtime around it is what makes it usable in an
application: the loop, the tools, memory, the files it works on, and — once
the agent can do real things — the policy that says what it may do, the
sandbox its code runs in, the record that survives a crash, the budget that
stops it spending, and the evidence a person can read afterwards.
OmniCoreAgent is an agent runtime for Python. It includes the harness,
the loop, tools, context, workspace and sub-agents around the model, and adds
what running an agent for real needs: a policy on every action, a sandbox as
the boundary for its commands, runs that survive a crash, budgets, and a record
of every step. You use it from Python, from the command line, or as an HTTP
server: one agent object, from a first script to a governed background worker,
and onto a benchmark.
| Layer | What it is | What it gives you |
| The harness | the loop around the model | tools (yours and MCP), context and memory, a workspace, code mode, skills, sub-agents and worker profiles |
| Control | decided before every action | a policy (allow, ask a person, or refuse), approvals, budgets, a sandbox that is the boundary for commands |
| Durability | a record every run keeps | pause and resume, survive a crash without redoing work, take over from a dead process |
| The record | the evidence of every run | one trace per run, readable start to finish, private by default, exported where you want it |
How it fits together
walks one run through all four.
## Install
bash
pip install omnicoreagent # Python 3.12–3.14; check with python --version
export LLMAPIKEY=yourapikey # the key for the provider in modelconfig
On Python 3.10 or 3.11, the install stops and says so.
## Quick start
python
import asyncio
from omnicoreagent import OmniCoreAgent, ToolRegistry
tools = ToolRegistry()
@tools.registertool("lookuporder")
def lookuporder(orderid: str) -> dict:
"""Look an order up in the application's own store."""
return {"orderid": orderid, "status": "shipped", "carrier": "DHL"}
agent = OmniCoreAgent(
name="support",
systeminstruction="You answer questions about orders, using the tools. Answer in plain text.",
modelconfig={"provider": "openai", "model": "gpt-5.6-terra"},
localtools=tools,
async def main():
result = await agent.run("Where is order 1042?", sessionid="customer-7")
print(result["response"])
# Every run is evidence: each step, what the model asked for,
# and what it received back.
trajectory = await agent.gettrajectory(result["traceid"])
for step in trajectory["steps"]:
for call in step["toolcalls"]:
print(step["step"], call["toolname"], call["arguments"], "->", call["observation"]["content"])
# What the run turned out to be worth, whenever that is known ...
await agent.recordoutcome(result["runid"], source="support-lead", reward=1.0, label="resolved")
# ... and the run as one record for an evaluator or a trainer.
[record] = await agent.trainingrecords(runid=result["runid"])